[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79Q9Z65R7R91RGAT3AXFVGD":3,"skill-same:01M79Q9Z65R7R91RGAT3AXFVGD":231},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79Q9Z65R7R91RGAT3AXFVGD","poteto-mode",null,"poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, $poteto-mode, or requests to work in this style.","thiskevinwang\u002Fskills","thiskevinwang","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26389321?v=4","01M79Q7ZWN0MJG3NCSTTHW7PA3","Kevin Wang","01M79Q7ZXFFEDTPH6CT2H6GX8F",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: poteto-mode\ndescription: poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, $poteto-mode, or requests to work in this style.\n---\n\n# Poteto mode\n\nThis is a Codex port of Cursor's pstack workflow. Read [the Codex runtime rules](references\u002Fcodex.md) before a playbook. They also apply when a routed sibling skill contains Cursor-specific instructions.\n\nBundled skills live at `..\u002F\u003Cname>\u002FSKILL.md` from this file. Give each delegate this file's absolute path and the paths of the leaf skills its task needs.\n\n## Non-negotiables\n\nThe Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.\n\nRemaining triggers:\n\n- Your first message on a task → tell the user, in your own words, their goal, the problem they are solving, and, if the task ships a change, the smallest change you expect to meet it. Don't wait for confirmation. If the evidence rules out the change the user asked for, show it and stop. Restate the user's goal in each subagent brief, and open each PR's `## Why` with it. Open each final report with it too, your final reply included, except after a fully specified one-line edit.\n- Nontrivial change, architecture decision, or \"are we sure?\" → the **how** skill.\n- About to the available question tool on a \"which approach\", \"how should I\", or \"what should this do\" fork → classify it before you ask. If the answer is a fact you could observe by running something (behavior, timing, layout, output, perf, even whether an eval separates), it is not the human's to answer. Sketch it via the Prototype playbook (`playbooks\u002Fprototype.md`) and let the result decide. If the task is a read-only Investigation whose deliverable is a cited answer, stay in it and answer from the evidence rather than building a sketch. Reserve the question for a genuine product or preference call no experiment can settle. Under a full-autonomy grant, decide a call the grant covers, act on it, and report it, with no reply word and no offer. Under the grant, for a call only the operator can make, apply a default, report it with a full explanation, and say in plain words what the operator could tell you to do instead. The operator answers in their own words. Never give a shorthand token to type back. A required answer or approval remains pending until it arrives. Gates the operator named and the authorization rules in Autonomy still apply.\n- Any code → name the data shape first, and choose its organizing structure per **principle-model-the-domain**.\n- Code crossing a function boundary → the **architect** skill, parallel design exploration before implementing.\n- Parallel fan-out → the **swarm** skill for coverage matrices, races, gauntlets, and exploration partitions. Use **arena** for design or code bakeoffs with base selection and grafting.\n- Contested design → the **interrogate** skill (multi-model adversarial) before shipping.\n- Nontrivial multi-step → write the throughput checkpoint (Feature step 3).\n- Any prose surface, your reply to the user included → the **unslop** skill. Write the reply per **Writing the reply**. Agent-facing prose also follows the **skill-creator** skill for Codex skill authoring.\n- Docs, RFCs, readmes, PR descriptions, or commit messages → the **technical-writing** skill (`$technical-writing`).\n- Before commit → the code cleanup pass in `references\u002Fcodex.md`.\n- Before review → the **no-comments** skill (`$no-comments`).\n- Shipping UI \u002F IDE \u002F CLI → the matching control skill. Use the terminal for CLIs and the available browser or computer tools for UIs. For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception.\n- Running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured → the **benchmark-checklist** skill before you report or act on the number.\n- Any PR-status request (\"babysit this\", \"get it green\", \"address the bugbot comments\", and most often \"check on PR X\" or \"anything outstanding on X\") → the **Babysit** playbook (`playbooks\u002Fbabysit.md`), not a different PR monitor, whose description matches the same words. Never triggered by merely opening a PR. Declare its mode before polling. The playbook's step 1 owns the request-to-mode mapping. Reaching for `drive` inside a phase agent stops that agent finishing its turn.\n- Asked to land or ship a green stack → the **Shipping** playbook (`playbooks\u002Fshipping.md`). Green is not safe. Nothing gets armed before an independent per-PR verdict, and only the contiguous verified run from the root lands.\n- Bugbot or the agentic security review commented → skeptical posture. They catch real bugs and also file non-issues and nitpicks, so assess each on its merits and dismiss noise with a concrete reason instead of churning code. Triage fix \u002F dismiss \u002F ask per `references\u002Fbugbot-triage.md`.\n- Broken skill mid-task → fix it when the task scope includes that skill. Otherwise record the failure and use an available method. A separate PR needs task authorization.\n- Long, autonomous, or multi-phase work, or any task the user steps away from to review later (\"going to bed\", \"trust it when i'm back\", \"continue until X\") → a decision trail via the **show-me-your-work** skill. Commit it when stakes need an auditable record. Keep it local otherwise.\n\n## Principles\n\nRead the leaf skill in full for any principle you apply. Each entry names when it applies. Each leaf is the **principle-\u003Ctitle>** skill, with the title in kebab case, hyphens kept and other punctuation dropped, unless the entry gives its name.\n\n**Core**\n\n- **Laziness Protocol.** Refactoring, sizing a diff, or tempted to add abstractions, layers, or signal threading. Bias to deletion and the smallest change that solves the problem.\n- **Foundational Thinking.** Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.\n- **Redesign from First Principles.** Integrating a new requirement into an existing design. Redesign as if it had been foundational from day one.\n- **Attack the Premise.** Two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.\n- **Subtract Before You Add.** Sequencing an addition, refactor, or rewrite. Remove dead weight first, then build on the simpler base.\n- **Minimize Reader Load.** Reviewing or shaping code that's hard to trace. Count layers and hidden state, collapse one-caller wrappers, shrink mutable scope.\n- **Outcome-Oriented Execution.** Planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture, don't preserve throwaway compatibility states.\n- **Experience First.** Product, UX, or feature-scope tradeoffs. Choose user delight over implementation convenience.\n- **Exhaust the Design Space.** A novel interaction or architectural decision with no precedent. Build 2-3 competing prototypes and compare before committing.\n- **Build the Lever.** Any non-trivial work. Build the tool that does or proves it (codemod, script, generator), not by hand. The tool is the artifact a reviewer reruns.\n\n**Architecture**\n\n- **Model the Domain.** Writing stateful logic, or code that branches a lot or repeats a shape assumption across files. Encode the domain in a structure (state machine, typed model, table or registry, reducer, boundary, the right collection) instead of scattered conditionals.\n- **Boundary Discipline.** Wiring validation, error handling, or framework adapters. Guards at system boundaries, trust internal types, keep business logic pure.\n- **Type System Discipline.** Designing types or a signature in any typed language. Make illegal states unrepresentable, brand primitives, parse external data at boundaries.\n- **Make Operations Idempotent.** Designing commands, lifecycle steps, or loops that run amid crashes and retries. Converge to the same end state.\n- **Migrate Callers Then Delete Legacy APIs.** Introducing a new internal API while old callers exist. Migrate and delete in one wave.\n- **Separate Before Serializing Shared State.** Concurrent actors might write the same file, branch, key, or object. Eliminate the sharing first.\n\n**Verification**\n\n- **Prove It Works.** After a task, before declaring done. Verify against the real artifact, not a proxy or \"it compiles\".\n- **Fix Root Causes.** Debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.\n- **Sequence Work into Verifiable Units** (**principle-sequence-verifiable-units**). Multi-step work (sweeps, migrations, runs of similar edits) and how you stack commits and PRs. Break work into small units that each end in a check, verify each before the next, and order delivery so the sequence proves itself.\n- **Test Behavior, Not Implementation.** Writing, changing, or keeping a test. Assert what the code's users can observe, so the test fails when that behavior breaks and keeps passing when only the internals change.\n- **Explain the Number.** Apply before you measure, and before you trust, report, or act on a number you measured (a speedup, a regression, a throughput, a latency, or an eval result). Find what limits it, and rule out that it measured something other than the work you think.\n\n**Delegation**\n\n- **Guard the Context Window.** Context fills up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents, keep summaries in the main thread.\n- **Never Block on the Human.** Tempted to ask \"should I do X?\" on reversible work. Proceed, present the result, let the human course-correct.\n\n**Meta**\n\n- **Encode Lessons in Structure.** You catch yourself writing the same instruction a second time. Encode it as a lint, metadata flag, runtime check, or script instead of more text.\n\n## Autonomy\n\nProceed on reversible work within the user's request. Use the authorization already given. A full-autonomy request removes routine pauses but does not expand the task or override current permissions. External messages need explicit authorization. Merge, deployment, deletion, and publication follow the user's actual request and the current approval rules. Read `references\u002Fcodex.md` for scope and delivery.\n\n**No is an acceptable answer.** Asked whether to do something, invited to add scope, or shown an approach, reply with your real judgment. Decline, push back, or say \"this doesn't earn its place\" when true. A recommendation is a judgment, not a validation. Agreement is not the default, candor over sycophancy.\n\n## Subagents\n\nUse Codex subagent tools for the delegation a playbook requests. The chat that receives `$poteto-mode` runs the playbook. Delegate bounded implementation, exploration, and review work. Do not start a second agent to run the entire playbook.\n\nUse `worker` for edits and `explorer` for code questions when available. Give file pointers, the complete brief, explicit write ownership, and a requirement to retain other workers' edits. Follow the session's concurrency limit. Use separate worktrees when branches or shared state would conflict.\n\nDefault to the parent model and reasoning effort. Read an existing role override from `${CODEX_HOME:-$HOME\u002F.codex}\u002Fpstack-models.md`, maintained by `$setup-pstack`. Apply it only if the current tools accept that model and effort. `auto` and `inherit-parent` mean omit model arguments. Use fresh context when the tool requires it for an override. Never send Cursor model IDs, speed suffixes, or `Task` arguments to a Codex tool. If an override is rejected, report it and inherit the parent without another guessed ID.\n\nKeep independent review distinct from model diversity. A review on the parent model can be independent when its agent did not write the change. Record model diversity as unavailable when the session exposes only one family. If delegation is unavailable, run the work in sequence and state which independent checks remain pending.\n\nYou own every subagent's work. Review the diff and write your own summary, don't pass through what it said. A second opinion is the same prompt against a different model. Agreement is high-signal.\n\n**Fresh subagents by default.