[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ABNV9J7DN1AFRBGDBHVBY2":3,"skill-same:01M7ABNV9J7DN1AFRBGDBHVBY2":46},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7ABNV9J7DN1AFRBGDBHVBY2","write-specs",null,"Spec a feature's observable behavior. Use when asked for requirements, when a request says what the system should do but not how, or to capture what a built system already guarantees. Not for how to build it (write-plan).","j0hanz\u002Fj0hanz-marketplace","j0hanz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F159924955?v=4","01M7ABFK415CKHXYV9GZRJ16T7","Linus Johansson","01M7ABFK52FCPP2PNBH1YR7ZPA",0,"MIT","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-specs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: write-specs\ndescription: Spec a feature's observable behavior. Use when asked for requirements, when a request says what the system should do but not how, or to capture what a built system already guarantees. Not for how to build it (write-plan).\n---\n\n# Write Specs\n\nA spec fixes **what** must be observably true; a plan fixes **how**. A requirement is **black-box** or it is prose — paths, function names, and libraries belong in the plan.\n\n## Steps\n\n### 1. Ground it\n\nRead the system before describing it — existing code, related specs, whatever fixes the vocabulary. Fan out [research](..\u002Fresearch\u002FSKILL.md) where the repo holds the answer; it reads while you write. Resolve what you can from that material; where it is silent, state the default you chose as an assumption. Leave a `[NEEDS CLARIFICATION: \u003Cquestion>]` marker inline instead only where a wrong guess would invalidate a requirement rather than adjust it. Ask the user only what the material cannot answer — [grilling](..\u002Fgrilling\u002FSKILL.md) is how.\n\n**Done when** every claim is traceable on the page: a link to what you read, a quoted user answer, a line in Assumptions, or a marker.\n\n### 2. Write it\n\nFill the template. Requirements get stable IDs (`R1`, `R2`, …) — the plan references them and test names cite them verbatim ([tdd](..\u002Ftdd\u002FSKILL.md)). IDs are never renumbered; new ones append.\n\n**Done when** every requirement has a stable ID and at least one scenario, every input has a malformed-version requirement, every dependency an outage requirement, every list an empty case, and every reference out of the file is a working relative link.\n\n### 3. Falsify it\n\nIts own pass over the finished set — contradictions and missing story behavior are only visible across requirements, never inside one.\n\nPer requirement, name the single observation that proves it false, on the page beside its ID; [verify-specs](..\u002Fverify-specs\u002FSKILL.md) runs it once the change lands. If you cannot name one, it is prose — rewrite until a black-box observer could fail it. Then read the set once as a whole.\n\n**Done when** every requirement carries its falsifying observation, no two requirements contradict (no input or state triggers two requirements whose responses cannot both hold), every story in Users and stories names the requirement IDs that deliver it, and every marker appears in the open-questions list.\n\n## Requirement syntax\n\nOne obligation per statement — the gate is the falsifier in step 3. The EARS patterns below match a statement to its trigger; `shall` marks the obligation.