[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71K7JZ57GFDT6PA0H1Z1X84":3,"skill-same:01M71K7JZ57GFDT6PA0H1Z1X84":93},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M71K7JZ57GFDT6PA0H1Z1X84","spawn-agent",null,"Prepare a composed Agent-tool invocation via kei-spawn. Click-only wizard — pick role, describe task, set scope. Emits ready-to-paste prompt + subagent_type + isolation + DNA.","KeiSeiLab\u002FKeiSeiKit","KeiSeiLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F283315582?v=4","01M71K2EW81JRFHSGF0T844B32","KeiSei Lab","01M71K2EWXTB52KWC65E55S6M2",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"spawn","spawn agent","prepare","role","describe","paste","via","DNA","type","task","subagent","prompt","only","wizard","pick","tool","scope","click","ready","SET","2026-11-10 10:12:30",false,"---\nname: spawn-agent\ndescription: Prepare a composed Agent-tool invocation via kei-spawn. Click-only wizard — pick role, describe task, set scope. Emits ready-to-paste prompt + subagent_type + isolation + DNA.\nargument-hint: (no arguments)\n---\n\n# \u002Fspawn-agent — Click-only Agent-tool composer (index)\n\n## When to use\n\n- Composing a ready-to-paste `Agent`-tool invocation via the `kei-spawn` CLI without writing it by hand.\n- Selecting agent role, task description, and scope files through a click-only wizard.\n- Preparing a sub-agent spawn that complies with RULE 0.12 (branch + artefact bundle).\n\nYou convert a user's intent into a ready-to-paste `Agent`-tool invocation\nvia the `kei-spawn` CLI. Every decision is a click; only the task description\n(Phase 2) is typed. No git, no side-effects on disk beyond the task.toml the\nCLI consumes.\n\nThis `SKILL.md` is the INDEX. Each phase lives in its own file and is\nexecuted in order. Never skip a phase. Never re-order phases.\n\n---\n\n## Pipeline overview\n\n| Phase | File | Purpose | AskUserQuestion |\n|---|---|---|---|\n| 1 | [phase-1-role.md](phase-1-role.md) | Pick agent role (capability tier) | 1× AskUserQuestion |\n| 2 | [phase-2-task.md](phase-2-task.md) | Free-text task description (ONE paragraph) | 0× (only free-text in the skill) |\n| 3 | [phase-3-scope.md](phase-3-scope.md) | Files whitelist glob patterns | 2× AskUserQuestion |\n| 4 | [phase-4-emit.md](phase-4-emit.md) | Write task.toml, run kei-spawn, emit Agent-tool invocation | 1× AskUserQuestion (confirm-emit) |\n\n**Minimum AskUserQuestion count: 4** — pure-click contract.\n\n---\n\n## Variables the pipeline produces\n\n| Name | Set in | Meaning |\n|---|---|---|\n| `ROLE` | Phase 1 | One of `read-only` \u002F `explorer` \u002F `edit-local` \u002F `edit-shared` |\n| `TASK` | Phase 2 | Free-text task description (1-3 sentences) |\n| `WHITELIST` | Phase 3 | List of glob patterns (relative to repo root) |\n| `DENYLIST` | Phase 3 | Optional list of glob patterns (auto-derived from role if skipped) |\n| `TASK_TOML` | Phase 4 | Path `tasks\u002F\u003Cuuid>.toml` relative to current repo |\n| `AGENT_ID` | Phase 4 | UUID returned by `kei-spawn spawn` |\n| `DNA` | Phase 4 | SHA-256 fingerprint returned by `kei-spawn spawn` |\n| `SUBAGENT_TYPE` | Phase 4 | Resolved by kei-spawn from ROLE (e.g. `code-implementer` \u002F `researcher`) |\n| `ISOLATION` | Phase 4 | Resolved by kei-spawn from ROLE (`worktree` or `shared`) |\n| `WORKTREE_PATH` | Phase 4 | Returned when isolation=worktree |\n\n---\n\n## Role → defaults map (LOAD-BEARING)\n\n| ROLE | subagent_type | isolation | Bash? | Writes? |\n|---|---|---|---|---|\n| read-only | researcher | shared | no | no |\n| explorer | researcher | shared | read-only bash | no |\n| edit-local | code-implementer | worktree | cargo\u002Ftest only | yes (whitelist) |\n| edit-shared | code-implementer | worktree | cargo\u002Ftest only | yes (whitelist) |\n\n`kei-spawn` owns the resolution — this table is reference only. The skill\npasses the ROLE string verbatim; the CLI returns the resolved values.