[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77H781ES9BQMKWK3JY7GR7B":3,"skill-same:01M77H781ES9BQMKWK3JY7GR7B":51},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M77H781ES9BQMKWK3JY7GR7B","spine-fanout",null,"Apply the two new-work defaults — ship the minimal WORKING end-to-end spine first (or file the spine as its own issue), then fan out the 3..50+ follow-on QA\u002Fdogfood\u002Fproductization backlog at creation time via `fak issue fanout`. Use when starting any new feature\u002Fleaf\u002Fverb\u002Fdemo, when a spine just shipped, when asked to \"fan out\", \"file follow-ons\", \"create the e2e spin\", or at the end of a super-loop turn that landed new work.","anthony-chaudhary\u002Ffak","anthony-chaudhary","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F18080164?v=4","01M77GSKCAEKV3JS07J40B94DY","Anthony Chaudhary","01M77GSKD26Z7F4FQQD4VA30VX",48,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspine-fanout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spine-fanout\ndescription: Apply the two new-work defaults — ship the minimal WORKING end-to-end spine first (or file the spine as its own issue), then fan out the 3..50+ follow-on QA\u002Fdogfood\u002Fproductization backlog at creation time via `fak issue fanout`. Use when starting any new feature\u002Fleaf\u002Fverb\u002Fdemo, when a spine just shipped, when asked to \"fan out\", \"file follow-ons\", \"create the e2e spin\", or at the end of a super-loop turn that landed new work.\nallowed-tools: Read, Bash, Write\nmetadata:\n  generated-by: fak project-assets sync\n  canonical: ..\u002F..\u002F..\u002F.claude\u002Fskills\u002Fspine-fanout\u002FSKILL.md\n---\n\n# spine-fanout — spine first, then fan out\n\nDoctrine: [`docs\u002Fspine-first-defaults.md`](..\u002F..\u002F..\u002Fdocs\u002Fspine-first-defaults.md).\nTwo defaults for any new unit of work; this skill is the mechanical checklist.\n\n## Step 1 — classify the moment\n\n- **Starting new work** → go to Step 2 (spine gate).\n- **A spine just shipped** (commit\u002Fdemo\u002Ftest exists) → go to Step 3 (fan out).\n\n## Step 2 — the spine gate\n\nShip the smallest runnable end-to-end path through the REAL seam this session.\nBefore broad proof or optimization, write the outcome in one sentence, connect one\nrepresentative applied path, and capture its command\u002Ftest result. Then expand the\nfailure\u002Fedge\u002Fplatform\u002Fconcurrency\u002Fsoak envelope; optimize only after the working\npath provides the real baseline. Do not count a component benchmark, comparison\nmatrix, or disconnected mock as the spine.\n\nBefore arming the issue, write both contract sections:\n\n- `Core through-line`: shortest change -> real seam -> observable outcome -> witness path.\n- `Gold-plating boundary`: tempting breadth, polish, abstraction, or optimization that the\n  named outcome and witness still work without; route valuable items to follow-ons.\n\nCounterfactual: if omitting an item still leaves the named user able to traverse the spine\nand the witness able to prove the outcome, it is gold plating for this issue. Required\nsafety, compatibility, and fail-closed behavior stay core.\n\n| Work shape | Minimal spine bar |\n|---|---|\n| user-facing | LCD demo (`docs\u002Frun-the-demos.md`): one command, deterministic, no key\u002Fnetwork\u002FGPU, `-selfcheck` |\n| library leaf \u002F verb | a test driving the real object + one captured live run (`--json`\u002F`--dry-run` ok) |\n| process\u002Fdoctrine | the enforcing machinery (gate\u002Fskill\u002Fverb), not a memo |\n\n**Not achievable this session with high confidence?** File the spine itself as\nthe first issue — `gen\u002Fnow`, milestoned at creation, missing witness named in\nthe body. Never silently defer the spine. Then continue to Step 3 with\n`--spine` set to that issue ref only if a partial witness exists; otherwise\nstop after filing (the fan-out waits for a spine).\n\n## Step 3 — prove outward from the working spine\n\nKeep the captured spine command\u002Ftest green while adding the issue's required\nproof envelope. Order the queue: correctness and fail-closed paths, edge cases,\nplatform\u002Fconcurrency\u002Fsoak evidence, then end-to-end optimization against the real\nbaseline. If new evidence breaks the spine, restore the applied path before\ncontinuing the matrix.