\n\n| Pattern      | Template                                                             | Use for                    |\n| ------------ | -------------------------------------------------------------------- | -------------------------- |\n| Ubiquitous   | The `\u003Csystem>` shall `\u003Cresponse>`                                    | property that always holds |\n| State-driven | While `\u003Cstate>`, the `\u003Csystem>` shall `\u003Cresponse>`                   | holds during a condition   |\n| Event-driven | When `\u003Ctrigger>`, the `\u003Csystem>` shall `\u003Cresponse>`                  | response to an event       |\n| Optional     | Where `\u003Cfeature is included>`, the `\u003Csystem>` shall `\u003Cresponse>`     | flagged or variant builds  |\n| Unwanted     | If `\u003Ctrigger>`, then the `\u003Csystem>` shall `\u003Cresponse>`               | errors, failures, abuse    |\n| Complex      | While `\u003Cstate>`, when `\u003Ctrigger>`, the `\u003Csystem>` shall `\u003Cresponse>` | both, when both matter     |\n\nQuality claims carry a number and a measurement point — not \"fast\" but \"within 200 ms at p95, measured at the API boundary\".\n\nScenarios use Given\u002FWhen\u002FThen, one per branch:\n\n```markdown\n- **R4** When a session token has expired, the API shall reject the request.\n  - Falsified by: a read with an expired token returning anything but 401.\n  - Given an expired token, When a read is requested, Then the response is 401.\n  - Given a valid token, When a read is requested, Then the response is 200.\n```\n\n## Referencing\n\nA change keeps one directory: `docs\u002Fplan\u002FYYYY-MM-DD-\u003Cname>\u002F`, dated the day it is created — by whichever skill creates it first. Every artifact scoped to that change sits in it: `\u003Cname>.spec.md`, `\u003Cname>.delta.md` ([spec delta](#spec-delta)), `\u003Cname>.spec-hunt.md` ([spec-hunt](..\u002Fspec-hunt\u002FSKILL.md)), `\u003Cname>.plan.md`, `\u003Cname>.plan-hunt.md` ([plan-hunt](..\u002Fplan-hunt\u002FSKILL.md)), `\u003Cname>.run.md`, `\u003Cname>.verify.md`, `\u003Cname>.hunt.md` ([bug-hunt](..\u002Fbug-hunt\u002FSKILL.md)), `\u003Cname>.diagnose.md` ([diagnose](..\u002Fdiagnose\u002FSKILL.md)), `\u003Cname>.refactor.md` ([refactor](..\u002Frefactor\u002FSKILL.md)), `\u003Cname>.map.md` ([frontier](..\u002Ffrontier\u002FSKILL.md)), and the QA set `\u003Cname>.test-plan.md`, `\u003Cname>.cases.md`, `\u003Cname>.regression.md` ([write-qa](..\u002Fwrite-qa\u002FSKILL.md)).\n\nA record that outlives the change that made it sits outside those directories: decisions at `docs\u002Fadr\u002F` ([write-adr](..\u002Fwrite-adr\u002FSKILL.md)), QA standing records at `docs\u002Fqa\u002F` ([write-qa](..\u002Fwrite-qa\u002FSKILL.md)). Where such a record is numbered, the number is `NNN-\u003Cslug>`, zero-padded, the next one found by scanning its directory.\n\nLinks are relative to the file they sit in. Depth from a file to repo source:\n\n| File                             | Lives in                   | Repo root is   |\n| :------------------------------- | :------------------------- | :------------- |\n| spec, plan, run log, verdict, QA | `docs\u002Fplan\u002F\u003Cdir>\u002F`         | `..\u002F..\u002F..\u002F`    |\n| ADR                              | `docs\u002Fadr\u002F`                | `..\u002F..\u002F`       |\n| QA standing record               | `docs\u002Fqa\u002F`                 | `..\u002F..\u002F`       |\n| frontier map                     | `docs\u002Fplan\u002F\u003Cdir>\u002F`         | `..\u002F..\u002F..\u002F`    |\n| frontier ticket                  | `docs\u002Fplan\u002F\u003Cdir>\u002Ftickets\u002F` | `..\u002F..\u002F..\u002F..\u002F` |\n\n```markdown\nrelated spec [`auth spec`](auth.md)\ndecision [`ADR-004`](..\u002F..\u002F..\u002Fdocs\u002Fadr\u002F004-tokens.md)\nexisting code [`db.ts:40-60`](..\u002F..\u002F..\u002Fsrc\u002Flib\u002Fdb.ts#L40-L60)\nrequirement [`R2`](auth.md#requirements)\n```\n\nRequirement IDs are cited by label and linked to their section. Terms the spec defines stay in backticks (`token_expired`) — a reader greps for them.\n\n## Template\n\n```markdown\n# Spec: \u003Csystem or feature name>\n\n\u003COne sentence: what this does for whom.