[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KC7V5ESJFEVG93K3FS4BT":3,"skill-same:01M77KC7V5ESJFEVG93K3FS4BT":60},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77KC7V5ESJFEVG93K3FS4BT","investigate",null,"Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.","WritzProtocol\u002Fwritz","WritzProtocol","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F296057967?v=4","01M77K5N0T3073T814APZTAXM4","Writz Protocol","01M77K5N1WQ551ZKCCK9MR379A",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finvestigate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: investigate\ndescription: Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.\n---\n\n# Investigate\n\n## Overview\n\nReconstruct what's happening, or what an unfamiliar area does, from the available evidence. Produce a structured case\nfile another engineer can pick up cold. Calibrate continuously between defect-chasing (symptom-driven) and\narea-exploration (no symptom); the same discipline applies on both ends.\n\n**Args:** A ticket ID, log file path, diagnostic archive, error message, code area name, problem description, or a path\nto an existing case file. The last form resumes a prior investigation; everything else opens a new case.\n\n**Output:** `{implementation_artifacts}\u002F{workflow.case_file_subdir}\u002F{workflow.case_file_filename}`. Reference inputs\nare recorded; raw content is not read into the parent context until an outcome calls for it.\n\n`{slug}` is the ticket ID when one is provided, otherwise a short descriptive name agreed with the user, sanitized to\nlowercase alphanumeric with hyphens. On collision with an existing case file at the resolved path, ask whether to\nrename to `slug-YYYY-MM-DD.md` or resume the existing file (resuming routes to Outcome 0).\n\nAfter every outcome, present what was learned and pause for the user before continuing.\n\n## Principles\n\n- **Evidence grading.**\n  - **Confirmed.** Directly observed; cite `path:line`, log timestamp, or commit hash.\n  - **Deduced.** Logically follows from Confirmed evidence; show the chain.\n  - **Hypothesized.** Plausible but unconfirmed; state what would confirm or refute it.\n- **Stronghold first.** Anchor in one Confirmed piece of evidence and expand outward. Never start from a theory and\n  hunt for support. When evidence is sparse, switch to evidence-light mode (Outcome 1 branch).\n- **Challenge the premise.** The user's description is a hypothesis, not a fact. Verify independently; if evidence\n  contradicts, say so.\n- **Follow the evidence, not the narrative.** When evidence contradicts the working theory, update the theory - never\n  the other way around. Resist confirmation bias even when the user is convinced.\n- **Hypotheses are never deleted.** Update Status (Open \u002F Confirmed \u002F Refuted) and add a Resolution. Wrong turns are\n  part of the deliverable.\n- **Missing evidence is itself a finding.** Document the gap, what it would resolve, and how to obtain it.\n- **Write it down early.** Initialize the case file as soon as the slug is agreed; it is the persistent state across\n  interruptions.\n- **Path:line citations** use CWD-relative format, no leading `\u002F`, so they're clickable in IDE-embedded terminals.\n- **Delegation discipline.** When a step requires reading 5+ files or any file >10K tokens, delegate to a subagent\n  that returns structured JSON only. Cite `path:line` from the result; don't re-read in the parent.\n- **Issue independent operations in parallel** (multi-grep, multi-read, parallel inventories) - one message, multiple\n  tool calls.\n- **Communication.** Evidence-first language (\"the evidence shows\", \"unconfirmed, requires X to verify\"). No hedging,\n  no narrative.\n\n## On Activation\n\n### Step 1: Resolve the workflow block\n\nRun: `python3 {project-root}\u002F.stellar-build\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\nIf the script fails, stop and surface the error.\n\n### Step 2: Execute prepend steps\n\nRun each entry in `{workflow.activation_steps_prepend}` in order.\n\n### Step 3: Load persistent facts\n\nTreat each entry in `{workflow.persistent_facts}` as foundational context. `file:` prefixes are paths or globs under\n`{project-root}` (load contents); other entries are facts verbatim.\n\n### Step 4: Load config\n\nLoad `{project-root}\u002F.stellar-build\u002Fbmm\u002Fconfig.yaml` and resolve `{user_name}`, `{communication_language}`,\n`{document_output_language}`, `{implementation_artifacts}`, `{project_knowledge}`. If `{implementation_artifacts}` is\nunresolved, fall back to `.