[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753RJB0MH7PSMHJAVGNG97C":3,"skill-same:01M753RJB0MH7PSMHJAVGNG97C":61},{"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},"01M753RJB0MH7PSMHJAVGNG97C","technical-spec",null,"Persists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree — one folder per feature, one file per concern. Invoke-only — discovery runs it at design sign-off and preflight's drift check reads its output; the user runs it via \u002Ftechnical-spec when they say \"save spec\", \"document this\", \"write up what we decided\", \"record the decision rationale\", \"spec this out\", \"save this PRD\", or \"write up the requirements\" — recording decisions for the future is spec work even when phrased as remembering. Not for turning a rough idea into a design first — that's discovery.","jabworks\u002Fagentic-toolkit","jabworks","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F159094119?v=4","01M753P4JBZBTT7WN1PJBPZJZP","JAB Works","01M753P4K5KDGEWGXWT811BZET",2,"MIT","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: technical-spec\ndescription: \"Persists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree — one folder per feature, one file per concern. Invoke-only — discovery runs it at design sign-off and preflight's drift check reads its output; the user runs it via \u002Ftechnical-spec when they say \\\"save spec\\\", \\\"document this\\\", \\\"write up what we decided\\\", \\\"record the decision rationale\\\", \\\"spec this out\\\", \\\"save this PRD\\\", or \\\"write up the requirements\\\" — recording decisions for the future is spec work even when phrased as remembering. Not for turning a rough idea into a design first — that's discovery.\"\ndisable-model-invocation: true\n---\n\n# Save Tech Spec\n\n## Overview\n\nPersists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree. One folder per feature, one file per concern — future sessions load only what they need. Specs are living contracts: `\u002Fpreflight`'s Drift Check compares the implementation against them at end-of-task.\n\n## Spec Folder Layout\n\nAll specs live under one `specs\u002F` tree at the **git root**, mirroring the\nrepo structure. The scaffold script detects the nearest package root (walking\nup from CWD to the git root, finding the first `package.json`, `Cargo.toml`,\n`go.mod`, or `pyproject.toml`) and uses its path *relative to the git root*\nto place the spec.\n\n```\n\u003Cgit-root>\u002Fspecs\u002F\n  {feature-slug}\u002F           # cross-cutting, or scaffolded from the repo root\n  apps\u002Fweb\u002F\n    {feature-slug}\u002F         # scaffolded while working in apps\u002Fweb\n      index.md              # purpose, TOC, last updated, PR stamp, changelog  ← scaffold creates this\n      prd.md                # Requirements: problem, users, goals\u002Fnon-goals, metrics, scope\n      decisions.md          # Design decisions with context + rationale\n      api.md                # Endpoints, types, external APIs consumed\n      fields.md             # Field mappings: BE\u002F3rd-party → UI, or forwarding chains\n      implementation.md     # Key files, patterns, how it hangs together\n      quirks.md             # Edge cases, gotchas, known issues\n```\n\nSlugs are kebab-case and acronym-aware: `WanConfig` → `wan-config`,\n`UIFormControls` → `ui-form-controls`.\n\nIn a single-package repo the package root is the git root, so specs land at\n`specs\u002F\u003Cslug>\u002F`. In a monorepo working on `apps\u002Fweb`, they land at\n`specs\u002Fapps\u002Fweb\u002F\u003Cslug>\u002F` — one browsable tree, with a natural home for\ncross-cutting features at `specs\u002F\u003Cslug>\u002F`.\n\nExisting specs co-located inside packages (`apps\u002Fweb\u002Fspecs\u002F…`) are not\nauto-migrated — `git mv` them into the root tree if you want them unified.\n\nOnly create files that have actual content. Don't create empty files.\n\n## Workflow\n\nInfer the feature name (ask if unclear) → confirm with the user before\nwriting → run the scaffold script → write or update the concern files and\n`index.md` → offer the live HTML preview. Each step is specified in the\nsections below.