[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RXK0KFS0BKX57A980GDZV":3,"skill-same:01M79RXK0KFS0BKX57A980GDZV":52},{"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":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79RXK0KFS0BKX57A980GDZV","tk-studio-onboard",null,"Onboard a project into the studio — stand up the taxonomy (store, config, registry, kb, vault window), then propose a role × project working set with evidence and record it only on explicit confirmation. Use when the user says \"onboard this project\", \"tk onboard\", \"set up the studio here\", or \"recommend a working set\".","thkennedy\u002Ftk-studio","thkennedy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4164502?v=4","01M79QZ8DMP5FF2HC6GS3S6FDF","Tim Kennedy","01M79QZ8EM9JBWJ15R5JNC4PW3",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-onboard\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tk-studio-onboard\ndescription: Onboard a project into the studio — stand up the taxonomy (store, config, registry, kb, vault window), then propose a role × project working set with evidence and record it only on explicit confirmation. Use when the user says \"onboard this project\", \"tk onboard\", \"set up the studio here\", or \"recommend a working set\".\n---\n\n# tk-studio-onboard\n\nOnboarding lands the Taxonomy (Epic 2) and turns the Recommendation inputs\n(`tk-studio-detect`) into a confirmed, recorded working set (AD-17). Detection\nnever guesses; recording happens only on the operator's explicit confirmation.\n\n## Flow (both modes)\n\nRun each step through the plugin root; all are idempotent.\n\n1. **Taxonomy standup** (skips cleanly whatever already exists):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fstore.py\" standup\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fconfig.py\" standup --directory \u003Cproject-root> [--vcs git|perforce] [--project-id ID]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fregistry.py\" register --directory \u003Cproject-root> --writer onboard [--project-id ID]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fkb.py\" standup --directory \u003Cproject-root>\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fvault.py\" link --project-id \u003Cid>\n   ```\n\n   A `project_id` collision fails registration and demands an explicit id\n   (AD-20) — surface it, never invent one. No vault configured → linking\n   skips cleanly (the vault is a view, never a dependency).\n\n   Attended, after standup: if the store config has no `display_name`, ask\n   how the operator wants the studio to address them and record the answer:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fstore.py\" set-name \"\u003Cname>\"\n   ```\n\n   \"Use my assistant preference\" records the literal `assistant-preference`\n   — the fallback, chosen, so no surface asks again. Headless never prompts\n   and skips this (address is presentation-only).\n\n2. **Propose** (read-only — this IS the dry run; it shows the full plan and\n   writes nothing):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" propose --directory \u003Cproject-root>\n   ```\n\n   Role resolves from the per-user store (`--role` overrides). Every proposed\n   resource carries evidence lines by source: `role-default` (conservative\n   per-role base), `detection` (only on a `confident` outcome — type, score,\n   fired markers), `user-authored` (the project's own resources, first-class).\n   On an ask outcome (`ambiguous — ask` \u002F `unknown — ask`) the proposal\n   carries no detection-derived entries and a note saying so.\n\n   A confident game profile can also propose a plugin-shipped engine skill\n   (`game-godot` → `gds-engine-godot-4`, Story 34.4): a `kind: skill` entry\n   with `detection:` and `engine-pin:` evidence (the project's pinned engine\n   version against the skill's supported range). A pin outside the range,\n   a features\u002FSDK disagreement or an unreadable pin adds the entry's\n   `warnings[]` and a `gds-engine-godot-4: ` note; a pin that cannot be\n   checked (no readable `project.godot`, a malformed `global.json`) is still\n   proposed and carries an `engine pin not checked: \u003Creason>` warning;\n   attended, show that warning to the operator before they confirm. Headless onboarding records\n   nothing new: it records only what the payload confirms.