>\n\n## Why\n\n2–5 sentences. For a proposed change: the problem, who hits it, what it costs\ntoday, what is true once this exists. For an existing system: the guarantee,\nwho depends on it, what a change risks without it. Intent is what lets a\ncorrect judgment call happen later when a requirement turns out to be\nunderspecified.\n\n## Users and stories\n\nPrioritized, each a slice that could ship and be demonstrated on its own, each\nnaming the requirement IDs that deliver it:\n\n- **P1** — As a \u003Cuser>, I want \u003Ccapability>, so that \u003Coutcome>. (R1, R4)\n\n## Requirements\n\n- **R1** The `\u003Csystem>` shall …\n  - Falsified by: \u003Cthe single observation that proves it false>\n  - Given …, When …, Then …\n- **R2** If \u003Cbad input>, then the `\u003Csystem>` shall …\n  - Falsified by: …\n  - Given …, When …, Then …\n\n## Constraints\n\nNon-functional bounds. Existing decisions this must stay consistent with,\nquoted, each linked to its source ([write-adr](..\u002Fwrite-adr\u002FSKILL.md) writes\nthem): \"tokens expire at 24 h — [`ADR-004`](rel-path)\".\n\n## Out of scope\n\nWhat a reader would expect and will not get, one line of why each.\n\n## Success criteria\n\n2–4 measurable, technology-agnostic outcomes — observable without reading the\nsource.\n\n## Assumptions and open questions\n\nDefaults you chose where the input was silent, stated as choices. Then every\n`[NEEDS CLARIFICATION]` marker still in the file, each linked to the\nrequirement it blocks, with who can answer it.\n```\n\n## Spec delta\n\nAmending a spec that already exists is a **delta** against its current IDs, never an edit in place, so a reader sees exactly what moved. Write it as `\u003Cname>.delta.md` in the directory of the change that makes it — `\u003Cname>` is that change's name, under the [referencing convention](#referencing) — with a first line linking the spec it amends: \"amends [`auth spec`](auth.spec.md)\" when that spec sits in the same directory, \"amends [`auth spec`](..\u002F2026-08-13-auth\u002Fauth.spec.md)\" when an earlier change owns it. One delta per change: a later amendment in the same change adds to it. ADDED and MODIFIED entries each carry their own falsifying observation. [verify-specs](..\u002Fverify-specs\u002FSKILL.md) scores the amended spec with the delta applied, then folds the delta into it once every ID is met, IDs intact.\n\n```markdown\namends [`auth spec`](auth.spec.md)\n\n## ADDED\n\n- **R9** When … the system shall …\n  - Falsified by: …\n  - Given …, When …, Then …\n\n## MODIFIED\n\n- **R3** was: \u003Cold text> — now: \u003Cnew text>. Reason: \u003Cone line>.\n  - Falsified by: \u003Cthe observation that proves the new text false>\n  - Given …, When …, Then …\n\n## REMOVED\n\n- **R5** — \u003Cwhy it no longer applies>\n```\n\nWhen the behavior is settled, hand the spec to\n[spec-hunt](..\u002Fspec-hunt\u002FSKILL.md) — it kills the gaps a cold executor would\nhit, checked against the **Done when** lines of the three steps above. A hunt\nwith no Confirmed gap forwards to [write-plan](..\u002Fwrite-plan\u002FSKILL.md), naming\neach Suspected finding's **Settles it** check. Confirmed gaps come back here:\nfix each as a [delta](#spec-delta), then hand the spec back to spec-hunt.\n","# Write Specs\n\nA spec fixes **what** must be observably true; a plan fixes **how**. A requirement is **black-box** or it is prose — paths, function names, and libraries belong in the plan.\n\n## Steps\n\n### 1. Ground it\n\nRead the system before describing it — existing code, related specs, whatever fixes the vocabulary. Fan out [research](..\u002Fresearch\u002FSKILL.md) where the repo holds the answer; it reads while you write. Resolve what you can from that material; where it is silent, state the default you chose as an assumption. Leave a `[NEEDS CLARIFICATION: \u003Cquestion>]` marker inline instead only where a wrong guess would invalidate a requirement rather than adjust it. Ask the user only what the material cannot answer — [grilling](..