\n\n**When `discovery` calls this at sign-off**, the design document already\nexists and has since the design's first section — discovery creates it at §1\nand appends to it as each section is agreed. So the input here is a finished\nfile on disk, not a summary reconstructed from the conversation: read\n`.condux\u002Fdesigns\u002FYYYY-MM-DD-\u003Cfeature>.md` and map its sections into the\nconcern files. Its `§0 · requirements` part uses `prd.md`'s six headings\nverbatim, so that mapping is a copy, heading for heading. Discovery's own\npreview server is already running against that file, so the live-preview\noffer below applies to the *spec directory* only — never start a second\nserver for the design.\n\n## Required Notifications\n\nAlways announce and confirm before writing or editing. Never silently modify files.\n\nNew spec:\n```\nAbout to save tech spec for `wan-config` → specs\u002Fwan-config\u002F\nProceed? [y\u002Fn]\n```\n\nUpdating existing spec:\n```\nUpdating spec for `wan-config` (last saved: 2026-06-20, commit abc1234)\nFiles to update: decisions.md, quirks.md\nProceed? [y\u002Fn]\n```\n\n## Running the Scaffold Script\n\nThe script lives next to this skill file. Find it relative to where this SKILL.md was loaded from:\n\n```bash\nbash path\u002Fto\u002Fskill\u002Freferences\u002Fscaffold.sh \"WanConfig\"\n```\n\nThe script outputs one line:\n- `created:\u002Fabs\u002Fpath\u002Fto\u002Fspecs\u002Fwan-config date:2026-06-24 commit:PR #pending` — new spec, `index.md` written\n- `exists:\u002Fabs\u002Fpath\u002Fto\u002Fspecs\u002Fwan-config date:2026-06-24 commit:PR #pending` — spec already exists\n\nParse `date` and the **absolute spec path** from the output — use the absolute path when writing content files and launching the preview server.\n\nThe `**Commit:**` stamp names the PR that carries the change (`PR #153`), never\na commit hash: a hash written on a feature branch is orphaned by the\nsquash-merge that lands it, so it resolves only in clones that had the branch.\nThe scaffold writes `PR #pending`; replace it with the number once the PR is\nopen, and use the same form in changelog lines.\n\n## After Scaffold: Writing Content Files\n\nRead [references\u002Ftemplates.md](references\u002Ftemplates.md) for the structure of each file.\n\n**The layering rule.** Every concern file opens with its summary table; the\nreasoning sits underneath; prose appears only where it earns its keep — the\nreasoning a future reader must be able to follow. Fill the table layer first:\nit is what a scanning human, `preflight`'s drift check, and an agent loading\nthe spec all read, so write each row as a claim someone could check.\n\n**The two-homes rule.** A type in `api.md` says what each field *means* —\ntrailing `\u002F\u002F` per field, JSDoc only when a line won't do. `fields.md` says\nwhat *happens to it* — mapping and transformation only. One fact never lives\nin both places: a fact with two homes goes missing from the one being read.\nThe same split holds one level up: `prd.md` says *why the feature exists and\nfor whom*; `decisions.md` says *how it was chosen*. A decision never restates\nthe problem, and the PRD never records an alternative.\n\n**`prd.md` is the requirements file, and the one file written before the\ndesign.** `discovery` authors it from its requirements card and writes it\nhere at sign-off; run standalone (\"save this PRD\", \"write up the\nrequirements\") you write it directly from what the user gives you. Six fixed\nsections — see the template. A section nobody has answered becomes an open\nquestion; never invent users or metrics to complete the table.\n\n**Quirk headings are `## Q\u003Cn> — Title`.** The `Q\u003Cn>` anchors are a citation\ncontract (`durable-citations.test.mjs` resolves them), so numbers are unique,\nascending, and never renumbered.\n\n- Write only files that have real content\n- After writing, update the `## Contents` table in `index.md` — one row per\n  file created, the `Answers` cell saying what a reader comes to it for\n- Replace the HTML comment the scaffold left below the title with a one-line\n  `> …` note saying what the spec is for. That note is what `spec-browser`'s\n  catalog shows for the spec; leave it and the spec is listed with nothing to\n  identify it\n\n**Cite committed paths only.** The spec is durable; the design and plan it came\nfrom live in `.condux\u002F`, which is gitignored — a citation into it is dead on\nevery machine but this one. When the changelog or a content file needs to point\nat a design or a verification report, copy that file into the spec directory\nfirst (`design.md`, `verification.md`) and cite that path. If the artifact is\nalready gone, say so and name what survives — a PR, a commit — instead of a\npath that resolves nowhere.