[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7VAF6C0Z5H8HM4DDCSTHP":3,"skill-same:01M7F7VAF6C0Z5H8HM4DDCSTHP":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7F7VAF6C0Z5H8HM4DDCSTHP","automate-me",null,"Turn the user's preferences or working style into a personal -mode skill, drafted or revised from recent sessions. Use for automate me or capture my style.","bitgineer\u002Fopencode-pstack","bitgineer","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F133060368?v=4","01M7F7V139SDYHXSH9GXXM8EV7","01M7F7V13Y1ZZCY3J922JX06QC",1,"MIT","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fautomate-me\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: automate-me\ndescription: \"Turn the user's preferences or working style into a personal -mode skill, drafted or revised from recent sessions. Use for automate me or capture my style.\"\n\n---\n\n# Automate me\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 Authoring a skill playbook in `poteto-mode` (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 `.opencode\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.config\u002Fopencode\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.opencode\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with `question` (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 sessions before fanning out with `opencode session list`, then read the ones you need with `opencode session export \u003CsessionID>`. Export only sessions started in this workspace's directory; they all live under `~\u002F.local\u002Fshare\u002Fopencode`. Don't sweep every session the database holds. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nSurvey recent sessions within that scope for recurring patterns. Run one `subagent` call per slice of history in a single turn, with `agent: \"explore\"`, the built-in read-only agent (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Do not pass a model. Each agent file carries its own, and the operator sets role models with `\u002Fpstack\u002Fsetup-pstack`. Each slice mining subagent reads the exported sessions 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 `question` tool (structured multi-choice) rather than asking the user to type from scratch.\n\nShape: one or two questions with 4-6 choices each, and say in the prompt when a question takes more than one answer. 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.\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, which agent takes which 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 Authoring a skill playbook, `playbooks\u002Fauthoring-a-skill.md` in the `poteto-mode` skill, to author it. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.opencode\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.opencode\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.config\u002Fopencode\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 the playbook'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. 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 the playbook's writing guidelines to every line.\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. 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.\n- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely.\n\n## Evaluation\n\nA `-mode` skill is subjective output. The playbook's test-and-iterate benchmark loop isn't 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): the Authoring a skill playbook 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","# Automate me\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 Authoring a skill playbook in `poteto-mode` (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 `.opencode\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.config\u002Fopencode\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.opencode\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with `question` (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 sessions before fanning out with `opencode session list`, then read the ones you need with `opencode session export \u003CsessionID>`. Export only sessions started in this workspace's directory; they all live under `~\u002F.local\u002Fshare\u002Fopencode`. Don't sweep every session the database holds. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nSurvey recent sessions within that scope for recurring patterns. Run one `subagent` call per slice of history in a single turn, with `agent: \"explore\"`, the built-in read-only agent (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Do not pass a model. Each agent file carries its own, and the operator sets role models with `\u002Fpstack\u002Fsetup-pstack`. Each slice mining subagent reads the exported sessions 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 `question` tool (structured multi-choice) rather than asking the user to type from scratch.\n\nShape: one or two questions with 4-6 choices each, and say in the prompt when a question takes more than one answer. 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.\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, which agent takes which 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 Authoring a skill playbook, `playbooks\u002Fauthoring-a-skill.md` in the `poteto-mode` skill, to author it. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.opencode\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.opencode\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.config\u002Fopencode\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 the playbook'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. 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 the playbook's writing guidelines to every line.\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. 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.\n- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely.\n\n## Evaluation\n\nA `-mode` skill is subjective output. The playbook's test-and-iterate benchmark loop isn't 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): the Authoring a skill playbook 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",{"name":5,"description":7},"main","dbb7a4935f614ebaec65ca3beb181bf74ed53431","skills\u002Fpstack\u002Fautomate-me",0,"https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack","https:\u002F\u002Fgithub.com\u002Fbitgineer","2026-10-21 18:58:00",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add bitgineer\u002Fopencode-pstack --skill automate-me",{"tool":36,"command":37},"bunx","bunx skills add bitgineer\u002Fopencode-pstack --skill automate-me",{"tool":39,"command":40},"pnpm","pnpm dlx skills add bitgineer\u002Fopencode-pstack --skill automate-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fautomate-me\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7F8095YEQBD1R95S3CQNM7M","why","Trace why code works this way or why a design was chosen, from source control, trackers, docs, and telemetry. Use for rationale, regressions, or postmortems.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7F807MX84XR7FGZ1YTDPNPP","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7F804Y0KW517P76ZAYQ86ED","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7F800R1VV08YF0AKMNTPZ2J","technical-writing","Write or review docs, RFCs, readmes, PR descriptions, and commit messages in Diataxis structure with Google style, STE, and Global English.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7F7ZX5TJ2049PWXHB07MA7Y","teach","Explain a body of work so a person actually understands it, running how and why and weaving both into one clear explanation. Use for teach me this.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fteach\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7F7ZSN544YPV34WWVFW332X","tdd","Use only when the user asks for TDD, a failing test, or a regression test, or when a bug has a cheap local test target; skip unclear or costly test paths.","https:\u002F\u002Fgithub.com\u002Fbitgineer\u002Fopencode-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftdd\u002FSKILL.md",[],[]]