\u002Fgrilling\u002FSKILL.md) is how.\n\n**Done when** every claim is traceable on the page: a link to what you read, a quoted user answer, a line in Assumptions, or a marker.\n\n### 2. Write it\n\nFill the template. Requirements get stable IDs (`R1`, `R2`, …) — the plan references them and test names cite them verbatim ([tdd](..\u002Ftdd\u002FSKILL.md)). IDs are never renumbered; new ones append.\n\n**Done when** every requirement has a stable ID and at least one scenario, every input has a malformed-version requirement, every dependency an outage requirement, every list an empty case, and every reference out of the file is a working relative link.\n\n### 3. Falsify it\n\nIts own pass over the finished set — contradictions and missing story behavior are only visible across requirements, never inside one.\n\nPer requirement, name the single observation that proves it false, on the page beside its ID; [verify-specs](..\u002Fverify-specs\u002FSKILL.md) runs it once the change lands. If you cannot name one, it is prose — rewrite until a black-box observer could fail it. Then read the set once as a whole.\n\n**Done when** every requirement carries its falsifying observation, no two requirements contradict (no input or state triggers two requirements whose responses cannot both hold), every story in Users and stories names the requirement IDs that deliver it, and every marker appears in the open-questions list.\n\n## Requirement syntax\n\nOne obligation per statement — the gate is the falsifier in step 3. The EARS patterns below match a statement to its trigger; `shall` marks the obligation.\n\n| Pattern      | Template                                                             | Use for                    |\n| ------------ | -------------------------------------------------------------------- | -------------------------- |\n| Ubiquitous   | The `\u003Csystem>` shall `\u003Cresponse>`                                    | property that always holds |\n| State-driven | While `\u003Cstate>`, the `\u003Csystem>` shall `\u003Cresponse>`                   | holds during a condition   |\n| Event-driven | When `\u003Ctrigger>`, the `\u003Csystem>` shall `\u003Cresponse>`                  | response to an event       |\n| Optional     | Where `\u003Cfeature is included>`, the `\u003Csystem>` shall `\u003Cresponse>`     | flagged or variant builds  |\n| Unwanted     | If `\u003Ctrigger>`, then the `\u003Csystem>` shall `\u003Cresponse>`               | errors, failures, abuse    |\n| Complex      | While `\u003Cstate>`, when `\u003Ctrigger>`, the `\u003Csystem>` shall `\u003Cresponse>` | both, when both matter     |\n\nQuality claims carry a number and a measurement point — not \"fast\" but \"within 200 ms at p95, measured at the API boundary\".\n\nScenarios use Given\u002FWhen\u002FThen, one per branch:\n\n```markdown\n- **R4** When a session token has expired, the API shall reject the request.\n  - Falsified by: a read with an expired token returning anything but 401.\n  - Given an expired token, When a read is requested, Then the response is 401.\n  - Given a valid token, When a read is requested, Then the response is 200.\n```\n\n## Referencing\n\nA change keeps one directory: `docs\u002Fplan\u002FYYYY-MM-DD-\u003Cname>\u002F`, dated the day it is created — by whichever skill creates it first. Every artifact scoped to that change sits in it: `\u003Cname>.spec.md`, `\u003Cname>.delta.md` ([spec delta](#spec-delta)), `\u003Cname>.spec-hunt.md` ([spec-hunt](..\u002Fspec-hunt\u002FSKILL.md)), `\u003Cname>.plan.md`, `\u003Cname>.plan-hunt.md` ([plan-hunt](..\u002Fplan-hunt\u002FSKILL.md)), `\u003Cname>.run.md`, `\u003Cname>.verify.md`, `\u003Cname>.hunt.md` ([bug-hunt](..\u002Fbug-hunt\u002FSKILL.md)), `\u003Cname>.diagnose.md` ([diagnose](..\u002Fdiagnose\u002FSKILL.md)), `\u003Cname>.refactor.md` ([refactor](..