[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GSVHQ4MY4R4SMS8RY6324Q":3,"skill-same:01M6GSVHQ4MY4R4SMS8RY6324Q":113},{"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":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M6GSVHQ4MY4R4SMS8RY6324Q","prd-ralph",null,"Complete at most one eligible unfinished PRD task, verify it, log progress, and optionally create one scoped commit.","japurcell\u002Fskills","japurcell","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10947458?v=4","01M6GSJK1YAG95R6VHF47V30KY","Adam Purcell","01M6GSJK6817NVR5FVDMFFNJ6H",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"prd ralph","prd","ralph","false","scoped","path","at","it","complete","progress","id","commit","task","log","verify","file","create","2026-11-10 10:12:30",false,"---\nname: prd-ralph\ndescription: Complete at most one eligible unfinished PRD task, verify it, log progress, and optionally create one scoped commit.\nargument-hint: '\u003Cprd-file> [progress_file \u003Cpath>] [task_id \u003Cid>] [commit false]'\n---\n\n# \u002Fprd-ralph\n\nComplete **at most one** eligible unfinished task from `prd_file`.\n\n## Inputs\n\n- `prd_file` required\n- `progress_file` optional; default: `\u003Cdirname(prd_file)>\u002Fprogress.txt`\n- `task_id` optional\n- `commit` optional; default: `true`\n  - Only boolean `false` or string `\"false\"` disables commit.\n\n## Core rules\n\n- Do not interview the user. Make reasonable assumptions and record them in `progress_file`.\n- Treat `prd_file` as the source of truth.\n- Never invent commands, paths, requirements, or acceptance criteria.\n- After any command\u002Ftool failure or timeout, read `references\u002Ffailures.md`.\n- Never commit `prd_file`, `progress_file`, unrelated changes, or blocked\u002Ffailing work.\n- Set `passes: true` only after:\n  1. required verification passes,\n  2. progress is appended,\n  3. commit rules are satisfied,\n  4. all session commits are recorded and audited.\n- A session commit is any commit in:\n  `git log --oneline \u003Csession_start_head>..HEAD`\n- If session commit audit fails, block and do not set `passes: true`.\n\n## References\n\nRead when triggered:\n\n- `references\u002Fverification.md` — before verification.\n- `references\u002Fbrowser-verification.md` — when browser\u002FUI\u002Fauth\u002Frouting\u002FDOM\u002Finteractive behavior is mentioned or implied.\n- `references\u002Ffailures.md` — after any command\u002Ftool failure or timeout.\n- `references\u002Fcommit.md` — after verification passes when commit is enabled.\n- `references\u002Fprogress.md` — before appending progress.\n\n## Workflow\n\n### 1. Prepare\n\n1. Read `prd_file` and `references\u002Fintake.md`. Validate the entire manifest before selection or completion detection. If unreadable or invalid, emit the blocked protocol and stop.\n2. If the validated nonempty manifest has all `tasks[].passes` equal to `true`, or authoritative source explicitly establishes a validated no-work result, output exactly:\n   `\u003Cpromise>COMPLETE\u003C\u002Fpromise>`\n   Then stop.\n3. Resolve `progress_file`:\n   - if missing, create it with `## Codebase Patterns` at the top\n   - otherwise read it, especially `## Codebase Patterns`\n4. Read repo guidance files if present: `AGENTS.md`, `GEMINI.md`, `CLAUDE.md`.\n5. Run:\n   - `git log --oneline -20`\n   - `git rev-parse --verify HEAD`\n6. Save `HEAD` as `session_start_head`.\n7. If any prepare command fails or times out:\n   - read `references\u002Ffailures.md` and `references\u002Fprogress.md`\n   - append a `PREPARE` progress block\n   - stop if `prd_file` is unreadable, task selection is unsafe, or `session_start_head` is unavailable\n\n### 2. Select one task\n\nA task is eligible only when:\n\n- `passes: false`\n- every `dependsOn` task has `passes: true`\n- `dependsOn: []` means no dependencies\n\nSelection:\n\n- If `task_id` is provided, use it only if it exists, is unfinished, and dependencies pass. Otherwise stop and report why.\n- If `task_id` is omitted, choose the eligible unfinished task with the lowest numeric `priority`.\n- Break ties by PRD order.