\n\n---\n\n## Final report (emit after Phase 4)\n\n```\n=== \u002FSPAWN-AGENT REPORT ===\nRole:            \u003CROLE>\nTask (first 80): \u003Cfirst 80 chars of TASK>...\nWhitelist:       \u003CN globs> — \u003Cfirst 3 shown>\nDenylist:        \u003Cauto \u002F explicit — N globs>\nAgent ID:        \u003CUUID>\nDNA:             \u003Csha256:first-12>...\nsubagent_type:   \u003CSUBAGENT_TYPE>\nisolation:       \u003CISOLATION>\nWorktree:        \u003CWORKTREE_PATH or n\u002Fa>\n\nReady-to-paste Agent-tool invocation:\n\n  \u003CJSON block — see phase-4-emit.md §4 for exact shape>\n\nNext step on return:\n  kei-spawn verify \u003CAGENT_ID> \u003CWORKTREE_PATH>\n```\n\n---\n\n## Runtime binary resolution\n\n`kei-spawn` must be on `PATH` OR reachable via `$KEI_RUNTIME_BIN_DIR`. The\nphases call `kei-spawn \u003Ccmd>` directly; if the shell returns `command not\nfound`, fall back to `\"$KEI_RUNTIME_BIN_DIR\u002Fkei-spawn\" \u003Ccmd>`. If both fail,\nSTOP and surface the error to the user with three constructive paths:\n\n- (A) Build `kei-spawn` from the kit source (`cd _primitives\u002F_rust\u002Fkei-spawn && cargo build --release`).\n- (B) Export `KEI_RUNTIME_BIN_DIR` to point at an existing build.\n- (C) Install via `install.sh` which wires both.\n\nNever silently substitute a mock.\n\n---\n\n## Rules (enforced at every phase)\n\n- **Pure-click contract.** Only `TASK` (Phase 2) is typed. Every other\n  decision is an `AskUserQuestion`. Count them in the final report.\n- **NO DOWNGRADE (RULE -1).** Any phase that fails returns 2-3 constructive\n  paths, never \"can't be done\".\n- **NO HALLUCINATION (RULE 0.4).** Never fabricate a DNA or agent_id — they\n  come from `kei-spawn spawn --format=json` verbatim. Never emit an Agent\n  invocation without a successful spawn call first.\n- **Plan Mode First (RULE 0.5).** This skill IS the plan; each phase file\n  has its own verify-criterion. No `kei-spawn spawn` call before Phase 4's\n  confirm click.\n- **Orchestrator branch first (RULE 0.13).** The skill NEVER invokes git.\n  The emitted prompt MUST contain the phrase \"MUST NOT invoke git\" so the\n  spawned agent respects the rule. Phase 4 inserts this automatically.\n- **Constructor Pattern (RULE ZERO).** One file per phase. This SKILL.md\n  stays \u003C200 LOC; each phase file stays \u003C200 LOC.\n- **Surgical Changes.** The skill only writes `tasks\u002F\u003Cuuid>.toml`. It does\n  not modify project source, does not commit, does not push.\n\n---\n\n## References\n\n- [phase-1-role.md](phase-1-role.md) · [phase-2-task.md](phase-2-task.md) · [phase-3-scope.md](phase-3-scope.md) · [phase-4-emit.md](phase-4-emit.md)\n- `_primitives\u002F_rust\u002Fkei-spawn\u002F` — CLI source (task.toml schema + spawn\u002Fverify commands)\n- `skills\u002Fnew-agent\u002FSKILL.md` — sister skill: generates agent *manifests*; this skill spawns *instances* of existing agents\n- `skills\u002Fhooks-control\u002FSKILL.md` — reference click-only pattern\n- RULE 0.12 (agent-git-model) — ledger row auto-written by `kei-spawn spawn`\n- RULE 0.13 (orchestrator-branch-first) — ban-phrase injected by Phase 4\n","# \u002Fspawn-agent — Click-only Agent-tool composer (index)\n\n## When to use\n\n- Composing a ready-to-paste `Agent`-tool invocation via the `kei-spawn` CLI without writing it by hand.\n- Selecting agent role, task description, and scope files through a click-only wizard.\n- Preparing a sub-agent spawn that complies with RULE 0.12 (branch + artefact bundle).\n\nYou convert a user's intent into a ready-to-paste `Agent`-tool invocation\nvia the `kei-spawn` CLI. Every decision is a click; only the task description\n(Phase 2) is typed. No git, no side-effects on disk beyond the task.toml the\nCLI consumes.