[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B45VXYV1V05AV4BET002DF":3,"skill-same:01M7B45VXYV1V05AV4BET002DF":51},{"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":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7B45VXYV1V05AV4BET002DF","automate-me",null,"Use for \"automate me\", \"create\u002Fupdate\u002Frefresh my -mode skill\", \"turn\u002Fcapture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill through skill-creator and unslop, optionally using supported recent task history.","Aqua-123\u002Fpstack-for-codex","Aqua-123","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F86239876?v=4","01M7B458HX3SN6PFMH26QACXHK","Aqua","01M7B458JP4A60EVJA4WEY7SFR",109,"MIT","https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Fautomate-me\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: automate-me\ndescription: \"Use for \\\"automate me\\\", \\\"create\u002Fupdate\u002Frefresh my -mode skill\\\", \\\"turn\u002Fcapture my preferences or working style into a skill\\\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill through skill-creator and unslop, optionally using supported recent task history.\"\n---\n\n# Automate me\n\nDelegation and optional capabilities follow `..\u002Fpoteto-mode\u002Freferences\u002Fcodex-agent-runtime.md`.\n\nA guided flow for turning the user's working conventions into a skill agents will follow. The output is one `-mode` skill tailored to them (e.g. `jay-mode`, `priya-mode`).\n\nThis skill orchestrates three others: an inline mining pass (see step 1), the `skill-creator` skill (authoring), and the **unslop** skill (prose discipline). It sequences them; it doesn't replace them.\n\n## Flow\n\n### 0. Check for an existing skill\n\nLook recursively for `.agents\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.agents\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.agents\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with ask the user (unless they already said \"update my skill\" or similar):\n\n- Update the existing skill (default for repeat runs)\n- Start fresh (rare; ask why before doing it)\n\nUpdate mode changes the rest of the flow:\n- Step 1 mines only history since the skill was last edited (`git log -1 --format=%cI \u003Cpath>`).\n- Step 2 asks what's changed or missing, not what to capture from zero.\n- Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted; revise ones with new evidence; add new sections only for genuinely new rules.\n\n### 1. Mine their history\n\nList recent tasks through supported Codex task APIs and scope them to the active project. Never infer or search a private history directory. If task APIs are unavailable, ask the user for a history digest or skip mining and state the limitation.\n\nSurvey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Inherit the parent model and reasoning effort unless the user or a validated profile requests another available pair. Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:\n\n- Response preferences (length, tone, format, \"dumb it down\" corrections)\n- Delegation habits (subagents, models, specialized workflows, parallelism)\n- Verification posture (what \"done\" means; unit tests vs live repro; reviewers)\n- Code and prose discipline (style, principles cited, lint\u002Fformat tools)\n- Process conventions (worktrees, commits, PRs, review\u002Fmerge tooling)\n- Meta preferences (fixing skills mid-task, proposing new ones)\n\nCross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence; lone signals are weak and usually get dropped.\n\n### 2. Ask the user directly\n\nMining misses intent that hasn't come up yet. Use the ask the user tool (structured multi-choice) rather than asking the user to type from scratch. Lower cognitive load, higher hit rate.\n\nShape: one or two questions with 4-6 options each, `allow_multiple: true` for category questions. Start broad (\"Which areas matter most?\"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.\n\nDon't dump 20 questions. Two structured rounds plus one open question is usually enough.\n\n### 3. Cluster findings\n\nGroup the combined signals into sections. Common ones (use only what applies):\n\n- **Response style**: length, tone, format.\n- **Autonomy**: how much to do without asking; MCP tool use.\n- **Understand first**: which skills to reach for when scoping or investigating a change.\n- **Subagents**: default, parallelism, model-to-task, specialized workflows.\n- **Prose \u002F code discipline**: principles, lint tools, style guides.\n- **Review and verify**: repro posture, verification skills, live-testing tools.\n- **Process**: git worktrees, commits, PRs, review\u002Fmerge tooling.\n- **Skills**: skill-authoring habits, fix-the-skill-first, proposing new skills.\n\nThe **poteto-mode** skill shows the shape. Read it for granularity. Don't copy its content; the user's rules are not the same as poteto-mode's.\n\n### 4. Draft the skill\n\nUse the `skill-creator` skill to author the skill. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.agents\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle; otherwise default to `.agents\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.agents\u002Fskills\u002F\u003Chandle>-mode\u002F` if the user prefers a personal skill).\n- Handle: the user's first name or chosen identifier.