\n\n## Updating an Existing Spec\n\nWhen scaffold output is `exists:`:\n1. Read `index.md` to see current state and which files exist\n2. Update only files with new or changed content\n3. Bump `Last updated` in `index.md` from scaffold output; set `Commit` to the PR carrying this change (`PR #pending` until it is open)\n4. Append to the `## Changelog` in `index.md`\n\n## Live HTML Preview & Review (Optional)\n\nSpec preview is served by the **plan-review** skill's annotate server in\ndirectory mode — the same annotation UI used for plan review, so the user can\nnot only read the spec live but select text, attach notes per file, and submit\na decision.\n\nAfter writing spec files, ask:\n\n```\nSpec saved. Want a live HTML preview? It renders all spec files, updates as you edit, and lets you annotate. [y\u002Fn]\n```\n\nIf yes, locate the plan-review server script:\n\n```bash\nfind ~\u002F.claude ~\u002F.codex ~\u002F.agents -name \"annotate-server.js\" -path \"*plan-review*\" 2>\u002Fdev\u002Fnull | head -1\n```\n\nRun it in the background, pointing at the spec folder:\n\n```bash\nnode \u002Fpath\u002Fto\u002Fplan-review\u002Freferences\u002Fannotate-server.js specs\u002Fwan-config\n```\n\nIt opens the browser automatically, lists every top-level `.md` in the folder\n(Contents tab), watches for file changes, and re-renders live. If the user\nsubmits a decision, it lands in `specs\u002F\u003Cslug>\u002Freview.feedback.md` with notes\ngrouped by file — read it and action it:\n\n- **Approve** — the spec is accurate; nothing to do.\n- **Request Revisions** — fix the spec files per the notes.\n\nSpec review is accept-or-fix, so the bar shows only these two verdicts (the\nplan-only \"Reject \u002F don't build it\" verdict is hidden in directory mode). If\nthe spec's whole premise is wrong, the user leaves a note saying so and stops\nthe server — treat that as a cue to discuss before rewriting, not a routine\nrevision.\n\nTell the user:\n\n```\nPreview running. Edit your spec files and the browser updates live.\nAnnotate and submit a decision, or just press Ctrl+C in the terminal when done.\n```\n\nThe server is in-memory only — no HTML files are written to disk (only the\nfeedback file, if a decision is submitted).\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---------|-----|\n| Skipping the notification\u002Fconfirmation | Always announce before writing, wait for approval |\n| Not using scaffold output for the date | Parse it from the script — don't run git separately |\n| Stamping a commit hash | The stamp is `PR #N` — a branch hash is orphaned by squash-merge; `PR #pending` until the PR is open |\n| Rewriting all files on update | Read `index.md` first, only touch files with new content |\n| Vague decisions | Each decision needs context + rationale + consequences |\n| Creating empty placeholder files | Only create a file when it has real content |\n| Forgetting to update index.md Contents | Always link to files you create |\n| Prose blob where the template has a table | Fill the table layer first; prose only for reasoning the table can't carry |\n| Bare interface with the field meanings in fields.md | Meaning goes on the type (`\u002F\u002F` per field); fields.md carries only the journey |\n","# Save Tech Spec\n\n## Overview\n\nPersists feature requirements, decisions, API contracts, implementation details, and quirks into a structured, queryable spec tree. One folder per feature, one file per concern — future sessions load only what they need. Specs are living contracts: `\u002Fpreflight`'s Drift Check compares the implementation against them at end-of-task.\n\n## Spec Folder Layout\n\nAll specs live under one `specs\u002F` tree at the **git root**, mirroring the\nrepo structure. The scaffold script detects the nearest package root (walking\nup from CWD to the git root, finding the first `package.json`, `Cargo.toml`,\n`go.mod`, or `pyproject.toml`) and uses its path *relative to the git root*\nto place the spec.