\n- If no task is eligible, emit `\u003Cpromise>BLOCKED\u003C\u002Fpromise>` and list actionable blockers.\n\nRead every selected task field, resolve its source\u002Fcontext references, and inspect prerequisite evidence\u002Fcurrent state as required by `references\u002Fintake.md` before execution. Priority never bypasses a prerequisite.\n\nBefore implementation, inspect the selected task. If requirements or acceptance criteria are missing, unsafe, or contradictory:\n\n1. read `references\u002Fprogress.md`\n2. append a blocked progress block\n3. stop\n\n### 3. Implement\n\n1. Execute the selected `taskType` outcome within user scope and owner limits. Activate the `tdd` skill before designing or editing source code; for noncode work collect real, outcome-appropriate evidence. A decision requiring owner approval stays blocked.\n2. Follow only the selected task’s:\n   - `description`\n   - `acceptanceCriteria`\n   - `filesLikelyTouched`\n   - `designGuidance`\n   - `sourceRefs`, `requiredContext`, `taskType`, and `verification`\n   - prerequisite guarantees, repo guidance, user constraints, and patterns\n3. For testable code changes:\n   - RED: add a failing test for the required behavior.\n   - GREEN: make the smallest passing change.\n   - REFACTOR: only if needed while tests stay green.\n4. For doc\u002Fconfig-only work:\n   - do not invent tests\n   - record why command verification is not applicable in `progress_file`, if true\n5. If any command\u002Ftool fails or times out, read `references\u002Ffailures.md`.\n\n### 4. Verify\n\n1. Read `references\u002Fverification.md`.\n2. Execute every required manifest check plus real applicable repo\u002Facceptance checks. Verify not-applicable reasons against actual scope. Unresolved checks block; never waive a failing check. See the reference for per-check evidence.\n3. If browser-visible behavior is mentioned or implied, read and apply `references\u002Fbrowser-verification.md`.\n4. Record exact commands\u002Fchecks, concise output, and exit codes.\n5. If any command\u002Ftool fails or times out, read `references\u002Ffailures.md`.\n\n### 5. Finish\n\nRescan the selected task for acceptance criteria and required verification.\n\nTo audit session commits:\n\n1. Run `git log --oneline \u003Csession_start_head>..HEAD`.\n2. For each listed commit, run `git show --name-only --format=oneline \u003Chash>`.\n3. Include every session commit in the next progress block.\n\nIf verification failed or is missing:\n\n1. Do not set `passes: true`.\n2. Do not commit.\n3. Audit session commits.\n4. If any session commit exists, the commit gate is blocked.\n5. Read `references\u002Fprogress.md`.\n6. Append progress with blocker evidence, failures, session commits, and any commit-gate blocker.\n7. Report blocker and stop.\n\nIf verification passed and commit is enabled:\n\n1. Read and follow `references\u002Fcommit.md`.\n2. Create exactly one scoped commit for task changes.\n3. Audit session commits.\n4. If the commit gate is blocked:\n   - do not set `passes: true`\n   - read `references\u002Fprogress.md`\n   - append progress with verification evidence, failures, commit blocker, and session commits\n   - report blocker and stop\n5. Read `references\u002Fprogress.md`.\n6. Append progress with verification evidence, failures, task commit, commit-gate result, and session commits.\n7. Set the selected task’s `passes` to `true` in `prd_file`.\n8. Leave `prd_file` and `progress_file` uncommitted.\n\nIf verification passed and commit is disabled:\n\n1. Do not commit.\n2. Audit session commits.\n3. If any session commit exists, the commit gate is blocked.\n4. Read `references\u002Fprogress.md`.\n5. Append progress with verification evidence, failures, `disabled by input`, commit-gate result, and session commits.\n6. If the commit gate is blocked:\n   - do not set `passes: true`\n   - report blocker and stop\n7. Set the selected task’s `passes` to `true` in `prd_file`.