\n- Frontmatter `description`: trigger on their name + `\u002F\u003Chandle>-mode` + \"work in their style\", not on generic keywords like \"write code\" or \"review PR\".\n- Frontmatter formatting: follow `skill-creator`'s YAML rules. Keep `description` as one YAML scalar; quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.\n- Frontmatter `disable-model-invocation: true` by default. Mode skills are heavy and opinionated; they should only apply when the user explicitly invokes them (by name or slash command), not auto-trigger on description matching. Opt out only if the user explicitly wants their mode to apply on every turn.\n\n### 5. Iterate on prose\n\nApply the **unslop** skill and `skill-creator`'s writing guidelines to every line. Both apply to any agent-read prose, not just skills.\n\nShow the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly; a mode skill is not a manual.\n\n### 6. Land it\n\nWork in a worktree off main. Commit and open a PR so the user can review it. Don't push to main directly.\n\n## Guardrails\n\n- **Don't overfit to one conversation.** A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.\n- **Don't be clever.** Restating other skills' contents, inventing metaphors, or writing \"poetic\" prose for an agent reader is cost without benefit. Keep it operational.\n- **Reference, don't inline.** Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.\n- **Keep sections minimal.** Only add a section if the user has a specific, non-default rule there. \"Communicate clearly\" is not a section. \"Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel.\" is.\n- **Name conventions generic.** Use \"the user\" or \"the human\" in imperatives, not the author's first name. Others may read or adopt the skill.\n- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely. Sparse is fine; bloated is not.\n\n## Evaluation\n\nA `-mode` skill is subjective output. A `skill-creator` benchmark loop is not useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.\n\nRun a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.\n\n## When not to use\n\n- User wants a task-specific skill (not working conventions): `skill-creator` alone, no mining required.\n- User wants to capture one narrow workflow (e.g. \"how I write commit messages\"): that's a regular skill, not a mode skill.\n\n## Reference files\n\n- The **poteto-mode** skill: example of the output shape.\n- The **unslop** skill: prose discipline for every line.\n- the `skill-creator` skill: skill authoring process and writing guidelines.\n","# Automate me\n\nDelegation and optional capabilities follow `..\u002Fpoteto-mode\u002Freferences\u002Fcodex-agent-runtime.md`.\n\nA guided flow for turning the user's working conventions into a skill agents will follow. The output is one `-mode` skill tailored to them (e.g. `jay-mode`, `priya-mode`).\n\nThis skill orchestrates three others: an inline mining pass (see step 1), the `skill-creator` skill (authoring), and the **unslop** skill (prose discipline). It sequences them; it doesn't replace them.\n\n## Flow\n\n### 0. Check for an existing skill\n\nLook recursively for `.agents\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.agents\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.agents\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with ask the user (unless they already said \"update my skill\" or similar):\n\n- Update the existing skill (default for repeat runs)\n- Start fresh (rare; ask why before doing it)\n\nUpdate mode changes the rest of the flow:\n- Step 1 mines only history since the skill was last edited (`git log -1 --format=%cI \u003Cpath>`).\n- Step 2 asks what's changed or missing, not what to capture from zero.\n- Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted; revise ones with new evidence; add new sections only for genuinely new rules.\n\n### 1. Mine their history\n\nList recent tasks through supported Codex task APIs and scope them to the active project. Never infer or search a private history directory. If task APIs are unavailable, ask the user for a history digest or skip mining and state the limitation.\n\nSurvey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Inherit the parent model and reasoning effort unless the user or a validated profile requests another available pair. Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:\n\n- Response preferences (length, tone, format, \"dumb it down\" corrections)\n- Delegation habits (subagents, models, specialized workflows, parallelism)\n- Verification posture (what \"done\" means; unit tests vs live repro; reviewers)\n- Code and prose discipline (style, principles cited, lint\u002Fformat tools)\n- Process conventions (worktrees, commits, PRs, review\u002Fmerge tooling)\n- Meta preferences (fixing skills mid-task, proposing new ones)\n\nCross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence; lone signals are weak and usually get dropped.\n\n### 2. Ask the user directly\n\nMining misses intent that hasn't come up yet. Use the ask the user tool (structured multi-choice) rather than asking the user to type from scratch. Lower cognitive load, higher hit rate.\n\nShape: one or two questions with 4-6 options each, `allow_multiple: true` for category questions. Start broad (\"Which areas matter most?\"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.\n\nDon't dump 20 questions. Two structured rounds plus one open question is usually enough.