\n\n## Step 4 — generate the fan-out (3..50+)\n\n```bash\nfak issue fanout --title \"\u003Cfeature>\" --leaf \u003Cleaf> \\\n    --spine \"\u003Ccommit sha | demo cmd | doc path>\" [--parent '#\u003Cepic>'] --json > \u002Ftmp\u002Ffanout.json\nfak issue cohort --from-plan \u002Ftmp\u002Ffanout.json   # optional: leased, concurrency-safe waves\n```\n\nThe verb refuses to run without `--spine` — that refusal is Step 2 talking.\nAreas: qa, dogfood, product, observability, integration, docs, release\n(`--areas` filters; `--max` caps, floor 3).\n\n## Step 5 — file the issues\n\nFor each candidate (or each wave): create the GitHub issue with the candidate's\ntitle and contract sections as the body, **milestone + labels at creation**\n(`fanout`, the area label, priority from the candidate, generation label).\nDedupe first: search existing issues for the `fanout-\u003Cleaf>-` marker key and\ncomment instead of re-filing. On this host run `gh` through PowerShell, never\nthe Bash tool.\n\n## Step 6 — close the loop\n\n- Link the fan-out issues from the epic\u002Fparent; note the spine SHA there.\n- If the session ends with candidates unfiled, commit the plan JSON output into\n  the epic\u002Fissue body or a `docs\u002Fnotes\u002F` entry (with the INDEX.md line) so the\n  fan-out is recoverable — a plan that lives only in a transcript is lost.\n","# spine-fanout — spine first, then fan out\n\nDoctrine: [`docs\u002Fspine-first-defaults.md`](..\u002F..\u002F..\u002Fdocs\u002Fspine-first-defaults.md).\nTwo defaults for any new unit of work; this skill is the mechanical checklist.\n\n## Step 1 — classify the moment\n\n- **Starting new work** → go to Step 2 (spine gate).\n- **A spine just shipped** (commit\u002Fdemo\u002Ftest exists) → go to Step 3 (fan out).\n\n## Step 2 — the spine gate\n\nShip the smallest runnable end-to-end path through the REAL seam this session.\nBefore broad proof or optimization, write the outcome in one sentence, connect one\nrepresentative applied path, and capture its command\u002Ftest result. Then expand the\nfailure\u002Fedge\u002Fplatform\u002Fconcurrency\u002Fsoak envelope; optimize only after the working\npath provides the real baseline. Do not count a component benchmark, comparison\nmatrix, or disconnected mock as the spine.\n\nBefore arming the issue, write both contract sections:\n\n- `Core through-line`: shortest change -> real seam -> observable outcome -> witness path.\n- `Gold-plating boundary`: tempting breadth, polish, abstraction, or optimization that the\n  named outcome and witness still work without; route valuable items to follow-ons.\n\nCounterfactual: if omitting an item still leaves the named user able to traverse the spine\nand the witness able to prove the outcome, it is gold plating for this issue. Required\nsafety, compatibility, and fail-closed behavior stay core.\n\n| Work shape | Minimal spine bar |\n|---|---|\n| user-facing | LCD demo (`docs\u002Frun-the-demos.md`): one command, deterministic, no key\u002Fnetwork\u002FGPU, `-selfcheck` |\n| library leaf \u002F verb | a test driving the real object + one captured live run (`--json`\u002F`--dry-run` ok) |\n| process\u002Fdoctrine | the enforcing machinery (gate\u002Fskill\u002Fverb), not a memo |\n\n**Not achievable this session with high confidence?** File the spine itself as\nthe first issue — `gen\u002Fnow`, milestoned at creation, missing witness named in\nthe body. Never silently defer the spine. Then continue to Step 3 with\n`--spine` set to that issue ref only if a partial witness exists; otherwise\nstop after filing (the fan-out waits for a spine).\n\n## Step 3 — prove outward from the working spine\n\nKeep the captured spine command\u002Ftest green while adding the issue's required\nproof envelope. Order the queue: correctness and fail-closed paths, edge cases,\nplatform\u002Fconcurrency\u002Fsoak evidence, then end-to-end optimization against the real\nbaseline. If new evidence breaks the spine, restore the applied path before\ncontinuing the matrix.\n\n## Step 4 — generate the fan-out (3..50+)\n\n```bash\nfak issue fanout --title \"\u003Cfeature>\" --leaf \u003Cleaf> \\\n    --spine \"\u003Ccommit sha | demo cmd | doc path>\" [--parent '#\u003Cepic>'] --json > \u002Ftmp\u002Ffanout.json\nfak issue cohort --from-plan \u002Ftmp\u002Ffanout.json   # optional: leased, concurrency-safe waves\n```\n\nThe verb refuses to run without `--spine` — that refusal is Step 2 talking.