\u002Frefactor\u002FSKILL.md)), `\u003Cname>.map.md` ([frontier](..\u002Ffrontier\u002FSKILL.md)), and the QA set `\u003Cname>.test-plan.md`, `\u003Cname>.cases.md`, `\u003Cname>.regression.md` ([write-qa](..\u002Fwrite-qa\u002FSKILL.md)).\n\nA record that outlives the change that made it sits outside those directories: decisions at `docs\u002Fadr\u002F` ([write-adr](..\u002Fwrite-adr\u002FSKILL.md)), QA standing records at `docs\u002Fqa\u002F` ([write-qa](..\u002Fwrite-qa\u002FSKILL.md)). Where such a record is numbered, the number is `NNN-\u003Cslug>`, zero-padded, the next one found by scanning its directory.\n\nLinks are relative to the file they sit in. Depth from a file to repo source:\n\n| File                             | Lives in                   | Repo root is   |\n| :------------------------------- | :------------------------- | :------------- |\n| spec, plan, run log, verdict, QA | `docs\u002Fplan\u002F\u003Cdir>\u002F`         | `..\u002F..\u002F..\u002F`    |\n| ADR                              | `docs\u002Fadr\u002F`                | `..\u002F..\u002F`       |\n| QA standing record               | `docs\u002Fqa\u002F`                 | `..\u002F..\u002F`       |\n| frontier map                     | `docs\u002Fplan\u002F\u003Cdir>\u002F`         | `..\u002F..\u002F..\u002F`    |\n| frontier ticket                  | `docs\u002Fplan\u002F\u003Cdir>\u002Ftickets\u002F` | `..\u002F..\u002F..\u002F..\u002F` |\n\n```markdown\nrelated spec [`auth spec`](auth.md)\ndecision [`ADR-004`](..\u002F..\u002F..\u002Fdocs\u002Fadr\u002F004-tokens.md)\nexisting code [`db.ts:40-60`](..\u002F..\u002F..\u002Fsrc\u002Flib\u002Fdb.ts#L40-L60)\nrequirement [`R2`](auth.md#requirements)\n```\n\nRequirement IDs are cited by label and linked to their section. Terms the spec defines stay in backticks (`token_expired`) — a reader greps for them.\n\n## Template\n\n```markdown\n# Spec: \u003Csystem or feature name>\n\n\u003COne sentence: what this does for whom.>\n\n## Why\n\n2–5 sentences. For a proposed change: the problem, who hits it, what it costs\ntoday, what is true once this exists. For an existing system: the guarantee,\nwho depends on it, what a change risks without it. Intent is what lets a\ncorrect judgment call happen later when a requirement turns out to be\nunderspecified.\n\n## Users and stories\n\nPrioritized, each a slice that could ship and be demonstrated on its own, each\nnaming the requirement IDs that deliver it:\n\n- **P1** — As a \u003Cuser>, I want \u003Ccapability>, so that \u003Coutcome>. (R1, R4)\n\n## Requirements\n\n- **R1** The `\u003Csystem>` shall …\n  - Falsified by: \u003Cthe single observation that proves it false>\n  - Given …, When …, Then …\n- **R2** If \u003Cbad input>, then the `\u003Csystem>` shall …\n  - Falsified by: …\n  - Given …, When …, Then …\n\n## Constraints\n\nNon-functional bounds. Existing decisions this must stay consistent with,\nquoted, each linked to its source ([write-adr](..\u002Fwrite-adr\u002FSKILL.md) writes\nthem): \"tokens expire at 24 h — [`ADR-004`](rel-path)\".\n\n## Out of scope\n\nWhat a reader would expect and will not get, one line of why each.\n\n## Success criteria\n\n2–4 measurable, technology-agnostic outcomes — observable without reading the\nsource.\n\n## Assumptions and open questions\n\nDefaults you chose where the input was silent, stated as choices. Then every\n`[NEEDS CLARIFICATION]` marker still in the file, each linked to the\nrequirement it blocks, with who can answer it.\n```\n\n## Spec delta\n\nAmending a spec that already exists is a **delta** against its current IDs, never an edit in place, so a reader sees exactly what moved. Write it as `\u003Cname>.delta.md` in the directory of the change that makes it — `\u003Cname>` is that change's name, under the [referencing convention](#referencing) — with a first line linking the spec it amends: \"amends [`auth spec`](auth.spec.md)\" when that spec sits in the same directory, \"amends [`auth spec`](..