\u002Finvestigations\u002F` and surface the fallback before initializing.\n\n### Step 5: Greet\n\nGreet `{user_name}` in `{communication_language}`.\n\n### Step 6: Execute append steps\n\nRun each entry in `{workflow.activation_steps_append}` in order.\n\n### Step 7: Acknowledge and route\n\nAcknowledge the input as a reference (record paths and IDs; don't read raw content). Path to an existing case file →\nOutcome 0. Otherwise → Outcome 1.\n\n## Procedure\n\n### Outcome 0: Existing case is loaded and surfaced\n\nRead the case file. Surface, in order: open hypotheses (Status = Open) with their confirm\u002Frefute criteria; open\nbacklog (Status ≠ Done); missing-evidence rows; last Conclusion with confidence. Ask which thread to pull. New\nevidence opens a new `## Follow-up: {YYYY-MM-DD}` block (append `#2`, `#3` on same-day reentry). Pause for user with the recap above; wait for direction.\n\n### Outcome 1: Scope and stronghold are established\n\nAcknowledge each input shape - record location, scope, time window only; bulk reads happen in Outcome 2.\n\n- **Issue tracker ticket.** Fetch full details via available MCP tools.\n- **Diagnostic archive.** Record path, file count, time window.\n- **Log file or stack trace.** Record path and time window; only the stack frame already in the user's message is in\n  scope here.\n- **Free-text description.** Capture verbatim; treat as hypothesis.\n- **Code area name** (no symptom). Record entry point.\n- **Recent commit area.** Record commit range.\n\nIf the user arrived with a hypothesis, register it as Hypothesis #1. Find the stronghold *independently*; the user's\nhypothesis is one of the things the stronghold validates or refutes.\n\nFind a stronghold: a Confirmed piece of evidence (error message, function name, HTTP route, config parameter, test\ncase). Anchor here.\n\n**Initialize `{case_file}` before branching.** The path is\n`{implementation_artifacts}\u002F{workflow.case_file_subdir}\u002F{workflow.case_file_filename}` with `{slug}` substituted (slug\nand collision rules in Overview). Create the file from `{workflow.case_file_template}` and fill Hand-off Brief\n(rough), Case Info, Problem Statement, initial Evidence Inventory.\n\n**Evidence-light branch.** When no Confirmed evidence is reachable: mark the case evidence-light in the Hand-off\nBrief; populate the Investigation Backlog with prioritized data-collection items; record \"to make progress, I need one\nof: …\"; pause for the user to provide evidence or authorize Outcome 2 to scan more broadly.\n\nOtherwise present scope, stronghold, file path, proposed approach. Pause for user with the recap above; wait for direction.\n\n### Outcome 2: Evidence perimeter is mapped\n\nSurvey the scene: inventory available evidence in parallel across these independent categories: diagnostic archives;\nissue tracker; version control; test results; static analysis; source code. For any category exceeding ~10K tokens,\ndelegate to a subagent that returns a JSON manifest (paths, sizes, time windows, key fragments cited as `path:line`).\n\nClassify each Available, Partial, or Missing - Missing is itself a finding. Update Evidence Inventory and Investigation\nBacklog. Pause for user with the recap above; wait for direction.\n\n### Outcome 3: Cause is reasoned about with discipline\n\n- **Trace causality.** Symptom-driven: trace backward from the symptom to producing conditions and the state that\n  emerged. Exploration: trace backward from outputs (returns, side effects, messages sent) to producing conditions.\n  Same technique, different anchor.\n- **Reconstruct the timeline** by cross-referencing logs, system events, version control, user observations.\n- **Form and test hypotheses.** State, identify confirming\u002Frefuting evidence, search, grade\n  (Confirmed \u002F Refuted \u002F Open). Update Status. Never delete.\n- **Refutation pass.** Each time a hypothesis transitions toward Confirmed, actively look for refuting evidence first.\n  Record the attempt in Resolution.\n- **Verify the user's premise.** If evidence contradicts, say so explicitly.\n- **Add discovered paths to the backlog.** Stay focused on the current thread.\n\nUpdate Confirmed Findings, Deduced Conclusions, Hypothesized Paths, Backlog, Timeline. Highlight contradictions to the\noriginal premise. Pause for user with the recap above; wait for direction.\n\n### Outcome 4: Source has been traced where it matters\n\nIssue these first-pass scans as parallel tool calls in one message: grep for exact error strings; glob the affected\ndirectory for parallel implementations; `git log` for recent changes.