\n\n### 6. Final response\n\nBefore responding, confirm:\n\n- progress was appended for any attempted selected task\n- every command\u002Ftool failure or timeout was recorded in `progress_file`\n- every mistake and\u002For workaround and human correction was recorded in `Learnings`\n- verification passed or the task was blocked\n- commit gate passed or the task was blocked\n- all session commits were recorded in `progress_file`\n- if commit was enabled and passed, the commit excludes `prd_file` and `progress_file`\n- if commit was disabled and passed, no commit was created\n\nIf all `tasks[].passes` are now `true` and commit gate rules are satisfied, output exactly:\n\n```xml\n\u003Cpromise>COMPLETE\u003C\u002Fpromise>\n```\n\nIf the selected task passed and unfinished work remains, emit `\u003Cpromise>TASK_COMPLETE\u003C\u002Fpromise>` followed by the selected-task summary. For any blocked outcome emit `\u003Cpromise>BLOCKED\u003C\u002Fpromise>` followed by the actionable reason, including invalid input, missing context, no eligible task, owner approval, unresolved verification, or commit gates. Never emit task completion for a blocked attempt.\n\nIn either nonterminal summary include:\n\n- task completed or blocked\n- verification results\n- browser evidence, if required\n- command\u002Ftool failures or timeouts, if any\n- files changed\n- commit status\n- session commits\n","# \u002Fprd-ralph\n\nComplete **at most one** eligible unfinished task from `prd_file`.\n\n## Inputs\n\n- `prd_file` required\n- `progress_file` optional; default: `\u003Cdirname(prd_file)>\u002Fprogress.txt`\n- `task_id` optional\n- `commit` optional; default: `true`\n  - Only boolean `false` or string `\"false\"` disables commit.\n\n## Core rules\n\n- Do not interview the user. Make reasonable assumptions and record them in `progress_file`.\n- Treat `prd_file` as the source of truth.\n- Never invent commands, paths, requirements, or acceptance criteria.\n- After any command\u002Ftool failure or timeout, read `references\u002Ffailures.md`.\n- Never commit `prd_file`, `progress_file`, unrelated changes, or blocked\u002Ffailing work.\n- Set `passes: true` only after:\n  1. required verification passes,\n  2. progress is appended,\n  3. commit rules are satisfied,\n  4. all session commits are recorded and audited.\n- A session commit is any commit in:\n  `git log --oneline \u003Csession_start_head>..HEAD`\n- If session commit audit fails, block and do not set `passes: true`.\n\n## References\n\nRead when triggered:\n\n- `references\u002Fverification.md` — before verification.\n- `references\u002Fbrowser-verification.md` — when browser\u002FUI\u002Fauth\u002Frouting\u002FDOM\u002Finteractive behavior is mentioned or implied.\n- `references\u002Ffailures.md` — after any command\u002Ftool failure or timeout.\n- `references\u002Fcommit.md` — after verification passes when commit is enabled.\n- `references\u002Fprogress.md` — before appending progress.\n\n## Workflow\n\n### 1. Prepare\n\n1. Read `prd_file` and `references\u002Fintake.md`. Validate the entire manifest before selection or completion detection. If unreadable or invalid, emit the blocked protocol and stop.\n2. If the validated nonempty manifest has all `tasks[].passes` equal to `true`, or authoritative source explicitly establishes a validated no-work result, output exactly:\n   `\u003Cpromise>COMPLETE\u003C\u002Fpromise>`\n   Then stop.\n3. Resolve `progress_file`:\n   - if missing, create it with `## Codebase Patterns` at the top\n   - otherwise read it, especially `## Codebase Patterns`\n4. Read repo guidance files if present: `AGENTS.md`, `GEMINI.md`, `CLAUDE.md`.\n5. Run:\n   - `git log --oneline -20`\n   - `git rev-parse --verify HEAD`\n6. Save `HEAD` as `session_start_head`.\n7. If any prepare command fails or times out:\n   - read `references\u002Ffailures.md` and `references\u002Fprogress.md`\n   - append a `PREPARE` progress block\n   - stop if `prd_file` is unreadable, task selection is unsafe, or `session_start_head` is unavailable\n\n### 2. Select one task\n\nA task is eligible only when:\n\n- `passes: false`\n- every `dependsOn` task has `passes: true`\n- `dependsOn: []` means no dependencies\n\nSelection:\n\n- If `task_id` is provided, use it only if it exists, is unfinished, and dependencies pass. Otherwise stop and report why.\n- If `task_id` is omitted, choose the eligible unfinished task with the lowest numeric `priority`.