\n\n```\n\u003Cgit-root>\u002Fspecs\u002F\n  {feature-slug}\u002F           # cross-cutting, or scaffolded from the repo root\n  apps\u002Fweb\u002F\n    {feature-slug}\u002F         # scaffolded while working in apps\u002Fweb\n      index.md              # purpose, TOC, last updated, PR stamp, changelog  ← scaffold creates this\n      prd.md                # Requirements: problem, users, goals\u002Fnon-goals, metrics, scope\n      decisions.md          # Design decisions with context + rationale\n      api.md                # Endpoints, types, external APIs consumed\n      fields.md             # Field mappings: BE\u002F3rd-party → UI, or forwarding chains\n      implementation.md     # Key files, patterns, how it hangs together\n      quirks.md             # Edge cases, gotchas, known issues\n```\n\nSlugs are kebab-case and acronym-aware: `WanConfig` → `wan-config`,\n`UIFormControls` → `ui-form-controls`.\n\nIn a single-package repo the package root is the git root, so specs land at\n`specs\u002F\u003Cslug>\u002F`. In a monorepo working on `apps\u002Fweb`, they land at\n`specs\u002Fapps\u002Fweb\u002F\u003Cslug>\u002F` — one browsable tree, with a natural home for\ncross-cutting features at `specs\u002F\u003Cslug>\u002F`.\n\nExisting specs co-located inside packages (`apps\u002Fweb\u002Fspecs\u002F…`) are not\nauto-migrated — `git mv` them into the root tree if you want them unified.\n\nOnly create files that have actual content. Don't create empty files.\n\n## Workflow\n\nInfer the feature name (ask if unclear) → confirm with the user before\nwriting → run the scaffold script → write or update the concern files and\n`index.md` → offer the live HTML preview. Each step is specified in the\nsections below.\n\n**When `discovery` calls this at sign-off**, the design document already\nexists and has since the design's first section — discovery creates it at §1\nand appends to it as each section is agreed. So the input here is a finished\nfile on disk, not a summary reconstructed from the conversation: read\n`.condux\u002Fdesigns\u002FYYYY-MM-DD-\u003Cfeature>.md` and map its sections into the\nconcern files. Its `§0 · requirements` part uses `prd.md`'s six headings\nverbatim, so that mapping is a copy, heading for heading. Discovery's own\npreview server is already running against that file, so the live-preview\noffer below applies to the *spec directory* only — never start a second\nserver for the design.\n\n## Required Notifications\n\nAlways announce and confirm before writing or editing. Never silently modify files.\n\nNew spec:\n```\nAbout to save tech spec for `wan-config` → specs\u002Fwan-config\u002F\nProceed? [y\u002Fn]\n```\n\nUpdating existing spec:\n```\nUpdating spec for `wan-config` (last saved: 2026-06-20, commit abc1234)\nFiles to update: decisions.md, quirks.md\nProceed? [y\u002Fn]\n```\n\n## Running the Scaffold Script\n\nThe script lives next to this skill file. Find it relative to where this SKILL.md was loaded from:\n\n```bash\nbash path\u002Fto\u002Fskill\u002Freferences\u002Fscaffold.sh \"WanConfig\"\n```\n\nThe script outputs one line:\n- `created:\u002Fabs\u002Fpath\u002Fto\u002Fspecs\u002Fwan-config date:2026-06-24 commit:PR #pending` — new spec, `index.md` written\n- `exists:\u002Fabs\u002Fpath\u002Fto\u002Fspecs\u002Fwan-config date:2026-06-24 commit:PR #pending` — spec already exists\n\nParse `date` and the **absolute spec path** from the output — use the absolute path when writing content files and launching the preview server.\n\nThe `**Commit:**` stamp names the PR that carries the change (`PR #153`), never\na commit hash: a hash written on a feature branch is orphaned by the\nsquash-merge that lands it, so it resolves only in clones that had the branch.\nThe scaffold writes `PR #pending`; replace it with the number once the PR is\nopen, and use the same form in changelog lines.\n\n## After Scaffold: Writing Content Files\n\nRead [references\u002Ftemplates.md](references\u002Ftemplates.md) for the structure of each file.\n\n**The layering rule.** Every concern file opens with its summary table; the\nreasoning sits underneath; prose appears only where it earns its keep — the\nreasoning a future reader must be able to follow. Fill the table layer first:\nit is what a scanning human, `preflight`'s drift check, and an agent loading\nthe spec all read, so write each row as a claim someone could check.\n\n**The two-homes rule.** A type in `api.md` says what each field *means* —\ntrailing `\u002F\u002F` per field, JSDoc only when a line won't do. `fields.md` says\nwhat *happens to it* — mapping and transformation only. One fact never lives\nin both places: a fact with two homes goes missing from the one being read.