\n\nThen sequentially: read the surrounding code; follow the caller chain; watch for language and process boundary\ncrossings (compiled→scripts, IPC, host→device, configuration flow).\n\nLean by case type:\n\n- **Exploration:** I\u002FO mapping (triggers, outputs, dependencies); frequent-terms scan; control-flow filtering\n  (branches, loops, error handling, state-machine transitions).\n- **Symptom-driven:** depth assessment - is the root cause reachable from local context, or is a broader area model\n  required? Surface escalations; never silently expand scope. Trivial-fix assessment - off-by-one, missing null check,\n  swapped argument → one-line code suggestion or draft diff in the report; non-trivial → stop at the root cause area.\n\nInvestigation stops at the diagnosis; implementation is out of scope. Update Source Code Trace (Error origin, Trigger,\nCondition, Related files; area model when broader). Pause for user with the recap above; wait for direction.\n\n### Outcome 5: Report is finalized and the hand-off is clean\n\nUpdate `{case_file}`:\n\n- **Hand-off Brief** rewritten to final form (3 sentences, 15-second read).\n- **Final Conclusion** with confidence: **High** (Confirmed root cause, deterministic repro), **Medium** (Deduced;\n  minor uncertainty), **Low** (Hypothesized; clear data gap).\n- **Fix direction** when applicable (categorize by mechanism if multiple combine).\n- **Diagnostic steps** if uncertainty remains.\n- **Reproduction Plan** when applicable, or a verification plan for exploration cases.\n- **Status:** Active \u002F Concluded \u002F Blocked on evidence.\n\nPresent the conclusion, then a concrete next-steps menu: trivial fix → `dev-story`; scope\u002Fplan adjustment →\n`dev-story`; tracked story → `create-epics-and-stories`; fresh review → `code-review`. Recommend the\nhighest-value action. Mitigations and workarounds are generated only on explicit request - investigation stops at the\ndiagnosis. Execute `{workflow.on_complete}` if non-empty. Pause for user with the recap above; wait for direction.\n\n## Follow-up Iterations\n\nContinue work by appending to `{case_file}` under a new `## Follow-up: {YYYY-MM-DD}` block (`#2`, `#3` on same-day\nreentry). The investigation is complete when:\n\n- Root cause is Confirmed.\n- Root cause is Hypothesized with a clear data gap.\n- The mental model is sufficient for the user's stated goal (exploration cases).\n- The backlog contains only items requiring unavailable evidence.\n- The user explicitly concludes.\n","# Investigate\n\n## Overview\n\nReconstruct what's happening, or what an unfamiliar area does, from the available evidence. Produce a structured case\nfile another engineer can pick up cold. Calibrate continuously between defect-chasing (symptom-driven) and\narea-exploration (no symptom); the same discipline applies on both ends.\n\n**Args:** A ticket ID, log file path, diagnostic archive, error message, code area name, problem description, or a path\nto an existing case file. The last form resumes a prior investigation; everything else opens a new case.\n\n**Output:** `{implementation_artifacts}\u002F{workflow.case_file_subdir}\u002F{workflow.case_file_filename}`. Reference inputs\nare recorded; raw content is not read into the parent context until an outcome calls for it.\n\n`{slug}` is the ticket ID when one is provided, otherwise a short descriptive name agreed with the user, sanitized to\nlowercase alphanumeric with hyphens. On collision with an existing case file at the resolved path, ask whether to\nrename to `slug-YYYY-MM-DD.md` or resume the existing file (resuming routes to Outcome 0).\n\nAfter every outcome, present what was learned and pause for the user before continuing.\n\n## Principles\n\n- **Evidence grading.**\n  - **Confirmed.** Directly observed; cite `path:line`, log timestamp, or commit hash.\n  - **Deduced.** Logically follows from Confirmed evidence; show the chain.\n  - **Hypothesized.** Plausible but unconfirmed; state what would confirm or refute it.\n- **Stronghold first.** Anchor in one Confirmed piece of evidence and expand outward. Never start from a theory and\n  hunt for support. When evidence is sparse, switch to evidence-light mode (Outcome 1 branch).\n- **Challenge the premise.** The user's description is a hypothesis, not a fact. Verify independently; if evidence\n  contradicts, say so.\n- **Follow the evidence, not the narrative.