\u002F2026-08-13-auth\u002Fauth.spec.md)\" when an earlier change owns it. One delta per change: a later amendment in the same change adds to it. ADDED and MODIFIED entries each carry their own falsifying observation. [verify-specs](..\u002Fverify-specs\u002FSKILL.md) scores the amended spec with the delta applied, then folds the delta into it once every ID is met, IDs intact.\n\n```markdown\namends [`auth spec`](auth.spec.md)\n\n## ADDED\n\n- **R9** When … the system shall …\n  - Falsified by: …\n  - Given …, When …, Then …\n\n## MODIFIED\n\n- **R3** was: \u003Cold text> — now: \u003Cnew text>. Reason: \u003Cone line>.\n  - Falsified by: \u003Cthe observation that proves the new text false>\n  - Given …, When …, Then …\n\n## REMOVED\n\n- **R5** — \u003Cwhy it no longer applies>\n```\n\nWhen the behavior is settled, hand the spec to\n[spec-hunt](..\u002Fspec-hunt\u002FSKILL.md) — it kills the gaps a cold executor would\nhit, checked against the **Done when** lines of the three steps above. A hunt\nwith no Confirmed gap forwards to [write-plan](..\u002Fwrite-plan\u002FSKILL.md), naming\neach Suspected finding's **Settles it** check. Confirmed gaps come back here:\nfix each as a [delta](#spec-delta), then hand the spec back to spec-hunt.\n",{"name":5,"description":7},"main","534498267dccbe415f22f31fceac9da6771c195f","plugins\u002Fworkbench\u002Fskills\u002Fwrite-specs","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace","https:\u002F\u002Fj0hanz-marketplace.vercel.app","https:\u002F\u002Fgithub.com\u002Fj0hanz","linus-johansson-cv-d308be9b73e1.herokuapp.com","2026-11-15 02:42:07",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add j0hanz\u002Fj0hanz-marketplace --skill write-specs",{"tool":38,"command":39},"bunx","bunx skills add j0hanz\u002Fj0hanz-marketplace --skill write-specs",{"tool":41,"command":42},"pnpm","pnpm dlx skills add j0hanz\u002Fj0hanz-marketplace --skill write-specs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-specs\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7ABP78JFYBMCXJ9GMETCYZM","unslop","Use when writing or editing prose a person will read, or when text sounds AI-generated.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7ABP52BNV7NRPNBR6PCNZWC","show-me","Use when asked to show, diagram, or walk through how code fits together or what a change does, or before explaining a multi-file flow in prose.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fshow-me\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7ABP3EPN4KFB4HPJNMY31NR","pr","Use when writing or updating a pull request description, or before running `gh pr create`.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fpr\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7ABP08MXTHPZYTG4HKEP7WQ","commit","Use when writing a commit message, or before running `git commit`.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwriteup\u002Fskills\u002Fcommit\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7ABNPK2GVG8EB3SSEAMK4FZ","write-skills","Write, fix, or audit a skill's frontmatter, trigger description, and body. Use when a skill is asked for, never fires, or fires at the wrong moment. Not for a hook (write-hooks) or the plugin manifest and catalog.","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-skills\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7ABNKNKPTZ5S8E3792Q0M6P","write-qa","Write coverage-mapped QA deliverables. Use when asked for a test plan, manual test cases, a regression suite, or a bug report. Not for automated tests (tdd) or hunting bugs in code (bug-hunt).","https:\u002F\u002Fgithub.com\u002Fj0hanz\u002Fj0hanz-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkbench\u002Fskills\u002Fwrite-qa\u002FSKILL.md",[],[]]