\n- Break ties by PRD order.\n- If no task is eligible, emit `\u003Cpromise>BLOCKED\u003C\u002Fpromise>` and list actionable blockers.\n\nRead every selected task field, resolve its source\u002Fcontext references, and inspect prerequisite evidence\u002Fcurrent state as required by `references\u002Fintake.md` before execution. Priority never bypasses a prerequisite.\n\nBefore implementation, inspect the selected task. If requirements or acceptance criteria are missing, unsafe, or contradictory:\n\n1. read `references\u002Fprogress.md`\n2. append a blocked progress block\n3. stop\n\n### 3. Implement\n\n1. Execute the selected `taskType` outcome within user scope and owner limits. Activate the `tdd` skill before designing or editing source code; for noncode work collect real, outcome-appropriate evidence. A decision requiring owner approval stays blocked.\n2. Follow only the selected task’s:\n   - `description`\n   - `acceptanceCriteria`\n   - `filesLikelyTouched`\n   - `designGuidance`\n   - `sourceRefs`, `requiredContext`, `taskType`, and `verification`\n   - prerequisite guarantees, repo guidance, user constraints, and patterns\n3. For testable code changes:\n   - RED: add a failing test for the required behavior.\n   - GREEN: make the smallest passing change.\n   - REFACTOR: only if needed while tests stay green.\n4. For doc\u002Fconfig-only work:\n   - do not invent tests\n   - record why command verification is not applicable in `progress_file`, if true\n5. If any command\u002Ftool fails or times out, read `references\u002Ffailures.md`.\n\n### 4. Verify\n\n1. Read `references\u002Fverification.md`.\n2. Execute every required manifest check plus real applicable repo\u002Facceptance checks. Verify not-applicable reasons against actual scope. Unresolved checks block; never waive a failing check. See the reference for per-check evidence.\n3. If browser-visible behavior is mentioned or implied, read and apply `references\u002Fbrowser-verification.md`.\n4. Record exact commands\u002Fchecks, concise output, and exit codes.\n5. If any command\u002Ftool fails or times out, read `references\u002Ffailures.md`.\n\n### 5. Finish\n\nRescan the selected task for acceptance criteria and required verification.\n\nTo audit session commits:\n\n1. Run `git log --oneline \u003Csession_start_head>..HEAD`.\n2. For each listed commit, run `git show --name-only --format=oneline \u003Chash>`.\n3. Include every session commit in the next progress block.\n\nIf verification failed or is missing:\n\n1. Do not set `passes: true`.\n2. Do not commit.\n3. Audit session commits.\n4. If any session commit exists, the commit gate is blocked.\n5. Read `references\u002Fprogress.md`.\n6. Append progress with blocker evidence, failures, session commits, and any commit-gate blocker.\n7. Report blocker and stop.\n\nIf verification passed and commit is enabled:\n\n1. Read and follow `references\u002Fcommit.md`.\n2. Create exactly one scoped commit for task changes.\n3. Audit session commits.\n4. If the commit gate is blocked:\n   - do not set `passes: true`\n   - read `references\u002Fprogress.md`\n   - append progress with verification evidence, failures, commit blocker, and session commits\n   - report blocker and stop\n5. Read `references\u002Fprogress.md`.\n6. Append progress with verification evidence, failures, task commit, commit-gate result, and session commits.\n7. Set the selected task’s `passes` to `true` in `prd_file`.\n8. Leave `prd_file` and `progress_file` uncommitted.\n\nIf verification passed and commit is disabled:\n\n1. Do not commit.\n2. Audit session commits.\n3. If any session commit exists, the commit gate is blocked.\n4. Read `references\u002Fprogress.md`.\n5. Append progress with verification evidence, failures, `disabled by input`, commit-gate result, and session commits.\n6. If the commit gate is blocked:\n   - do not set `passes: true`\n   - report blocker and stop\n7. Set the selected task’s `passes` to `true` in `prd_file`.