** When evidence contradicts the working theory, update the theory - never\n  the other way around. Resist confirmation bias even when the user is convinced.\n- **Hypotheses are never deleted.** Update Status (Open \u002F Confirmed \u002F Refuted) and add a Resolution. Wrong turns are\n  part of the deliverable.\n- **Missing evidence is itself a finding.** Document the gap, what it would resolve, and how to obtain it.\n- **Write it down early.** Initialize the case file as soon as the slug is agreed; it is the persistent state across\n  interruptions.\n- **Path:line citations** use CWD-relative format, no leading `\u002F`, so they're clickable in IDE-embedded terminals.\n- **Delegation discipline.** When a step requires reading 5+ files or any file >10K tokens, delegate to a subagent\n  that returns structured JSON only. Cite `path:line` from the result; don't re-read in the parent.\n- **Issue independent operations in parallel** (multi-grep, multi-read, parallel inventories) - one message, multiple\n  tool calls.\n- **Communication.** Evidence-first language (\"the evidence shows\", \"unconfirmed, requires X to verify\"). No hedging,\n  no narrative.\n\n## On Activation\n\n### Step 1: Resolve the workflow block\n\nRun: `python3 {project-root}\u002F.stellar-build\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\nIf the script fails, stop and surface the error.\n\n### Step 2: Execute prepend steps\n\nRun each entry in `{workflow.activation_steps_prepend}` in order.\n\n### Step 3: Load persistent facts\n\nTreat each entry in `{workflow.persistent_facts}` as foundational context. `file:` prefixes are paths or globs under\n`{project-root}` (load contents); other entries are facts verbatim.\n\n### Step 4: Load config\n\nLoad `{project-root}\u002F.stellar-build\u002Fbmm\u002Fconfig.yaml` and resolve `{user_name}`, `{communication_language}`,\n`{document_output_language}`, `{implementation_artifacts}`, `{project_knowledge}`. If `{implementation_artifacts}` is\nunresolved, fall back to `.\u002Finvestigations\u002F` and surface the fallback before initializing.\n\n### Step 5: Greet\n\nGreet `{user_name}` in `{communication_language}`.\n\n### Step 6: Execute append steps\n\nRun each entry in `{workflow.activation_steps_append}` in order.\n\n### Step 7: Acknowledge and route\n\nAcknowledge the input as a reference (record paths and IDs; don't read raw content). Path to an existing case file →\nOutcome 0. Otherwise → Outcome 1.\n\n## Procedure\n\n### Outcome 0: Existing case is loaded and surfaced\n\nRead the case file. Surface, in order: open hypotheses (Status = Open) with their confirm\u002Frefute criteria; open\nbacklog (Status ≠ Done); missing-evidence rows; last Conclusion with confidence. Ask which thread to pull. New\nevidence opens a new `## Follow-up: {YYYY-MM-DD}` block (append `#2`, `#3` on same-day reentry). Pause for user with the recap above; wait for direction.\n\n### Outcome 1: Scope and stronghold are established\n\nAcknowledge each input shape - record location, scope, time window only; bulk reads happen in Outcome 2.\n\n- **Issue tracker ticket.** Fetch full details via available MCP tools.\n- **Diagnostic archive.** Record path, file count, time window.\n- **Log file or stack trace.** Record path and time window; only the stack frame already in the user's message is in\n  scope here.\n- **Free-text description.** Capture verbatim; treat as hypothesis.\n- **Code area name** (no symptom). Record entry point.\n- **Recent commit area.** Record commit range.\n\nIf the user arrived with a hypothesis, register it as Hypothesis #1. Find the stronghold *independently*; the user's\nhypothesis is one of the things the stronghold validates or refutes.\n\nFind a stronghold: a Confirmed piece of evidence (error message, function name, HTTP route, config parameter, test\ncase). Anchor here.\n\n**Initialize `{case_file}` before branching.** The path is\n`{implementation_artifacts}\u002F{workflow.case_file_subdir}\u002F{workflow.case_file_filename}` with `{slug}` substituted (slug\nand collision rules in Overview). Create the file from `{workflow.case_file_template}` and fill Hand-off Brief\n(rough), Case Info, Problem Statement, initial Evidence Inventory.\n\n**Evidence-light branch.** When no Confirmed evidence is reachable: mark the case evidence-light in the Hand-off\nBrief; populate the Investigation Backlog with prioritized data-collection items; record \"to make progress, I need one\nof: …\"; pause for the user to provide evidence or authorize Outcome 2 to scan more broadly.