\nAreas: qa, dogfood, product, observability, integration, docs, release\n(`--areas` filters; `--max` caps, floor 3).\n\n## Step 5 — file the issues\n\nFor each candidate (or each wave): create the GitHub issue with the candidate's\ntitle and contract sections as the body, **milestone + labels at creation**\n(`fanout`, the area label, priority from the candidate, generation label).\nDedupe first: search existing issues for the `fanout-\u003Cleaf>-` marker key and\ncomment instead of re-filing. On this host run `gh` through PowerShell, never\nthe Bash tool.\n\n## Step 6 — close the loop\n\n- Link the fan-out issues from the epic\u002Fparent; note the spine SHA there.\n- If the session ends with candidates unfiled, commit the plan JSON output into\n  the epic\u002Fissue body or a `docs\u002Fnotes\u002F` entry (with the INDEX.md line) so the\n  fan-out is recoverable — a plan that lives only in a transcript is lost.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27},{"canonical":25,"generated-by":26},"..\u002F..\u002F..\u002F.claude\u002Fskills\u002Fspine-fanout\u002FSKILL.md","fak project-assets sync","Read, Bash, Write","main","f565b7b7db63e79649f3a02c08108132a86c5d05",".agents\u002Fskills\u002Fspine-fanout",16,"https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak","https:\u002F\u002Fanthony-chaudhary.github.io\u002Ffak\u002Fshowcase.html","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary","https:\u002F\u002Flinkedin.com\u002Fin\u002Fanthonychaudhary","2026-11-15 03:06:00",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add anthony-chaudhary\u002Ffak --skill spine-fanout",{"tool":43,"command":44},"bunx","bunx skills add anthony-chaudhary\u002Ffak --skill spine-fanout",{"tool":46,"command":47},"pnpm","pnpm dlx skills add anthony-chaudhary\u002Ffak --skill spine-fanout","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspine-fanout\u002FSKILL.md",true,[],[52,59,68,75,82,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M78V4059KRP2T88YR6Z05MJQ","serve-receipt","On-demand research protocol + deterministic receipt for serving a Hugging Face model on a concrete GPU target — fan out research lanes (model facts\u002Ffiles, engine support matrix, serving recipes, KV\u002Fstate memory math), compute the tiered feasibility verdict with `fak serve-receipt` (never narrated math), and emit a witnessed launch receipt. Use when asked for an \"initial config\", \"serving receipt\", or \"how do I serve \u003Cmodel> on \u003CGPUs>\".","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fserve-receipt\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M77HRGKQV2CJ2K6ZFN4YQ32K","caveman","Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes \u002Fcaveman. Also auto-triggers when token efficiency is requested.","MIT","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fsyspromptmmu\u002Fthird_party\u002Fcaveman\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fsyspromptmmu\u002Fthird_party\u002Fcaveman\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},"01M77HRAY3Y3BE7APN5PVJF7NV","quality-report","Score the repo quality and emit a report card.","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplans\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\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},"01M77HR9807KHAX13DG9PW2K2Q","ctx-overlay","Compact the context window and prune the memory store when a session grows too long.","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplans\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[],{"skillNo":83,"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":84,"categories":85,"keywords":86,"publishedAt":19},"01M77HR7XQ9X8F2CY9Z4F2ZEZ3","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fquality-report\u002FSKILL.md",[],[],{"skillNo":88,"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":89,"categories":90,"keywords":91,"publishedAt":19},"01M77HR5BVKCTR1WNJGRBSDNX7","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Ffak\u002Fblob\u002Fmain\u002Finternal\u002Fctxplanlint\u002Ftestdata\u002Frepo\u002F.claude\u002Fskills\u002Fctx-overlay\u002FSKILL.md",[],[]]