\n\n3. **Confirm, then record**:\n   - **Attended:** present the proposal with its evidence; the operator\n     edits\u002Faccepts the set. On an ask outcome, ask what the project is\n     first and re-propose. Only after an explicit yes:\n\n     ```bash\n     uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" record --directory \u003Cproject-root> --role \u003Crole> --resources \u003Ca,b,c>\n     ```\n\n   - **Headless:** confirmation must arrive in the payload (an explicit\n     `resources` list). No payload set → do NOT record; end `blocked` naming\n     the missing confirmation (AD-11 — never prompt, never guess).\n   - **The engine MCP (Story 34.5):** a confident game profile can also\n     propose its engine MCP — a `kind: mcp` entry with `detection:` and\n     `kb: kb\u002Fengine-mcp-godot.md` evidence, status `configured` (the\n     project's `.mcp.json` already has it) or `not-configured`. It is never\n     part of `--resources`; only after an explicit yes for that entry\n     (attended), or an explicit `mcp` name in the payload (headless), record\n     it — the one write of the project's `.mcp.json`:\n\n     ```bash\n     uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" record --directory \u003Cproject-root> --mcp \u003Cname>\n     ```\n\n     It merges `mcpServers.\u003Cname>` with the URL and bearer as\n     `${TK_ENGINE_MCP_URL:-}` \u002F `${TK_ENGINE_MCP_BEARER:-}` (never a value;\n     the empty default keeps `.mcp.json` parseable in every session where\n     the supervisor set neither), rewrites an entry in the earlier `${VAR}`\n     form, leaves every other server untouched, and refuses a name no\n     profile suggests or a malformed `.mcp.json` (exit 2). Given with\n     `--role`\u002F`--resources` in one call, both are checked before either is\n     written. Detection and `propose` never write it.\n\n   Recording lands in tracked config `working_set.\u003Crole>` — a role-keyed\n   map: this role's entry replaced, every other role's entry and every\n   comment preserved byte-for-byte. Re-recording an identical set is a\n   no-op (idempotent re-onboarding).\n\n4. **Set up tracking** (optional — only when asked: attended, the operator\n   asks for it; headless, the payload carries `tracking: true`). The\n   planning adapter creates the project's Jira project, its statuses and\n   the \"Needs you\" filter, and the linked Confluence space with its\n   design-page folders, from the studio template, and records the keys and\n   ids under `planning.jira` and `planning.confluence` (AD-4: this skill\n   never calls Atlassian itself):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fplansync.py\" setup --directory \u003Cproject-root> [--dry-run] [--owner-account-id \u003Cid> | --owner-email \u003Cowner email>]\n   ```\n\n   Pass `--owner-account-id` or `--owner-email` from the payload's\n   `owner_account_id` \u002F `owner_email` when given. It uses the agent seat's\n   variables only — `TK_ATLASSIAN_SITE` (first setup), `TK_ATLASSIAN_AGENT_EMAIL`,\n   `TK_ATLASSIAN_AGENT_TOKEN`, `TK_ATLASSIAN_AGENT_CONFLUENCE_TOKEN`,\n   `TK_ATLASSIAN_CLOUD_ID` — and refuses with each absent one named (and\n   on an unregistered project) before any call: relay that refusal as\n   `blocked`, never ask for a token. Relay the setup's status block as\n   this skill's — its `status` and `reason` unchanged, its `artifacts`\n   added to (deduplicated with) the artifacts onboard itself wrote this\n   run (`kb\u002F`, vault links, the registry entry), with `intent` set to\n   `tk-studio-onboard` (the core's block says `tk-studio-plan-sync`):\n   `complete` when every step was created or found;\n   `partial` with its `owner_steps[]` shown **verbatim and in order** —\n   the numbered steps the API could not do on the free plan — never\n   reworded and never reported `complete`; `blocked` with its `reason`.\n   A rerun is idempotent: what exists is recognised by key and named in\n   `found[]`.\n\n## Report\n\n- **Attended:** one line per standup step (created vs already-present), the\n  proposal table with evidence, then the recorded outcome.\n- **Attended, tracking:** the setup's `found[]` and `created[]`, then, on\n  `partial`, its numbered owner steps verbatim.