\n\nThis `SKILL.md` is the INDEX. Each phase lives in its own file and is\nexecuted in order. Never skip a phase. Never re-order phases.\n\n---\n\n## Pipeline overview\n\n| Phase | File | Purpose | AskUserQuestion |\n|---|---|---|---|\n| 1 | [phase-1-role.md](phase-1-role.md) | Pick agent role (capability tier) | 1× AskUserQuestion |\n| 2 | [phase-2-task.md](phase-2-task.md) | Free-text task description (ONE paragraph) | 0× (only free-text in the skill) |\n| 3 | [phase-3-scope.md](phase-3-scope.md) | Files whitelist glob patterns | 2× AskUserQuestion |\n| 4 | [phase-4-emit.md](phase-4-emit.md) | Write task.toml, run kei-spawn, emit Agent-tool invocation | 1× AskUserQuestion (confirm-emit) |\n\n**Minimum AskUserQuestion count: 4** — pure-click contract.\n\n---\n\n## Variables the pipeline produces\n\n| Name | Set in | Meaning |\n|---|---|---|\n| `ROLE` | Phase 1 | One of `read-only` \u002F `explorer` \u002F `edit-local` \u002F `edit-shared` |\n| `TASK` | Phase 2 | Free-text task description (1-3 sentences) |\n| `WHITELIST` | Phase 3 | List of glob patterns (relative to repo root) |\n| `DENYLIST` | Phase 3 | Optional list of glob patterns (auto-derived from role if skipped) |\n| `TASK_TOML` | Phase 4 | Path `tasks\u002F\u003Cuuid>.toml` relative to current repo |\n| `AGENT_ID` | Phase 4 | UUID returned by `kei-spawn spawn` |\n| `DNA` | Phase 4 | SHA-256 fingerprint returned by `kei-spawn spawn` |\n| `SUBAGENT_TYPE` | Phase 4 | Resolved by kei-spawn from ROLE (e.g. `code-implementer` \u002F `researcher`) |\n| `ISOLATION` | Phase 4 | Resolved by kei-spawn from ROLE (`worktree` or `shared`) |\n| `WORKTREE_PATH` | Phase 4 | Returned when isolation=worktree |\n\n---\n\n## Role → defaults map (LOAD-BEARING)\n\n| ROLE | subagent_type | isolation | Bash? | Writes? |\n|---|---|---|---|---|\n| read-only | researcher | shared | no | no |\n| explorer | researcher | shared | read-only bash | no |\n| edit-local | code-implementer | worktree | cargo\u002Ftest only | yes (whitelist) |\n| edit-shared | code-implementer | worktree | cargo\u002Ftest only | yes (whitelist) |\n\n`kei-spawn` owns the resolution — this table is reference only. The skill\npasses the ROLE string verbatim; the CLI returns the resolved values.\n\n---\n\n## Final report (emit after Phase 4)\n\n```\n=== \u002FSPAWN-AGENT REPORT ===\nRole:            \u003CROLE>\nTask (first 80): \u003Cfirst 80 chars of TASK>...\nWhitelist:       \u003CN globs> — \u003Cfirst 3 shown>\nDenylist:        \u003Cauto \u002F explicit — N globs>\nAgent ID:        \u003CUUID>\nDNA:             \u003Csha256:first-12>...\nsubagent_type:   \u003CSUBAGENT_TYPE>\nisolation:       \u003CISOLATION>\nWorktree:        \u003CWORKTREE_PATH or n\u002Fa>\n\nReady-to-paste Agent-tool invocation:\n\n  \u003CJSON block — see phase-4-emit.md §4 for exact shape>\n\nNext step on return:\n  kei-spawn verify \u003CAGENT_ID> \u003CWORKTREE_PATH>\n```\n\n---\n\n## Runtime binary resolution\n\n`kei-spawn` must be on `PATH` OR reachable via `$KEI_RUNTIME_BIN_DIR`. The\nphases call `kei-spawn \u003Ccmd>` directly; if the shell returns `command not\nfound`, fall back to `\"$KEI_RUNTIME_BIN_DIR\u002Fkei-spawn\" \u003Ccmd>`. If both fail,\nSTOP and surface the error to the user with three constructive paths:\n\n- (A) Build `kei-spawn` from the kit source (`cd _primitives\u002F_rust\u002Fkei-spawn && cargo build --release`).\n- (B) Export `KEI_RUNTIME_BIN_DIR` to point at an existing build.\n- (C) Install via `install.sh` which wires both.\n\nNever silently substitute a mock.\n\n---\n\n## Rules (enforced at every phase)\n\n- **Pure-click contract.** Only `TASK` (Phase 2) is typed. Every other\n  decision is an `AskUserQuestion`. Count them in the final report.