\n\nOtherwise present scope, stronghold, file path, proposed approach. Pause for user with the recap above; wait for direction.\n\n### Outcome 2: Evidence perimeter is mapped\n\nSurvey the scene: inventory available evidence in parallel across these independent categories: diagnostic archives;\nissue tracker; version control; test results; static analysis; source code. For any category exceeding ~10K tokens,\ndelegate to a subagent that returns a JSON manifest (paths, sizes, time windows, key fragments cited as `path:line`).\n\nClassify each Available, Partial, or Missing - Missing is itself a finding. Update Evidence Inventory and Investigation\nBacklog. Pause for user with the recap above; wait for direction.\n\n### Outcome 3: Cause is reasoned about with discipline\n\n- **Trace causality.** Symptom-driven: trace backward from the symptom to producing conditions and the state that\n  emerged. Exploration: trace backward from outputs (returns, side effects, messages sent) to producing conditions.\n  Same technique, different anchor.\n- **Reconstruct the timeline** by cross-referencing logs, system events, version control, user observations.\n- **Form and test hypotheses.** State, identify confirming\u002Frefuting evidence, search, grade\n  (Confirmed \u002F Refuted \u002F Open). Update Status. Never delete.\n- **Refutation pass.** Each time a hypothesis transitions toward Confirmed, actively look for refuting evidence first.\n  Record the attempt in Resolution.\n- **Verify the user's premise.** If evidence contradicts, say so explicitly.\n- **Add discovered paths to the backlog.** Stay focused on the current thread.\n\nUpdate Confirmed Findings, Deduced Conclusions, Hypothesized Paths, Backlog, Timeline. Highlight contradictions to the\noriginal premise. Pause for user with the recap above; wait for direction.\n\n### Outcome 4: Source has been traced where it matters\n\nIssue these first-pass scans as parallel tool calls in one message: grep for exact error strings; glob the affected\ndirectory for parallel implementations; `git log` for recent changes.\n\nThen sequentially: read the surrounding code; follow the caller chain; watch for language and process boundary\ncrossings (compiled→scripts, IPC, host→device, configuration flow).\n\nLean by case type:\n\n- **Exploration:** I\u002FO mapping (triggers, outputs, dependencies); frequent-terms scan; control-flow filtering\n  (branches, loops, error handling, state-machine transitions).\n- **Symptom-driven:** depth assessment - is the root cause reachable from local context, or is a broader area model\n  required? Surface escalations; never silently expand scope. Trivial-fix assessment - off-by-one, missing null check,\n  swapped argument → one-line code suggestion or draft diff in the report; non-trivial → stop at the root cause area.\n\nInvestigation stops at the diagnosis; implementation is out of scope. Update Source Code Trace (Error origin, Trigger,\nCondition, Related files; area model when broader). Pause for user with the recap above; wait for direction.\n\n### Outcome 5: Report is finalized and the hand-off is clean\n\nUpdate `{case_file}`:\n\n- **Hand-off Brief** rewritten to final form (3 sentences, 15-second read).\n- **Final Conclusion** with confidence: **High** (Confirmed root cause, deterministic repro), **Medium** (Deduced;\n  minor uncertainty), **Low** (Hypothesized; clear data gap).\n- **Fix direction** when applicable (categorize by mechanism if multiple combine).\n- **Diagnostic steps** if uncertainty remains.\n- **Reproduction Plan** when applicable, or a verification plan for exploration cases.\n- **Status:** Active \u002F Concluded \u002F Blocked on evidence.\n\nPresent the conclusion, then a concrete next-steps menu: trivial fix → `dev-story`; scope\u002Fplan adjustment →\n`dev-story`; tracked story → `create-epics-and-stories`; fresh review → `code-review`. Recommend the\nhighest-value action. Mitigations and workarounds are generated only on explicit request - investigation stops at the\ndiagnosis. Execute `{workflow.on_complete}` if non-empty. Pause for user with the recap above; wait for direction.\n\n## Follow-up Iterations\n\nContinue work by appending to `{case_file}` under a new `## Follow-up: {YYYY-MM-DD}` block (`#2`, `#3` on same-day\nreentry). The investigation is complete when:\n\n- Root cause is Confirmed.\n- Root cause is Hypothesized with a clear data gap.\n- The mental model is sufficient for the user's stated goal (exploration cases).\n- The backlog contains only items requiring unavailable evidence.\n- The user explicitly concludes.