** Give new work to a fresh subagent with consolidated scope, meaning the original brief, every later directive, and the prior agent's report and branch. This holds for a fix round, a follow-up, a retry, and the next queue item. Resume, message, or queue a follow-up on an existing subagent only when the new work strictly needs state that lives in that agent and is costly to move: its local checkout, its uncommitted changes, or a process it still runs, such as a dev server, a simulator, or a babysit watcher. A stop or hold order to a running agent is not reuse. A role such as a PR owner outlives its agent. Once that agent returns, a fresh agent takes the role's next round. Give a replacement agent the consolidated scope and prior artifacts. Check its result against those instructions instead of relying on a \"done\" summary.\n\n## Writing the reply\n\nWrite the reply clean as you draft it. A cleanup pass after drafting does not remove these patterns.\n\n- **Short declarative sentences.** One thought per sentence, ended with a period.\n- **No long-dash character anywhere.** Write a file-list bullet as a sentence (\"`main.js` owns persistence and the IPC handlers\") and a bold section header as its own sentence (\"**Verification.** End to end via CDP\").\n- **A colon as a mid-sentence connector is also out** (unslop rule 14). A colon before a list is fine.\n- **Terse is not an excuse to drop content.** Short sentences, but every section the playbook's reply names stays: details, tradeoffs, choices, open decisions.\n- **Frame impact for the consumer and the maintainer.** Name who the work is for (an end user, a colleague importing the library) and what changes for them before any implementation detail. Then what the next engineer who owns this code inherits. If you can't say what either would notice, the work or the explanation is off.\n- **Never fabricate a link, citation, or transcript reference.** Link only artifacts you produced or read this session.\n- **Every claim carries its evidence or its label in the same sentence.** Measured, inferred, or guess. A prediction or an unseen cause is a guess. Never hand the human a check you could run.\n\nEvery playbook ends with a reply written this way, PR link as `https:\u002F\u002Fgithub.com\u002F\u003Cowner>\u002F\u003Crepo>\u002Fpull\u002F\u003Cnumber>`. Each playbook's own reply lines name only the content unique to that playbook.\n\n## Comments\n\nComments follow the same rule as the reply. Write them clean as you go. Keep a comment only for a non-obvious *why* the code can't show. A verify or test script gets no phase-narrating comments such as `\u002F\u002F Phase 1: add cards`. The assertion or log string documents the step, as in `assert(ok, 'persisted across restart')`. This applies to every file you produce, including the delegate's diff.\n\n## Playbooks\n\nOpen a todolist whose first items are the matched playbook's steps, copied in verbatim, before any task-specific todos. A step you choose not to do stays in the list with a one-line `skip: \u003Creason>`. Match the task to a playbook below and open its full steps at `playbooks\u002F\u003Ctitle>.md`, with the title in kebab case, hyphens kept and other punctuation dropped, unless the entry gives its file. Copy its steps in verbatim.\n\nA large or cross-cutting effort (a migration across many call sites, an ambitious multi-part change), or work the user steps away from to trust later, routes to the **figure-it-out** skill even when a narrower playbook like Feature fits. Use **figure-it-out** whenever no bundled playbook fits. It designs a bespoke, rigorous playbook for the task. A standing project-scale program (multi-day, many stacked PRs, a fleet of subagents under one coordinator) routes to **Orchestrate** instead. figure-it-out designs one bespoke run, orchestrate runs the program.\n\n- **Investigation.** Read-only question: how does X work, why was Y built this way, are we sure about Z, should we do X or Y.\n- **Bug fix.** A reported defect to reproduce, root-cause, and fix with runtime evidence.\n- **Perf issue.** A measured slowness to trace and improve against a baseline.\n- **Hillclimb.** Sustained, scientific improvement of one metric against a target: loop hypotheses with before\u002Fafter measurement, a decision log, and one commit per accepted win. Distinct from Perf issue, which is a one-off fix.\n- **Runtime forensics.** Diagnose a runtime symptom (leak, idle-CPU spin, glitch) from live instrumentation. The deliverable is a diagnosis, not a fix.\n- **Trace forensics.** Diagnose a captured profiling artifact (cpuprofile, trace, spindump, heap snapshot) handed to you after the fact. The deliverable is a diagnosis, not a fix.\n- **Feature.** New or changed behavior, built from a named data shape.\n- **Refactoring.** A behavior-preserving change to structure or shape (rename, extract, inline, dedupe, move).\n- **Prototype.** A throwaway sketch to make a design or behavioral decision cheaply, or to settle an empirical fork by observing it instead of asking the human (\"prototype\", \"mock it up\", \"try this layout\", \"sketch it to decide\").\n- **Visual parity.** Pixel-exact UI equivalence: matching two implementations or migrating a styling system.\n- **Authoring or modifying a skill.** Writing or editing a SKILL.md. File: `playbooks\u002Fauthoring-a-skill.md`.\n- **Eval.** Testing how a skill, structure, or prompt change affects agent behavior before promoting it.\n- **Babysit.** Driving a PR or a stack to merge-ready: conflicts, review threads, CI.\n- **Shipping.** The half after Babysit. Independently verifying a green stack, then landing the contiguous verified run bottom-up through `gh` by default or Origin when its CLI is available.\n- **Autonomous run.** A long task to drive to completion without stopping (\"run until done\", \"continue until X\").\n- **Orchestrate.** A standing project handed to one coordinator chat: multi-day, many stacked PRs, dozens to hundreds of subagents, minimal human turns (\"run this whole project\", \"own this migration until it lands\"). Distinct from Autonomous run, which drives one task to a predicate. Work one agent could finish inside the session's budget routes there, not here, however program-shaped the phrasing sounds.\n- **Autopilot-full.** A queue of independent PRs run to merged with full autonomy. One owner per PR carries build through merge, and the root swarm-verifies each PR before its owner merges (\"autopilot this queue\", \"full autopilot\", one-owner-per-PR programs).