\n\n### 6. Final response\n\nBefore responding, confirm:\n\n- progress was appended for any attempted selected task\n- every command\u002Ftool failure or timeout was recorded in `progress_file`\n- every mistake and\u002For workaround and human correction was recorded in `Learnings`\n- verification passed or the task was blocked\n- commit gate passed or the task was blocked\n- all session commits were recorded in `progress_file`\n- if commit was enabled and passed, the commit excludes `prd_file` and `progress_file`\n- if commit was disabled and passed, no commit was created\n\nIf all `tasks[].passes` are now `true` and commit gate rules are satisfied, output exactly:\n\n```xml\n\u003Cpromise>COMPLETE\u003C\u002Fpromise>\n```\n\nIf the selected task passed and unfinished work remains, emit `\u003Cpromise>TASK_COMPLETE\u003C\u002Fpromise>` followed by the selected-task summary. For any blocked outcome emit `\u003Cpromise>BLOCKED\u003C\u002Fpromise>` followed by the actionable reason, including invalid input, missing context, no eligible task, owner approval, unresolved verification, or commit gates. Never emit task completion for a blocked attempt.\n\nIn either nonterminal summary include:\n\n- task completed or blocked\n- verification results\n- browser evidence, if required\n- command\u002Ftool failures or timeouts, if any\n- files changed\n- commit status\n- session commits\n",{"name":5,"description":7,"argument-hint":46},"\u003Cprd-file> [progress_file \u003Cpath>] [task_id \u003Cid>] [commit false]","main","2ce71d590264b43342c52d3011b0097c5ece7e21","skills\u002Fdefault\u002Fprd-ralph","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills","https:\u002F\u002Fgithub.com\u002Fjapurcell","2026-11-11 08:59:34",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add japurcell\u002Fskills --skill prd-ralph",{"tool":59,"command":60},"bunx","bunx skills add japurcell\u002Fskills --skill prd-ralph",{"tool":62,"command":63},"pnpm","pnpm dlx skills add japurcell\u002Fskills --skill prd-ralph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002FSKILL.md",true,[67,73,77,81,85,89,93,97,101,105,109],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Fevals.json","REFERENCE","参考文档",5242,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Fevals\u002Fevals.json",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"evals\u002Ffiles\u002Fenriched\u002Ftasks.json",4535,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Fevals\u002Ffiles\u002Fenriched\u002Ftasks.json",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"evals\u002Ffiles\u002Fpartial-complete\u002Ftasks.json",1533,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Fevals\u002Ffiles\u002Fpartial-complete\u002Ftasks.json",{"path":82,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":83,"sourceHtmlUrl":84},"evals\u002Ffiles\u002Funresolved\u002Ftasks.json",4846,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Fevals\u002Ffiles\u002Funresolved\u002Ftasks.json",{"path":86,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":87,"sourceHtmlUrl":88},"evals\u002FREADME.md",684,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Fevals\u002FREADME.md",{"path":90,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fbrowser-verification.md",1372,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Fbrowser-verification.md",{"path":94,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fcommit.md",2109,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Fcommit.md",{"path":98,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Ffailures.md",800,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Ffailures.md",{"path":102,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fintake.md",3386,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Fintake.md",{"path":106,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fprogress.md",2486,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Fprogress.md",{"path":110,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fverification.md",2051,"https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fprd-ralph\u002Freferences\u002Fverification.md",[114,138,167,190,211,230],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":41},"01M6PT0ZTYCN4DHK3SXWS79WSY","spec-create","Create or revise a portable behavioral SPEC for a feature or whole product. Use when specifying a new idea, documenting an existing system for reimplementation, or defining a change while preserving compatibility. Implementation planning is a separate task.