\n",{"name":5,"description":7},"main","db2f47e2b79822ad3d8dd0f17489d5d15bcba96d",".claude\u002Fskills\u002Finvestigate",3,"https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz","https:\u002F\u002Fwritz.xyz","https:\u002F\u002Fgithub.com\u002FWritzProtocol","https:\u002F\u002Fwritz.xyz\u002F","Native Bitcoin lending on Stellar. No bridge, no custodian.","2026-11-14 18:13:11",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add WritzProtocol\u002Fwritz --skill investigate",{"tool":40,"command":41},"bunx","bunx skills add WritzProtocol\u002Fwritz --skill investigate",{"tool":43,"command":44},"pnpm","pnpm dlx skills add WritzProtocol\u002Fwritz --skill investigate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finvestigate\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"customize.toml","OTHER","其他",2520,"https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finvestigate\u002Fcustomize.toml",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fcase-file-template.md","REFERENCE","参考文档",4132,"https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finvestigate\u002Freferences\u002Fcase-file-template.md",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M77KKJ6DYZP10BJ74CW4H0AE","zk-proofs","Zero-knowledge proofs and privacy patterns on Stellar. Covers Groth16 verification in smart contracts via BLS12-381 host functions (CAP-0059, available), the BN254 + Poseidon proposals (CAP-0074\u002F0075, status-sensitive), and concrete toolchain walkthroughs for Circom (on-chain verifiable today), Noir, and RISC Zero (attestation pattern until BN254 lands). Use when building privacy-preserving applications, ZK-verifier contracts, or wiring a proving toolchain to Stellar.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fzk-proofs\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M77KKF3SK8JVBGRY4A89HYQC","tyler-architect","System architect and technical design leader. Use when the user asks to talk to Tyler or requests the architect.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftyler-architect\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77KKCD584VQA1TM1F9Q8JBH","stellar-help","Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fstellar-help\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77KK7W2HKQ3QMAG0KJY1BHH","stellar-competitive-landscape","Map the competitive landscape for a Stellar project idea. Use when a user says \"who are my competitors on Stellar\", \"competitive analysis Stellar\", \"what already exists in this space on Stellar\", \"show me similar Stellar projects\", \"is anyone else building this on Stellar\", or \"map the Stellar landscape for X\". Queries the 728-project LumenLoop ecosystem database and Electric Capital developer activity to rank competitors by SCF funding history and repo activity.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fstellar-competitive-landscape\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M77KK1ACXYN5AZTWR8B5CKTX","standards","Stellar standards, ecosystem, and reference. Covers SEPs (Stellar Ecosystem Proposals), CAPs (Core Advancement Proposals), and a quick map for picking the right standard for wallets, anchors, payments, deposits\u002Fwithdrawals, federation, deep links, and KYC. Also bundles ecosystem references (DeFi protocols, dev tools, wallets, infra, community projects), curated documentation links, and MCP servers (live tools such as Raven). Use when you need to know which SEP applies, or want a starting point for ecosystem integrations, official docs, or live MCP tooling.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fstandards\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M77KJV8VW46WC58DHJR2296C","smart-contracts","Stellar smart contract development (Rust, soroban-sdk). Entry point with project setup, contract anatomy, and build\u002Fdeploy workflow, routing to three companion files in this directory - development.md (storage\u002FTTL, authorization, cross-contract calls, tokens, events, errors, upgrades, fees, troubleshooting), testing.md (unit, fuzz, property, fork, mutation, integration), and security.md (vulnerability classes, checklists, tooling, audits). Use when writing, testing, reviewing, securing, debugging, or shipping Stellar smart contracts, including anything the user calls \"Soroban\" - Soroban contracts, soroban-sdk, Soroban auth\u002Fstorage\u002FTTL errors, SEP-41 tokens, or SAC integration from contract code.","https:\u002F\u002Fgithub.com\u002FWritzProtocol\u002Fwritz\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsmart-contracts\u002FSKILL.md",[],[]]