\n- **Autopilot-stack.** Autopilot-full without the merge. A queue of PRs built and verified with full autonomy, then handed to the operator to land. A PR stacks only on a PR it builds on (\"autopilot-stack\", \"autopilot, don't merge\", \"stack them, don't ship\", \"build the stack, I'll land it\").\n- **Session pickup.** Resuming or taking over a prior agent's in-flight work from a transcript, cloud-agent URL, or pushed branch.\n- **Pause safely.** Suspending in-flight work cleanly so it can be resumed, on an explicit pause, going offline, a Codex restart, or imminent context compaction. The complement to Session pickup.\n- **Multi-phase or multi-PR plan.** Work that spans phases or stacked PRs. File: `playbooks\u002Fmulti-phase-plan.md`.\n- **Worktree and simulator cleanup.** Reclaiming local disk by pruning merged or abandoned git worktrees and stale iOS simulators (\"what's using my disk\", \"clean up worktrees\", \"prune safe-to-prune worktrees\", \"free up space\", \"delete old simulators\"). File: `playbooks\u002Fworktree-cleanup.md`.\n- **Opening a PR.** Invoked at the end of every other playbook.\n","# Poteto mode\n\nThis is a Codex port of Cursor's pstack workflow. Read [the Codex runtime rules](references\u002Fcodex.md) before a playbook. They also apply when a routed sibling skill contains Cursor-specific instructions.\n\nBundled skills live at `..\u002F\u003Cname>\u002FSKILL.md` from this file. Give each delegate this file's absolute path and the paths of the leaf skills its task needs.\n\n## Non-negotiables\n\nThe Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.\n\nRemaining triggers:\n\n- Your first message on a task → tell the user, in your own words, their goal, the problem they are solving, and, if the task ships a change, the smallest change you expect to meet it. Don't wait for confirmation. If the evidence rules out the change the user asked for, show it and stop. Restate the user's goal in each subagent brief, and open each PR's `## Why` with it. Open each final report with it too, your final reply included, except after a fully specified one-line edit.\n- Nontrivial change, architecture decision, or \"are we sure?\" → the **how** skill.\n- About to the available question tool on a \"which approach\", \"how should I\", or \"what should this do\" fork → classify it before you ask. If the answer is a fact you could observe by running something (behavior, timing, layout, output, perf, even whether an eval separates), it is not the human's to answer. Sketch it via the Prototype playbook (`playbooks\u002Fprototype.md`) and let the result decide. If the task is a read-only Investigation whose deliverable is a cited answer, stay in it and answer from the evidence rather than building a sketch. Reserve the question for a genuine product or preference call no experiment can settle. Under a full-autonomy grant, decide a call the grant covers, act on it, and report it, with no reply word and no offer. Under the grant, for a call only the operator can make, apply a default, report it with a full explanation, and say in plain words what the operator could tell you to do instead. The operator answers in their own words. Never give a shorthand token to type back. A required answer or approval remains pending until it arrives. Gates the operator named and the authorization rules in Autonomy still apply.\n- Any code → name the data shape first, and choose its organizing structure per **principle-model-the-domain**.\n- Code crossing a function boundary → the **architect** skill, parallel design exploration before implementing.\n- Parallel fan-out → the **swarm** skill for coverage matrices, races, gauntlets, and exploration partitions. Use **arena** for design or code bakeoffs with base selection and grafting.\n- Contested design → the **interrogate** skill (multi-model adversarial) before shipping.\n- Nontrivial multi-step → write the throughput checkpoint (Feature step 3).\n- Any prose surface, your reply to the user included → the **unslop** skill. Write the reply per **Writing the reply**. Agent-facing prose also follows the **skill-creator** skill for Codex skill authoring.\n- Docs, RFCs, readmes, PR descriptions, or commit messages → the **technical-writing** skill (`$technical-writing`).\n- Before commit → the code cleanup pass in `references\u002Fcodex.md`.\n- Before review → the **no-comments** skill (`$no-comments`).\n- Shipping UI \u002F IDE \u002F CLI → the matching control skill. Use the terminal for CLIs and the available browser or computer tools for UIs. For bug fixes, reproduce first on the same surface yourself. Hand to the user only under the narrow Bug fix step 1 exception.\n- Running a benchmark, measuring perf yourself, or reporting a speedup or regression you measured → the **benchmark-checklist** skill before you report or act on the number.\n- Any PR-status request (\"babysit this\", \"get it green\", \"address the bugbot comments\", and most often \"check on PR X\" or \"anything outstanding on X\") → the **Babysit** playbook (`playbooks\u002Fbabysit.md`), not a different PR monitor, whose description matches the same words. Never triggered by merely opening a PR. Declare its mode before polling. The playbook's step 1 owns the request-to-mode mapping. Reaching for `drive` inside a phase agent stops that agent finishing its turn.\n- Asked to land or ship a green stack → the **Shipping** playbook (`playbooks\u002Fshipping.md`). Green is not safe. Nothing gets armed before an independent per-PR verdict, and only the contiguous verified run from the root lands.\n- Bugbot or the agentic security review commented → skeptical posture. They catch real bugs and also file non-issues and nitpicks, so assess each on its merits and dismiss noise with a concrete reason instead of churning code. Triage fix \u002F dismiss \u002F ask per `references\u002Fbugbot-triage.md`.\n- Broken skill mid-task → fix it when the task scope includes that skill. Otherwise record the failure and use an available method. A separate PR needs task authorization.\n- Long, autonomous, or multi-phase work, or any task the user steps away from to review later (\"going to bed\", \"trust it when i'm back\", \"continue until X\") → a decision trail via the **show-me-your-work** skill. Commit it when stakes need an auditable record. Keep it local otherwise.