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fspec-create\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[40,122,123,124,125,126,127,128,129,36,130,131,132,133,134,135,136,137,29],"spec","spec create","feature","planning","for","system","use","Existing","output","change","product","implementation","revise","compatibility","behavioral","idea",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":41},"01M6GSYMGHE2FEGEFKD926EJH8","fsdp-style-guide","Mandatory for all UI\u002FUX design, implementation, review, audit, or visual regression tasks. Always use for any work that affects user-facing appearance, behavior, accessibility, branding, layout, navigation, forms, dialogs, alerts, tables, or visual design.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Ffsdp-style-guide\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",[148,149,150,151,152,153,154,155,128,156,157,158,159,160,161,162,163,164,165,166,126],"fsdp style guide","style guide","FSDP","style","guide","visual regression","regression","design","visual","tasks","review","visual design","alerts","work","branding","layout","audit","ux","behavior",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":41},"01M6GSYHEQARNM7WN0RJA7K7T2","agency-priorities","Provide self-contained USDA strategic goals and Forest Service priorities for agency briefings, proposals, and work-plan alignment. Use when explaining agency direction or evaluating how a project contributes to USDA and Forest Service priorities.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Fagency-priorities\u002FSKILL.md",[],[174,175,176,177,178,161,179,180,181,182,183,184,185,186,128,126,187,188,189],"agency priorities","priorities","agency","self","alignment","plan","goals","proposals","direction","how","project","strategic","service","when","briefings","self-contained",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":41},"01M6GSY9VVN8RSJ5QYM540ZJ1D","accomplishment-report","Create a concise Forest Service executive accomplishment report when all work in an ExecPlan is completed, or update its existing report. Use at ExecPlan closeout and when asked to report completed work, agency alignment, and estimated AI-assisted versus human-only time and cost savings.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fforest-service\u002Faccomplishment-report\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员",[200,201,178,202,40,161,203,204,205,206,30,176,207,186,128,208,209,210,129,187],"report","accomplishment report","cost","concise","human","time","update","only","closeout","savings","execplan",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":225,"publishedAt":41},"01M6GSY7J8ZMCE319P8Y6JZ432","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fwriting-for-agents\u002FSKILL.md",[217,222],{"categoryNo":218,"categoryName":219,"taxonomyType":220,"taxonomyTypeDesc":221},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":223,"categoryName":224,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[226,227,126,128,228,229,187],"writing","writing for agents","documents","editing",{"skillNo":231,"name":232,"nameZh":6,"description":233,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":234,"categories":235,"keywords":236,"publishedAt":41},"01M6GSY44J636RZ4NEVAC6KTG3","web-performance","Optimize web performance for faster loading and better user experience. Use when asked to \"speed up my site\", \"optimize performance\", \"reduce load time\", \"fix slow loading\", \"improve page speed\", or \"performance audit\".","https:\u002F\u002Fgithub.com\u002Fjapurcell\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdefault\u002Fweb-performance\u002FSKILL.md",[],[237,238,239,240,205,241,242,243,244,164,245,246,247,248,128,249,250,251,252,253,187,254,255,126],"performance","web performance","web","loading","up","fix","improve","optimize","user experience","my","page","speed","load","quality","optimize web","site","user","reduce","performance audit"]