\n\n### 3. Cluster findings\n\nGroup the combined signals into sections. Common ones (use only what applies):\n\n- **Response style**: length, tone, format.\n- **Autonomy**: how much to do without asking; MCP tool use.\n- **Understand first**: which skills to reach for when scoping or investigating a change.\n- **Subagents**: default, parallelism, model-to-task, specialized workflows.\n- **Prose \u002F code discipline**: principles, lint tools, style guides.\n- **Review and verify**: repro posture, verification skills, live-testing tools.\n- **Process**: git worktrees, commits, PRs, review\u002Fmerge tooling.\n- **Skills**: skill-authoring habits, fix-the-skill-first, proposing new skills.\n\nThe **poteto-mode** skill shows the shape. Read it for granularity. Don't copy its content; the user's rules are not the same as poteto-mode's.\n\n### 4. Draft the skill\n\nUse the `skill-creator` skill to author the skill. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.agents\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle; otherwise default to `.agents\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.agents\u002Fskills\u002F\u003Chandle>-mode\u002F` if the user prefers a personal skill).\n- Handle: the user's first name or chosen identifier.\n- Frontmatter `description`: trigger on their name + `\u002F\u003Chandle>-mode` + \"work in their style\", not on generic keywords like \"write code\" or \"review PR\".\n- Frontmatter formatting: follow `skill-creator`'s YAML rules. Keep `description` as one YAML scalar; quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.\n- Frontmatter `disable-model-invocation: true` by default. Mode skills are heavy and opinionated; they should only apply when the user explicitly invokes them (by name or slash command), not auto-trigger on description matching. Opt out only if the user explicitly wants their mode to apply on every turn.\n\n### 5. Iterate on prose\n\nApply the **unslop** skill and `skill-creator`'s writing guidelines to every line. Both apply to any agent-read prose, not just skills.\n\nShow the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly; a mode skill is not a manual.\n\n### 6. Land it\n\nWork in a worktree off main. Commit and open a PR so the user can review it. Don't push to main directly.\n\n## Guardrails\n\n- **Don't overfit to one conversation.** A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.\n- **Don't be clever.** Restating other skills' contents, inventing metaphors, or writing \"poetic\" prose for an agent reader is cost without benefit. Keep it operational.\n- **Reference, don't inline.** Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.\n- **Keep sections minimal.** Only add a section if the user has a specific, non-default rule there. \"Communicate clearly\" is not a section. \"Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel.\" is.\n- **Name conventions generic.** Use \"the user\" or \"the human\" in imperatives, not the author's first name. Others may read or adopt the skill.\n- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely. Sparse is fine; bloated is not.\n\n## Evaluation\n\nA `-mode` skill is subjective output. A `skill-creator` benchmark loop is not useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.\n\nRun a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.\n\n## When not to use\n\n- User wants a task-specific skill (not working conventions): `skill-creator` alone, no mining required.\n- User wants to capture one narrow workflow (e.g. \"how I write commit messages\"): that's a regular skill, not a mode skill.\n\n## Reference files\n\n- The **poteto-mode** skill: example of the output shape.\n- The **unslop** skill: prose discipline for every line.\n- the `skill-creator` skill: skill authoring process and writing guidelines.\n",{"name":5,"description":7},"main","d5b20bce6f0602e3155960b5ea46e47fa0692ad2","skills\u002Fautomate-me",19,"https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex","https:\u002F\u002Fgithub.com\u002FAqua-123","2026-11-14 06:14:34",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Aqua-123\u002Fpstack-for-codex --skill automate-me",{"tool":37,"command":38},"bunx","bunx skills add Aqua-123\u002Fpstack-for-codex --skill automate-me",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Aqua-123\u002Fpstack-for-codex --skill automate-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Fautomate-me\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",289,"https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Fautomate-me\u002Fagents\u002Fopenai.yaml",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7B4B801F05H7M25W5R1WPTC","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\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7B4B6AX64TQTHQ6S1J724FA","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7B4B4H352GFCSGK6TW53CK1","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7B4B0S042R380EPHBDDWC37","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for $technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7B4AXQTEMW7E7ZVV5SK3MPA","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\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7B4ATQP0JBSBYC0Z43J2FSE","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002FAqua-123\u002Fpstack-for-codex\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]