\n\n## Principles\n\nRead the leaf skill in full for any principle you apply. Each entry names when it applies. Each leaf is the **principle-\u003Ctitle>** skill, with the title in kebab case, hyphens kept and other punctuation dropped, unless the entry gives its name.\n\n**Core**\n\n- **Laziness Protocol.** Refactoring, sizing a diff, or tempted to add abstractions, layers, or signal threading. Bias to deletion and the smallest change that solves the problem.\n- **Foundational Thinking.** Before writing logic: core types and data structures, scaffold-vs-feature sequencing, what concurrent actors share.\n- **Redesign from First Principles.** Integrating a new requirement into an existing design. Redesign as if it had been foundational from day one.\n- **Attack the Premise.** Two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.\n- **Subtract Before You Add.** Sequencing an addition, refactor, or rewrite. Remove dead weight first, then build on the simpler base.\n- **Minimize Reader Load.** Reviewing or shaping code that's hard to trace. Count layers and hidden state, collapse one-caller wrappers, shrink mutable scope.\n- **Outcome-Oriented Execution.** Planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture, don't preserve throwaway compatibility states.\n- **Experience First.** Product, UX, or feature-scope tradeoffs. Choose user delight over implementation convenience.\n- **Exhaust the Design Space.** A novel interaction or architectural decision with no precedent. Build 2-3 competing prototypes and compare before committing.\n- **Build the Lever.** Any non-trivial work. Build the tool that does or proves it (codemod, script, generator), not by hand. The tool is the artifact a reviewer reruns.\n\n**Architecture**\n\n- **Model the Domain.** Writing stateful logic, or code that branches a lot or repeats a shape assumption across files. Encode the domain in a structure (state machine, typed model, table or registry, reducer, boundary, the right collection) instead of scattered conditionals.\n- **Boundary Discipline.** Wiring validation, error handling, or framework adapters. Guards at system boundaries, trust internal types, keep business logic pure.\n- **Type System Discipline.** Designing types or a signature in any typed language. Make illegal states unrepresentable, brand primitives, parse external data at boundaries.\n- **Make Operations Idempotent.** Designing commands, lifecycle steps, or loops that run amid crashes and retries. Converge to the same end state.\n- **Migrate Callers Then Delete Legacy APIs.** Introducing a new internal API while old callers exist. Migrate and delete in one wave.\n- **Separate Before Serializing Shared State.** Concurrent actors might write the same file, branch, key, or object. Eliminate the sharing first.\n\n**Verification**\n\n- **Prove It Works.** After a task, before declaring done. Verify against the real artifact, not a proxy or \"it compiles\".\n- **Fix Root Causes.** Debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.\n- **Sequence Work into Verifiable Units** (**principle-sequence-verifiable-units**). Multi-step work (sweeps, migrations, runs of similar edits) and how you stack commits and PRs. Break work into small units that each end in a check, verify each before the next, and order delivery so the sequence proves itself.\n- **Test Behavior, Not Implementation.** Writing, changing, or keeping a test. Assert what the code's users can observe, so the test fails when that behavior breaks and keeps passing when only the internals change.\n- **Explain the Number.** Apply before you measure, and before you trust, report, or act on a number you measured (a speedup, a regression, a throughput, a latency, or an eval result). Find what limits it, and rule out that it measured something other than the work you think.\n\n**Delegation**\n\n- **Guard the Context Window.** Context fills up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents, keep summaries in the main thread.\n- **Never Block on the Human.** Tempted to ask \"should I do X?\" on reversible work. Proceed, present the result, let the human course-correct.\n\n**Meta**\n\n- **Encode Lessons in Structure.** You catch yourself writing the same instruction a second time. Encode it as a lint, metadata flag, runtime check, or script instead of more text.\n\n## Autonomy\n\nProceed on reversible work within the user's request. Use the authorization already given. A full-autonomy request removes routine pauses but does not expand the task or override current permissions. External messages need explicit authorization. Merge, deployment, deletion, and publication follow the user's actual request and the current approval rules. Read `references\u002Fcodex.md` for scope and delivery.\n\n**No is an acceptable answer.** Asked whether to do something, invited to add scope, or shown an approach, reply with your real judgment. Decline, push back, or say \"this doesn't earn its place\" when true. A recommendation is a judgment, not a validation. Agreement is not the default, candor over sycophancy.\n\n## Subagents\n\nUse Codex subagent tools for the delegation a playbook requests. The chat that receives `$poteto-mode` runs the playbook. Delegate bounded implementation, exploration, and review work. Do not start a second agent to run the entire playbook.\n\nUse `worker` for edits and `explorer` for code questions when available. Give file pointers, the complete brief, explicit write ownership, and a requirement to retain other workers' edits. Follow the session's concurrency limit. Use separate worktrees when branches or shared state would conflict.\n\nDefault to the parent model and reasoning effort. Read an existing role override from `${CODEX_HOME:-$HOME\u002F.codex}\u002Fpstack-models.md`, maintained by `$setup-pstack`. Apply it only if the current tools accept that model and effort. `auto` and `inherit-parent` mean omit model arguments. Use fresh context when the tool requires it for an override. Never send Cursor model IDs, speed suffixes, or `Task` arguments to a Codex tool. If an override is rejected, report it and inherit the parent without another guessed ID.\n\nKeep independent review distinct from model diversity. A review on the parent model can be independent when its agent did not write the change. Record model diversity as unavailable when the session exposes only one family. If delegation is unavailable, run the work in sequence and state which independent checks remain pending.