[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD443JG9BMP0Y94CCPK44S":3,"skill-same:01M7FD443JG9BMP0Y94CCPK44S":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7FD443JG9BMP0Y94CCPK44S","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 via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.","l246804\u002Fdsh-pstack","l246804","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F53589602?v=4","01M7FD2TFY24A2KKK55FSQWJ47","leihaohao","01M7FD2TGRS2ZCQ68BRY93D89D",23,"MIT","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fpstack\u002Fskills\u002Fautomate-me\u002FSKILL.md",[],[],"2026-11-16 10:05:34",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 via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.\"\ndisable-model-invocation: true\n---\n\n# Automate me\n\nIn DeepSeek Harness, read [the DSH adapter](..\u002F..\u002Fdocs\u002Fharness\u002Fdsh.md) once per session before you follow this skill. It maps the Cursor names in pstack skills to DeepSeek Harness.\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), Cursor's built-in `create-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 `.cursor\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.cursor\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.cursor\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with `AskQuestion` (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\nLocate the active workspace's transcripts before fanning out. The system prompt names the workspace's `agent-transcripts\u002F` directory. Use only that path. Don't glob across `~\u002F.cursor\u002Fprojects\u002F*\u002F`. That crosses workspace boundaries and reads private chats from unrelated projects.\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). Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill. 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 `AskQuestion` tool (structured multi-choice) rather than asking the user to type from scratch.\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.\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 Cursor's built-in `create-skill` skill to author the skill. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.cursor\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.cursor\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.cursor\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 `create-skill`'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 `create-skill`'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. A `create-skill`-style test\u002Fiterate 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): `create-skill` 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\nIn DeepSeek Harness, read [the DSH adapter](..\u002F..\u002Fdocs\u002Fharness\u002Fdsh.md) once per session before you follow this skill. It maps the Cursor names in pstack skills to DeepSeek Harness.\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), Cursor's built-in `create-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 `.cursor\u002Fskills\u002F**\u002F*-mode\u002FSKILL.md` and `~\u002F.cursor\u002Fskills\u002F*-mode\u002FSKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.cursor\u002Fskills\u002F\u003Chandle>\u002F`), not only at the top level. If one exists, confirm intent with `AskQuestion` (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\nLocate the active workspace's transcripts before fanning out. The system prompt names the workspace's `agent-transcripts\u002F` directory. Use only that path. Don't glob across `~\u002F.cursor\u002Fprojects\u002F*\u002F`. That crosses workspace boundaries and reads private chats from unrelated projects.\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). Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill. 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 `AskQuestion` tool (structured multi-choice) rather than asking the user to type from scratch.\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.\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 Cursor's built-in `create-skill` skill to author the skill. Placement:\n\n- Path: preserve an existing mode skill's category. For a new mode, use `.cursor\u002Fskills\u002F\u003Chandle>\u002F\u003Chandle>-mode\u002FSKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.cursor\u002Fskills\u002F\u003Chandle>-mode\u002FSKILL.md` in the project (or `~\u002F.cursor\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 `create-skill`'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 `create-skill`'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. A `create-skill`-style test\u002Fiterate 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): `create-skill` 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,"disable-model-invocation":24},true,"main","df33da1bb4942fbd2761c305edb3785093ec1055","pstack\u002Fskills\u002Fautomate-me",4,"https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack","https:\u002F\u002Fgithub.com\u002Fl246804","2026-11-15 16:09:02",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add l246804\u002Fdsh-pstack --skill automate-me",{"tool":38,"command":39},"bunx","bunx skills add l246804\u002Fdsh-pstack --skill automate-me",{"tool":41,"command":42},"pnpm","pnpm dlx skills add l246804\u002Fdsh-pstack --skill automate-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fpstack\u002Fskills\u002Fautomate-me\u002FSKILL.md",[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7FDC7PA7ACJ95HW5T1N9ZJ3","setup-project-docs","Bootstrap architecture, glossary, decision-record conventions, and root agent-doc pointers; rerun to fill approved gaps.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fsetup-project-docs\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FDC35BXG4PW3HG16BXF5FG","docs-drift","Audit living project documentation for drift and redundancy; repair approved findings.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdocs-drift\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7FDBZ7PP5T1V4Q1MEP95BGM","decision-write","Write, update, land, or supersede decision records. Use for resolved alternatives, missing rationale, reversed decisions, or record-file changes. Land finds and verifies the implementation; Review-only updates keep the current status.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdecision-write\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FDBVXYSHCB2E52HKS2TH2E","decision-audit","Read-only audit of decision records for a PR, local changes, or the whole repository. Report routing, status, scope, anchor, supersession, and overdue-review findings with command evidence.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002Fauthored\u002Fdecision-audit\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7FDBSF0V6HTFHD5PHDC6BAM","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7FDBQPY2F8PSNJKTGZ6AYD6","retro","Conduct a retrospective on a coding session.","https:\u002F\u002Fgithub.com\u002Fl246804\u002Fdsh-pstack\u002Fblob\u002Fmain\u002Fskills\u002F.agents\u002Fskills\u002Fretro\u002FSKILL.md",[],[]]