\n- **Headless:** end with the status block — `complete` after a successful\n  record (or a clean standup-only run with no confirmation requested),\n  `partial` when tracking setup ended `partial` (its `reason` carries the\n  owner's numbered steps verbatim, `artifacts` the config it wrote plus\n  what onboard itself wrote),\n  `blocked` on collision, classification refusal, missing confirmation, or\n  a tracking-setup refusal:\n\n  ```json\n  {\"status\": \"complete\", \"intent\": \"tk-studio-onboard\", \"artifacts\": [\".tk-studio\u002Fconfig.yaml\"], \"reason\": null}\n  ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- Recording is the only write to `working_set` and happens only on explicit\n  confirmation — a proposal is never auto-recorded (NFR6).\n- Registry writes go through `registry.py` with `--writer onboard` (AD-20\n  single-writer); this skill never edits `projects.yaml` directly.\n- Tracked-config writes are classification-checked (AD-3) — a refusal is a\n  `blocked` status, not a workaround.\n- Tracking setup goes through `plansync.py setup` only (AD-4); the\n  owner's token is never read and no token lands in any file (AD-3).\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n","# tk-studio-onboard\n\nOnboarding lands the Taxonomy (Epic 2) and turns the Recommendation inputs\n(`tk-studio-detect`) into a confirmed, recorded working set (AD-17). Detection\nnever guesses; recording happens only on the operator's explicit confirmation.\n\n## Flow (both modes)\n\nRun each step through the plugin root; all are idempotent.\n\n1. **Taxonomy standup** (skips cleanly whatever already exists):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fstore.py\" standup\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fconfig.py\" standup --directory \u003Cproject-root> [--vcs git|perforce] [--project-id ID]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fregistry.py\" register --directory \u003Cproject-root> --writer onboard [--project-id ID]\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fkb.py\" standup --directory \u003Cproject-root>\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fvault.py\" link --project-id \u003Cid>\n   ```\n\n   A `project_id` collision fails registration and demands an explicit id\n   (AD-20) — surface it, never invent one. No vault configured → linking\n   skips cleanly (the vault is a view, never a dependency).\n\n   Attended, after standup: if the store config has no `display_name`, ask\n   how the operator wants the studio to address them and record the answer:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fstore.py\" set-name \"\u003Cname>\"\n   ```\n\n   \"Use my assistant preference\" records the literal `assistant-preference`\n   — the fallback, chosen, so no surface asks again. Headless never prompts\n   and skips this (address is presentation-only).\n\n2. **Propose** (read-only — this IS the dry run; it shows the full plan and\n   writes nothing):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" propose --directory \u003Cproject-root>\n   ```\n\n   Role resolves from the per-user store (`--role` overrides). Every proposed\n   resource carries evidence lines by source: `role-default` (conservative\n   per-role base), `detection` (only on a `confident` outcome — type, score,\n   fired markers), `user-authored` (the project's own resources, first-class).\n   On an ask outcome (`ambiguous — ask` \u002F `unknown — ask`) the proposal\n   carries no detection-derived entries and a note saying so.\n\n   A confident game profile can also propose a plugin-shipped engine skill\n   (`game-godot` → `gds-engine-godot-4`, Story 34.4): a `kind: skill` entry\n   with `detection:` and `engine-pin:` evidence (the project's pinned engine\n   version against the skill's supported range). A pin outside the range,\n   a features\u002FSDK disagreement or an unreadable pin adds the entry's\n   `warnings[]` and a `gds-engine-godot-4: ` note; a pin that cannot be\n   checked (no readable `project.godot`, a malformed `global.json`) is still\n   proposed and carries an `engine pin not checked: \u003Creason>` warning;\n   attended, show that warning to the operator before they confirm. Headless onboarding records\n   nothing new: it records only what the payload confirms.\n\n3. **Confirm, then record**:\n   - **Attended:** present the proposal with its evidence; the operator\n     edits\u002Faccepts the set. On an ask outcome, ask what the project is\n     first and re-propose. Only after an explicit yes:\n\n     ```bash\n     uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" record --directory \u003Cproject-root> --role \u003Crole> --resources \u003Ca,b,c>\n     ```\n\n   - **Headless:** confirmation must arrive in the payload (an explicit\n     `resources` list). No payload set → do NOT record; end `blocked` naming\n     the missing confirmation (AD-11 — never prompt, never guess).