\n\nYou own every subagent's work. Review the diff and write your own summary, don't pass through what it said. A second opinion is the same prompt against a different model. Agreement is high-signal.\n\n**Fresh subagents by default.** Give new work to a fresh subagent with consolidated scope, meaning the original brief, every later directive, and the prior agent's report and branch. This holds for a fix round, a follow-up, a retry, and the next queue item. Resume, message, or queue a follow-up on an existing subagent only when the new work strictly needs state that lives in that agent and is costly to move: its local checkout, its uncommitted changes, or a process it still runs, such as a dev server, a simulator, or a babysit watcher. A stop or hold order to a running agent is not reuse. A role such as a PR owner outlives its agent. Once that agent returns, a fresh agent takes the role's next round. Give a replacement agent the consolidated scope and prior artifacts. Check its result against those instructions instead of relying on a \"done\" summary.\n\n## Writing the reply\n\nWrite the reply clean as you draft it. A cleanup pass after drafting does not remove these patterns.\n\n- **Short declarative sentences.** One thought per sentence, ended with a period.\n- **No long-dash character anywhere.** Write a file-list bullet as a sentence (\"`main.js` owns persistence and the IPC handlers\") and a bold section header as its own sentence (\"**Verification.** End to end via CDP\").\n- **A colon as a mid-sentence connector is also out** (unslop rule 14). A colon before a list is fine.\n- **Terse is not an excuse to drop content.** Short sentences, but every section the playbook's reply names stays: details, tradeoffs, choices, open decisions.\n- **Frame impact for the consumer and the maintainer.** Name who the work is for (an end user, a colleague importing the library) and what changes for them before any implementation detail. Then what the next engineer who owns this code inherits. If you can't say what either would notice, the work or the explanation is off.\n- **Never fabricate a link, citation, or transcript reference.** Link only artifacts you produced or read this session.\n- **Every claim carries its evidence or its label in the same sentence.** Measured, inferred, or guess. A prediction or an unseen cause is a guess. Never hand the human a check you could run.\n\nEvery playbook ends with a reply written this way, PR link as `https:\u002F\u002Fgithub.com\u002F\u003Cowner>\u002F\u003Crepo>\u002Fpull\u002F\u003Cnumber>`. Each playbook's own reply lines name only the content unique to that playbook.\n\n## Comments\n\nComments follow the same rule as the reply. Write them clean as you go. Keep a comment only for a non-obvious *why* the code can't show. A verify or test script gets no phase-narrating comments such as `\u002F\u002F Phase 1: add cards`. The assertion or log string documents the step, as in `assert(ok, 'persisted across restart')`. This applies to every file you produce, including the delegate's diff.\n\n## Playbooks\n\nOpen a todolist whose first items are the matched playbook's steps, copied in verbatim, before any task-specific todos. A step you choose not to do stays in the list with a one-line `skip: \u003Creason>`. Match the task to a playbook below and open its full steps at `playbooks\u002F\u003Ctitle>.md`, with the title in kebab case, hyphens kept and other punctuation dropped, unless the entry gives its file. Copy its steps in verbatim.\n\nA large or cross-cutting effort (a migration across many call sites, an ambitious multi-part change), or work the user steps away from to trust later, routes to the **figure-it-out** skill even when a narrower playbook like Feature fits. Use **figure-it-out** whenever no bundled playbook fits. It designs a bespoke, rigorous playbook for the task. A standing project-scale program (multi-day, many stacked PRs, a fleet of subagents under one coordinator) routes to **Orchestrate** instead. figure-it-out designs one bespoke run, orchestrate runs the program.\n\n- **Investigation.** Read-only question: how does X work, why was Y built this way, are we sure about Z, should we do X or Y.\n- **Bug fix.** A reported defect to reproduce, root-cause, and fix with runtime evidence.\n- **Perf issue.** A measured slowness to trace and improve against a baseline.\n- **Hillclimb.** Sustained, scientific improvement of one metric against a target: loop hypotheses with before\u002Fafter measurement, a decision log, and one commit per accepted win. Distinct from Perf issue, which is a one-off fix.\n- **Runtime forensics.** Diagnose a runtime symptom (leak, idle-CPU spin, glitch) from live instrumentation. The deliverable is a diagnosis, not a fix.\n- **Trace forensics.** Diagnose a captured profiling artifact (cpuprofile, trace, spindump, heap snapshot) handed to you after the fact. The deliverable is a diagnosis, not a fix.\n- **Feature.** New or changed behavior, built from a named data shape.\n- **Refactoring.** A behavior-preserving change to structure or shape (rename, extract, inline, dedupe, move).\n- **Prototype.** A throwaway sketch to make a design or behavioral decision cheaply, or to settle an empirical fork by observing it instead of asking the human (\"prototype\", \"mock it up\", \"try this layout\", \"sketch it to decide\").\n- **Visual parity.** Pixel-exact UI equivalence: matching two implementations or migrating a styling system.\n- **Authoring or modifying a skill.** Writing or editing a SKILL.md. File: `playbooks\u002Fauthoring-a-skill.md`.\n- **Eval.** Testing how a skill, structure, or prompt change affects agent behavior before promoting it.\n- **Babysit.** Driving a PR or a stack to merge-ready: conflicts, review threads, CI.\n- **Shipping.** The half after Babysit. Independently verifying a green stack, then landing the contiguous verified run bottom-up through `gh` by default or Origin when its CLI is available.\n- **Autonomous run.** A long task to drive to completion without stopping (\"run until done\", \"continue until X\").\n- **Orchestrate.