\n- **NO DOWNGRADE (RULE -1).** Any phase that fails returns 2-3 constructive\n  paths, never \"can't be done\".\n- **NO HALLUCINATION (RULE 0.4).** Never fabricate a DNA or agent_id — they\n  come from `kei-spawn spawn --format=json` verbatim. Never emit an Agent\n  invocation without a successful spawn call first.\n- **Plan Mode First (RULE 0.5).** This skill IS the plan; each phase file\n  has its own verify-criterion. No `kei-spawn spawn` call before Phase 4's\n  confirm click.\n- **Orchestrator branch first (RULE 0.13).** The skill NEVER invokes git.\n  The emitted prompt MUST contain the phrase \"MUST NOT invoke git\" so the\n  spawned agent respects the rule. Phase 4 inserts this automatically.\n- **Constructor Pattern (RULE ZERO).** One file per phase. This SKILL.md\n  stays \u003C200 LOC; each phase file stays \u003C200 LOC.\n- **Surgical Changes.** The skill only writes `tasks\u002F\u003Cuuid>.toml`. It does\n  not modify project source, does not commit, does not push.\n\n---\n\n## References\n\n- [phase-1-role.md](phase-1-role.md) · [phase-2-task.md](phase-2-task.md) · [phase-3-scope.md](phase-3-scope.md) · [phase-4-emit.md](phase-4-emit.md)\n- `_primitives\u002F_rust\u002Fkei-spawn\u002F` — CLI source (task.toml schema + spawn\u002Fverify commands)\n- `skills\u002Fnew-agent\u002FSKILL.md` — sister skill: generates agent *manifests*; this skill spawns *instances* of existing agents\n- `skills\u002Fhooks-control\u002FSKILL.md` — reference click-only pattern\n- RULE 0.12 (agent-git-model) — ledger row auto-written by `kei-spawn spawn`\n- RULE 0.13 (orchestrator-branch-first) — ban-phrase injected by Phase 4\n",{"name":5,"description":7,"argument-hint":49},"(no arguments)","main","32e85218a997294f68da27ff3dfd638196186ae5","skills\u002Fspawn-agent",8,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit","https:\u002F\u002Fgithub.com\u002FKeiSeiLab","2026-10-11 11:17:46",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add KeiSeiLab\u002FKeiSeiKit --skill spawn-agent",{"tool":63,"command":64},"bunx","bunx skills add KeiSeiLab\u002FKeiSeiKit --skill spawn-agent",{"tool":66,"command":67},"pnpm","pnpm dlx skills add KeiSeiLab\u002FKeiSeiKit --skill spawn-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002FSKILL.md",true,[71,77,81,85,89],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"phase-1-role.md","REFERENCE","参考文档",3039,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002Fphase-1-role.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"phase-2-task.md",3385,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002Fphase-2-task.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"phase-3-pet-overlay.md",6103,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002Fphase-3-pet-overlay.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"phase-3-scope.md",5907,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002Fphase-3-scope.md",{"path":90,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":91,"sourceHtmlUrl":92},"phase-4-emit.md",6449,"https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fspawn-agent\u002Fphase-4-emit.md",[94,122,145,180,208,233],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"publishedAt":44},"01M71K887N78V089XR5BWT0JAV","wave-audit","3-wave parallel audit — Wave 1 discovery (4 agents), Wave 2 verification (4 agents), Wave 3 cross-optimization (1 synthesizer). Each wave runs agents in parallel. Combines security review, runtime analysis, quality check, and constructor pattern into one unified workflow with evidence grading and Go\u002FNo-Go verdict.","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fwave-audit\u002FSKILL.md",[100],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"wave audit","audit","unified workflow","workflow","analysis","review","verification","security review","pattern","grading","go","security","parallel","evidence","runtime","quality check","discovery","Optimization","one","check",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":44},"01M71K85100JQS4Y10EGCTWQXW","vm-provision","End-to-end VPS provisioning — select provider → plan → provision → harden → verify (ssh-check + firewall-diff hard-gate) → handoff. 