\n   - **The engine MCP (Story 34.5):** a confident game profile can also\n     propose its engine MCP — a `kind: mcp` entry with `detection:` and\n     `kb: kb\u002Fengine-mcp-godot.md` evidence, status `configured` (the\n     project's `.mcp.json` already has it) or `not-configured`. It is never\n     part of `--resources`; only after an explicit yes for that entry\n     (attended), or an explicit `mcp` name in the payload (headless), record\n     it — the one write of the project's `.mcp.json`:\n\n     ```bash\n     uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Frecommend.py\" record --directory \u003Cproject-root> --mcp \u003Cname>\n     ```\n\n     It merges `mcpServers.\u003Cname>` with the URL and bearer as\n     `${TK_ENGINE_MCP_URL:-}` \u002F `${TK_ENGINE_MCP_BEARER:-}` (never a value;\n     the empty default keeps `.mcp.json` parseable in every session where\n     the supervisor set neither), rewrites an entry in the earlier `${VAR}`\n     form, leaves every other server untouched, and refuses a name no\n     profile suggests or a malformed `.mcp.json` (exit 2). Given with\n     `--role`\u002F`--resources` in one call, both are checked before either is\n     written. Detection and `propose` never write it.\n\n   Recording lands in tracked config `working_set.\u003Crole>` — a role-keyed\n   map: this role's entry replaced, every other role's entry and every\n   comment preserved byte-for-byte. Re-recording an identical set is a\n   no-op (idempotent re-onboarding).\n\n4. **Set up tracking** (optional — only when asked: attended, the operator\n   asks for it; headless, the payload carries `tracking: true`). The\n   planning adapter creates the project's Jira project, its statuses and\n   the \"Needs you\" filter, and the linked Confluence space with its\n   design-page folders, from the studio template, and records the keys and\n   ids under `planning.jira` and `planning.confluence` (AD-4: this skill\n   never calls Atlassian itself):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fplansync.py\" setup --directory \u003Cproject-root> [--dry-run] [--owner-account-id \u003Cid> | --owner-email \u003Cowner email>]\n   ```\n\n   Pass `--owner-account-id` or `--owner-email` from the payload's\n   `owner_account_id` \u002F `owner_email` when given. It uses the agent seat's\n   variables only — `TK_ATLASSIAN_SITE` (first setup), `TK_ATLASSIAN_AGENT_EMAIL`,\n   `TK_ATLASSIAN_AGENT_TOKEN`, `TK_ATLASSIAN_AGENT_CONFLUENCE_TOKEN`,\n   `TK_ATLASSIAN_CLOUD_ID` — and refuses with each absent one named (and\n   on an unregistered project) before any call: relay that refusal as\n   `blocked`, never ask for a token. Relay the setup's status block as\n   this skill's — its `status` and `reason` unchanged, its `artifacts`\n   added to (deduplicated with) the artifacts onboard itself wrote this\n   run (`kb\u002F`, vault links, the registry entry), with `intent` set to\n   `tk-studio-onboard` (the core's block says `tk-studio-plan-sync`):\n   `complete` when every step was created or found;\n   `partial` with its `owner_steps[]` shown **verbatim and in order** —\n   the numbered steps the API could not do on the free plan — never\n   reworded and never reported `complete`; `blocked` with its `reason`.\n   A rerun is idempotent: what exists is recognised by key and named in\n   `found[]`.\n\n## Report\n\n- **Attended:** one line per standup step (created vs already-present), the\n  proposal table with evidence, then the recorded outcome.\n- **Attended, tracking:** the setup's `found[]` and `created[]`, then, on\n  `partial`, its numbered owner steps verbatim.\n- **Headless:** end with the status block — `complete` after a successful\n  record (or a clean standup-only run with no confirmation requested),\n  `partial` when tracking setup ended `partial` (its `reason` carries the\n  owner's numbered steps verbatim, `artifacts` the config it wrote plus\n  what onboard itself wrote),\n  `blocked` on collision, classification refusal, missing confirmation, or\n  a tracking-setup refusal:\n\n  ```json\n  {\"status\": \"complete\", \"intent\": \"tk-studio-onboard\", \"artifacts\": [\".tk-studio\u002Fconfig.yaml\"], \"reason\": null}\n  ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- Recording is the only write to `working_set` and happens only on explicit\n  confirmation — a proposal is never auto-recorded (NFR6).