** A standing project handed to one coordinator chat: multi-day, many stacked PRs, dozens to hundreds of subagents, minimal human turns (\"run this whole project\", \"own this migration until it lands\"). Distinct from Autonomous run, which drives one task to a predicate. Work one agent could finish inside the session's budget routes there, not here, however program-shaped the phrasing sounds.\n- **Autopilot-full.** A queue of independent PRs run to merged with full autonomy. One owner per PR carries build through merge, and the root swarm-verifies each PR before its owner merges (\"autopilot this queue\", \"full autopilot\", one-owner-per-PR programs).\n- **Autopilot-stack.** Autopilot-full without the merge. A queue of PRs built and verified with full autonomy, then handed to the operator to land. A PR stacks only on a PR it builds on (\"autopilot-stack\", \"autopilot, don't merge\", \"stack them, don't ship\", \"build the stack, I'll land it\").\n- **Session pickup.** Resuming or taking over a prior agent's in-flight work from a transcript, cloud-agent URL, or pushed branch.\n- **Pause safely.** Suspending in-flight work cleanly so it can be resumed, on an explicit pause, going offline, a Codex restart, or imminent context compaction. The complement to Session pickup.\n- **Multi-phase or multi-PR plan.** Work that spans phases or stacked PRs. File: `playbooks\u002Fmulti-phase-plan.md`.\n- **Worktree and simulator cleanup.** Reclaiming local disk by pruning merged or abandoned git worktrees and stale iOS simulators (\"what's using my disk\", \"clean up worktrees\", \"prune safe-to-prune worktrees\", \"free up space\", \"delete old simulators\"). File: `playbooks\u002Fworktree-cleanup.md`.\n- **Opening a PR.** Invoked at the end of every other playbook.\n",{"name":5,"description":7},"main","51c07bb1edf30125b4a1e70a61744acb942e3368","skills\u002Fpoteto-mode","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills","https:\u002F\u002Fgithub.com\u002Fthiskevinwang","thekevinwang.com","At @clerk — ex-@HashiCorp","2026-10-30 13:13:33",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add thiskevinwang\u002Fskills --skill poteto-mode",{"tool":39,"command":40},"bunx","bunx skills add thiskevinwang\u002Fskills --skill poteto-mode",{"tool":42,"command":43},"pnpm","pnpm dlx skills add thiskevinwang\u002Fskills --skill poteto-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002FSKILL.md",true,[47,53,57,61,65,69,73,77,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,157,163,167,171,175,179,183,187,191,195,199,203,207,211,215,219,223,227],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"playbooks\u002Fauthoring-a-skill.md",809,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fauthoring-a-skill.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"playbooks\u002Fautonomous-run.md",1890,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fautonomous-run.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"playbooks\u002Fautopilot-full.md",6769,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fautopilot-full.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"playbooks\u002Fautopilot-stack.md",877,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fautopilot-stack.md",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"playbooks\u002Fbabysit.md",7899,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fbabysit.md",{"path":78,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":79,"sourceHtmlUrl":80},"playbooks\u002Fbug-fix.md",2362,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fbug-fix.md",{"path":82,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":83,"sourceHtmlUrl":84},"playbooks\u002Feval.md",2487,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Feval.md",{"path":86,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":87,"sourceHtmlUrl":88},"playbooks\u002Ffeature.md",2808,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Ffeature.md",{"path":90,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":91,"sourceHtmlUrl":92},"playbooks\u002Fhillclimb.md",4445,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fhillclimb.md",{"path":94,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":95,"sourceHtmlUrl":96},"playbooks\u002Finvestigation.md",928,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Finvestigation.md",{"path":98,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":99,"sourceHtmlUrl":100},"playbooks\u002Fmulti-phase-plan.md",13594,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fmulti-phase-plan.md",{"path":102,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":103,"sourceHtmlUrl":104},"playbooks\u002Fopening-a-pr.md",5793,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fopening-a-pr.md",{"path":106,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":107,"sourceHtmlUrl":108},"playbooks\u002Forchestrate.md",4699,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Forchestrate.md",{"path":110,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":111,"sourceHtmlUrl":112},"playbooks\u002Fpause-safely.md",1135,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fpause-safely.md",{"path":114,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":115,"sourceHtmlUrl":116},"playbooks\u002Fperf-issue.md",1488,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fperf-issue.md",{"path":118,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":119,"sourceHtmlUrl":120},"playbooks\u002Fprototype.md",2161,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fprototype.md",{"path":122,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":123,"sourceHtmlUrl":124},"playbooks\u002Frefactoring.md",3253,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Frefactoring.md",{"path":126,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":127,"sourceHtmlUrl":128},"playbooks\u002Fruntime-forensics.md",1257,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fruntime-forensics.md",{"path":130,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":131,"sourceHtmlUrl":132},"playbooks\u002Fsession-pickup.md",1588,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fsession-pickup.md",{"path":134,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":135,"sourceHtmlUrl":136},"playbooks\u002Fshipping.md",4507,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fshipping.md",{"path":138,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":139,"sourceHtmlUrl":140},"playbooks\u002Ftrace-forensics.md",1810,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Ftrace-forensics.md",{"path":142,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":143,"sourceHtmlUrl":144},"playbooks\u002Fvisual-parity.md",1196,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fvisual-parity.md",{"path":146,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":147,"sourceHtmlUrl":148},"playbooks\u002Fworktree-cleanup.md",1702,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fplaybooks\u002Fworktree-cleanup.md",{"path":150,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Fbugbot-triage.md",9641,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Freferences\u002Fbugbot-triage.md",{"path":154,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":155,"sourceHtmlUrl":156},"references\u002Fcodex.md",5580,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Freferences\u002Fcodex.md",{"path":158,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":161,"sourceHtmlUrl":162},"scripts\u002Fbootstrap.ts","SCRIPT","脚本",1737,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fbootstrap.ts",{"path":164,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":165,"sourceHtmlUrl":166},"scripts\u002Fbun.lock",6679,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fbun.lock",{"path":168,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":169,"sourceHtmlUrl":170},"scripts\u002Fcheck-plan.mjs",8200,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fcheck-plan.mjs",{"path":172,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":173,"sourceHtmlUrl":174},"scripts\u002Fcheck-plan.test.ts",3898,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fcheck-plan.test.ts",{"path":176,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":177,"sourceHtmlUrl":178},"scripts\u002Fpackage.json",366,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fpackage.json",{"path":180,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":181,"sourceHtmlUrl":182},"scripts\u002Fwatch-pr\u002Fcli.test.ts",6161,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fcli.test.ts",{"path":184,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":185,"sourceHtmlUrl":186},"scripts\u002Fwatch-pr\u002Fcli.ts",6983,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fcli.ts",{"path":188,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":189,"sourceHtmlUrl":190},"scripts\u002Fwatch-pr\u002Ffakes.test-helper.ts",3357,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Ffakes.test-helper.ts",{"path":192,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":193,"sourceHtmlUrl":194},"scripts\u002Fwatch-pr\u002Fgithub.test.ts",16206,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fgithub.test.ts",{"path":196,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":197,"sourceHtmlUrl":198},"scripts\u002Fwatch-pr\u002Fgithub.ts",25642,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fgithub.ts",{"path":200,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":201,"sourceHtmlUrl":202},"scripts\u002Fwatch-pr\u002Fpolicy.test.ts",14759,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fpolicy.test.ts",{"path":204,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":205,"sourceHtmlUrl":206},"scripts\u002Fwatch-pr\u002Fpolicy.ts",25407,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fpolicy.ts",{"path":208,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":209,"sourceHtmlUrl":210},"scripts\u002Fwatch-pr\u002Frender.ts",7083,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Frender.ts",{"path":212,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":213,"sourceHtmlUrl":214},"scripts\u002Fwatch-pr\u002Ftsconfig.json",270,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Ftsconfig.json",{"path":216,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":217,"sourceHtmlUrl":218},"scripts\u002Fwatch-pr\u002Ftypes.compile.ts",2258,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Ftypes.compile.ts",{"path":220,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":221,"sourceHtmlUrl":222},"scripts\u002Fwatch-pr\u002Ftypes.ts",12688,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Ftypes.ts",{"path":224,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":225,"sourceHtmlUrl":226},"scripts\u002Fwatch-pr\u002Fwatch-pr",211,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fwatch-pr\u002Fwatch-pr",{"path":228,"resourceType":159,"resourceTypeDesc":160,"sizeBytes":229,"sourceHtmlUrl":230},"scripts\u002Fworktree-audit.sh",6285,"https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpoteto-mode\u002Fscripts\u002Fworktree-audit.sh",[232,240,248,256,264,272],{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":236,"sourceHtmlUrl":237,"categories":238,"keywords":239,"publishedAt":20},"01M79QDJ0DXTASX9AHRE9J2ZKG","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":241,"name":242,"nameZh":6,"description":243,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":244,"sourceHtmlUrl":245,"categories":246,"keywords":247,"publishedAt":20},"01M79QDF7H8WJZVBMBDH97DSW2","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":249,"name":250,"nameZh":6,"description":251,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":252,"sourceHtmlUrl":253,"categories":254,"keywords":255,"publishedAt":20},"01M79QDD9NV7D94SD7FSXJQ6S1","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":257,"name":258,"nameZh":6,"description":259,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":260,"sourceHtmlUrl":261,"categories":262,"keywords":263,"publishedAt":20},"01M79QD8EKW32GD0B1MQ49ZPCP","thermo-nuclear-code-quality-review","Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthermo-nuclear-code-quality-review\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fthermo-nuclear-code-quality-review\u002FSKILL.md",[],[],{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":268,"sourceHtmlUrl":269,"categories":270,"keywords":271,"publishedAt":20},"01M79QD4GG4D1FQJMRJFKHY3SF","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":273,"name":274,"nameZh":6,"description":275,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":276,"sourceHtmlUrl":277,"categories":278,"keywords":279,"publishedAt":20},"01M79QD0Y7HC8X8HW1JMXPN52T","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fthiskevinwang\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FSKILL.md",[],[]]