6 phases, ≥6 AskUserQuestion calls, defensive-only. Stops if either verification primitive fails.","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fvm-provision\u002FSKILL.md",[],[129,130,131,132,133,134,135,136,36,137,120,138,139,121,108,140,141,142,143,144],"vm","vm provision","firewall","diff","provider","select","end","calls","either","api","hetzner","plan","defensive","verify","intent","line",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":149,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":160,"publishedAt":44},"01M71K80ZRH2H5ES83QS97BB91","visual-explainer","Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.","MIT","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-explainer\u002FSKILL.md",[152,155],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":156,"categoryName":157,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[161,162,163,164,165,166,167,168,140,169,170,171,172,173,174,175,176,177,178,179],"visual","visual explainer","explainer","project","files","image","you","architecture","generate","present","concepts","table","as","view","for","ascii table","ascii","surf","use",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":189,"publishedAt":44},"01M71K7VSD5ZWN26QJEC4T0770","video-gen","Use when generating video from frame sequences — FFmpeg extraction, WebP\u002FAVIF conversion, sprite sheets, scroll-synced playback, video encoding\u002Ftranscoding. Covers the full pipeline from video source to web-ready frame sequence or optimized video.","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-gen\u002FSKILL.md",[186],{"categoryNo":187,"categoryName":188,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[190,191,192,42,193,194,195,196,197,198,166,199,200,201,202,203,204,205,206,207],"Video","gen","video gen","pipeline","default","generated","synced","false","when","conversion","directory","sequences","sequence","source","full","path","webp","target",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":217,"publishedAt":44},"01M71K7R88RM8ENVCRZHZSMM5T","test-matrix","Use when a project needs testing BEYOND unit tests — fuzzing, property-based, load, E2E, or mutation. Five-phase hub-and-spoke pipeline composes the right mix per language × critical path × CI target, scaffolds configs + corpus + fixtures, wires CI jobs, and defines the crash\u002Fregression triage workflow. Pure-click: every decision except intake is an AskUserQuestion.","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Ftest-matrix\u002FSKILL.md",[214],{"categoryNo":215,"categoryName":216,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[218,219,220,221,207,41,164,222,193,223,224,225,226,227,228,229,230,179,231,232],"test","matrix","test matrix","unit","regression","mix","intake","testing","decision","ci","tests","e2e","mutation","load","fuzzing",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":240,"publishedAt":44},"01M71K7N3ZY9FMMH3CSE1H8K5J","test-gen","Use when generating tests for untested code — happy path, edge cases, error handling","https:\u002F\u002Fgithub.com\u002FKeiSeiLab\u002FKeiSeiKit\u002Fblob\u002Fmain\u002Fskills\u002Ftest-gen\u002FSKILL.md",[239],{"categoryNo":215,"categoryName":216,"taxonomyType":21,"taxonomyTypeDesc":22},[241,191,218,242,207,175,243,228,244,179,198,245,246,247,248,205],"test gen","error","true","edge","file","code","error handling","name"]