\nThe same split holds one level up: `prd.md` says *why the feature exists and\nfor whom*; `decisions.md` says *how it was chosen*. A decision never restates\nthe problem, and the PRD never records an alternative.\n\n**`prd.md` is the requirements file, and the one file written before the\ndesign.** `discovery` authors it from its requirements card and writes it\nhere at sign-off; run standalone (\"save this PRD\", \"write up the\nrequirements\") you write it directly from what the user gives you. Six fixed\nsections — see the template. A section nobody has answered becomes an open\nquestion; never invent users or metrics to complete the table.\n\n**Quirk headings are `## Q\u003Cn> — Title`.** The `Q\u003Cn>` anchors are a citation\ncontract (`durable-citations.test.mjs` resolves them), so numbers are unique,\nascending, and never renumbered.\n\n- Write only files that have real content\n- After writing, update the `## Contents` table in `index.md` — one row per\n  file created, the `Answers` cell saying what a reader comes to it for\n- Replace the HTML comment the scaffold left below the title with a one-line\n  `> …` note saying what the spec is for. That note is what `spec-browser`'s\n  catalog shows for the spec; leave it and the spec is listed with nothing to\n  identify it\n\n**Cite committed paths only.** The spec is durable; the design and plan it came\nfrom live in `.condux\u002F`, which is gitignored — a citation into it is dead on\nevery machine but this one. When the changelog or a content file needs to point\nat a design or a verification report, copy that file into the spec directory\nfirst (`design.md`, `verification.md`) and cite that path. If the artifact is\nalready gone, say so and name what survives — a PR, a commit — instead of a\npath that resolves nowhere.\n\n## Updating an Existing Spec\n\nWhen scaffold output is `exists:`:\n1. Read `index.md` to see current state and which files exist\n2. Update only files with new or changed content\n3. Bump `Last updated` in `index.md` from scaffold output; set `Commit` to the PR carrying this change (`PR #pending` until it is open)\n4. Append to the `## Changelog` in `index.md`\n\n## Live HTML Preview & Review (Optional)\n\nSpec preview is served by the **plan-review** skill's annotate server in\ndirectory mode — the same annotation UI used for plan review, so the user can\nnot only read the spec live but select text, attach notes per file, and submit\na decision.\n\nAfter writing spec files, ask:\n\n```\nSpec saved. Want a live HTML preview? It renders all spec files, updates as you edit, and lets you annotate. [y\u002Fn]\n```\n\nIf yes, locate the plan-review server script:\n\n```bash\nfind ~\u002F.claude ~\u002F.codex ~\u002F.agents -name \"annotate-server.js\" -path \"*plan-review*\" 2>\u002Fdev\u002Fnull | head -1\n```\n\nRun it in the background, pointing at the spec folder:\n\n```bash\nnode \u002Fpath\u002Fto\u002Fplan-review\u002Freferences\u002Fannotate-server.js specs\u002Fwan-config\n```\n\nIt opens the browser automatically, lists every top-level `.md` in the folder\n(Contents tab), watches for file changes, and re-renders live. If the user\nsubmits a decision, it lands in `specs\u002F\u003Cslug>\u002Freview.feedback.md` with notes\ngrouped by file — read it and action it:\n\n- **Approve** — the spec is accurate; nothing to do.\n- **Request Revisions** — fix the spec files per the notes.\n\nSpec review is accept-or-fix, so the bar shows only these two verdicts (the\nplan-only \"Reject \u002F don't build it\" verdict is hidden in directory mode). If\nthe spec's whole premise is wrong, the user leaves a note saying so and stops\nthe server — treat that as a cue to discuss before rewriting, not a routine\nrevision.\n\nTell the user:\n\n```\nPreview running. Edit your spec files and the browser updates live.\nAnnotate and submit a decision, or just press Ctrl+C in the terminal when done.\n```\n\nThe server is in-memory only — no HTML files are written to disk (only the\nfeedback file, if a decision is submitted).