\n- Registry writes go through `registry.py` with `--writer onboard` (AD-20\n  single-writer); this skill never edits `projects.yaml` directly.\n- Tracked-config writes are classification-checked (AD-3) — a refusal is a\n  `blocked` status, not a workaround.\n- Tracking setup goes through `plansync.py setup` only (AD-4); the\n  owner's token is never read and no token lands in any file (AD-3).\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n",{"name":5,"description":7},"main","ecd23b3c0458cd511812f643d9111e3d7c8235f4","plugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-onboard","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio","https:\u002F\u002Fgithub.com\u002Fthkennedy","https:\u002F\u002Ftimothyhkennedy.com","Just a guy who loves making tools, automation and games.","2026-11-10 20:38:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add thkennedy\u002Ftk-studio --skill tk-studio-onboard",{"tool":38,"command":39},"bunx","bunx skills add thkennedy\u002Ftk-studio --skill tk-studio-onboard",{"tool":41,"command":42},"pnpm","pnpm dlx skills add thkennedy\u002Ftk-studio --skill tk-studio-onboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-onboard\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"customize.toml","OTHER","其他",516,"https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-onboard\u002Fcustomize.toml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79RYSQ8C3MWDFTDSRAYFJYA","tk-studio-track","Tracking verbs on the bound Jira project — `block` moves a story the loop cannot progress, and each dependent story, to \"Blocked - Awaiting User\" with a comment that @mentions the owner (or, with `--engagement`, one engagement's questions issue, which `close` later moves to \"Done\"); `reply` posts the owner's answer (or \"Done.\") with the owner's host-only token and moves the issue to \"Block Resolved\"; `validate` checks that resolution and passes the issue back to work or re-blocks it with a follow-up. Use when the user says \"block this story\", \"tk track block\", \"put it in the owner's inbox\", \"reply to the blocked issue\", \"validate the resolution\", or a supervisor or engagement payload names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-track\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79RYMVE0031EV5B64MBGD8V","tk-studio-session","Session discipline as a surface — land a boundary handoff (optionally carrying knowledge deltas) and end the session, or resume a fresh session from a run workspace alone. Use when the user says \"hand off this run\", \"tk session\", \"resume the run\", or a boundary\u002Fbudget trigger says the session must split.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-session\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"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},"01M79RYFM9ATWHM6HAXJ3D19WV","tk-studio-research","Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\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},"01M79RYA1AWZZF83KBHGR6JDN3","tk-studio-report","One-verb human defect report — \"the skill did the wrong thing\" — recorded as a report event in the local measurement ledger. Use when the user says \"tk report\", \"report a defect\", \"that skill misbehaved\", or \"log a studio issue\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-report\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},"01M79RY33VMYR5YNPVFKWRNW9S","tk-studio-playable-judge","The playable-verify leg's screenshot judge (Story 34.3) — reads only a playable run's report.json and its frames, answers the fixed rubric (scene loaded, player visible and framed, no magenta or error overlay, HUD reads, the named moments shown) with pass or fail and findings each naming a frame and a rubric line. Driven headless by the supervisor's host leg on the project's sandbox tier; use when the payload names a playable `media` folder, or the user says \"judge the playable frames\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-playable-judge\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},"01M79RXY4AM8JM6ZK2MAR3W3X2","tk-studio-plan-sync","Planning adapter — canonicalize BMad-native planning artifacts (normalize pass, sole id authority) and sync them with the bound planning backend. Use when the user says \"sync the plan\", \"normalize planning artifacts\", \"tk plan sync\", or after stock BMad planning flows produce or change epics\u002Fstories.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-plan-sync\u002FSKILL.md",[],[]]