\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---------|-----|\n| Skipping the notification\u002Fconfirmation | Always announce before writing, wait for approval |\n| Not using scaffold output for the date | Parse it from the script — don't run git separately |\n| Stamping a commit hash | The stamp is `PR #N` — a branch hash is orphaned by squash-merge; `PR #pending` until the PR is open |\n| Rewriting all files on update | Read `index.md` first, only touch files with new content |\n| Vague decisions | Each decision needs context + rationale + consequences |\n| Creating empty placeholder files | Only create a file when it has real content |\n| Forgetting to update index.md Contents | Always link to files you create |\n| Prose blob where the template has a table | Fill the table layer first; prose only for reasoning the table can't carry |\n| Bare interface with the field meanings in fields.md | Meaning goes on the type (`\u002F\u002F` per field); fields.md carries only the journey |\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","5277649b071c1c0cdf4f15eee861b1608fc1bbcb","packages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec",0,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit","https:\u002F\u002Fgithub.com\u002Fjabworks","2026-11-03 15:03:51",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jabworks\u002Fagentic-toolkit --skill technical-spec",{"tool":38,"command":39},"bunx","bunx skills add jabworks\u002Fagentic-toolkit --skill technical-spec",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jabworks\u002Fagentic-toolkit --skill technical-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec\u002FSKILL.md",[45,51,57],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"evals\u002Ftrigger_eval.json","REFERENCE","参考文档",3264,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec\u002Fevals\u002Ftrigger_eval.json",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fscaffold.sh","SCRIPT","脚本",4162,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec\u002Freferences\u002Fscaffold.sh",{"path":58,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftemplates.md",9478,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Ftechnical-spec\u002Freferences\u002Ftemplates.md",[62,68,74,81,88,95],{"skillNo":63,"name":64,"nameZh":6,"description":6,"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},"01M7540BPNTFZH7V41P5E2S692","orphan","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Forphan\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"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},"01M7540AG2KFTQ8DJMNV6806MV","no-blurb","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Fno-blurb\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},"01M75404N306PY1JFPQ0GGNTYB","workflow","Routes any dev task into the right execution tier (Small\u002FMedium\u002FLarge) and carries condux's operating rules — proportional effort, lazy skill loading, soft gates, implement-yourself-by-default.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\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},"01M753ZZ6TTA06GRJAG679BQ2H","usage-trace","Checks and manages durable, local usage capture — ingest, health status, and the opt-in limit snapshot — for Claude Code and Codex. Capture itself runs automatically at session start.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fusage-trace\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M753ZSKJSF8WFS7AXR2N65SE","toolkit-skill-standards","Use when writing or reviewing a SKILL.md for jabworks\u002Fagentic-toolkit — frontmatter budgets, the trigger contract (\"Use when…\" description or when_to_use field), progressive disclosure into references\u002F, and keeping a new description out of existing skills' trigger space. Triggers include \"review this skill description\", \"write the frontmatter\", \"does this collide with an existing skill\", \"where should this content live\". Not for scaffold\u002Fsync mechanics; use toolkit-foundry.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-skill-standards\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M753ZKX3KTVYWX15A9A0WZN0","toolkit-research-frontier","Use when planning improvement work on jabworks\u002Fagentic-toolkit itself — open problems (trigger-collision automation, YAML-strict frontmatter checks, docs-catalog enforcement), existing assets, the next three concrete steps, and the four-front library-health campaign with commands and success criteria. Triggers include \"let's improve our toolkit\", \"let's improve this repo\", \"what should we improve next\", \"toolkit roadmap\", \"open problems\", \"run the health campaign\".","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-research-frontier\u002FSKILL.md",[],[]]