[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AQE5PVHTQ8F4DBNZ0JC11M":3,"skill-same:01M7AQE5PVHTQ8F4DBNZ0JC11M":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":43},"01M7AQE5PVHTQ8F4DBNZ0JC11M","wayfinder",null,"Plan a chunk of work too big for one agent session as a map of workstreams in Task, and resolve them one at a time until the way to the destination is clear.","FastTrackStudios\u002Ftask","FastTrackStudios","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F210671141?v=4","01M7AQB9T7HCY285ERN7G42A9W","01M7AQB9TWYE6J7R97QC1HW15K",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fwayfinder\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: wayfinder\ndescription: Plan a chunk of work too big for one agent session as a map of workstreams in Task, and resolve them one at a time until the way to the destination is clear.\ndisable-model-invocation: true\n---\n\nA loose idea has arrived — too big for one session, and wrapped in\nfog: the way from here to the **destination** isn't visible yet.\nWayfinding is about finding that way, not charging at the destination.\n\nRead [..\u002FISSUE-TRACKER.md](..\u002FISSUE-TRACKER.md) first. Everything here\nlives in Task.\n\n## Plan, don't do\n\nEach workstream resolves a decision. The map is done when nothing is\nleft to decide before someone goes and builds. The pull to just do the\nwork is usually the signal you've reached the edge of the map and it's\ntime to hand off.\n\n## Refer by name\n\nEvery map and workstream has a title. In everything a human reads,\nrefer to it by that title, never by a bare id. A wall of `a7c62905,\ndd1e00ab, ed88375c` is illegible; names read at a glance. The id rides\ninside the name, never stands in for it.\n\n## The map\n\nAn ordinary Task issue. Its body carries five sections, and the\nsections round-trip losslessly — anything you add between them\nsurvives, so hand edits are safe.\n\n```markdown\n## Destination\n\n\u003Cwhat reaching the end looks like. One or two lines; every session\norients to it before choosing what to work.>\n\n## Notes\n\n\u003Cdomain; skills to consult; standing preferences for this effort>\n\n## Decisions so far\n\n- [\u003Cclosed workstream title>](\u003Cid>) — \u003Cone-line gist of the answer>\n\n## Not yet specified\n\n\u003Cin-scope fog you cannot state sharply enough to ticket yet>\n\n## Out of scope\n\n\u003Cwork consciously ruled beyond the destination; never graduates>\n```\n\nThe map is an **index, not a store**. A decision lives in exactly one\nplace — its workstream — and the map only gists it and links.\n*Decisions so far* is append-only: never rewrite an entry, because\neach one is the only pointer to a closed workstream's reasoning.\n\n## Workstreams\n\nWhat upstream calls a *decision ticket*. Each is one session's worth of\ncontext, created as a subtask of the map:\n\n```bash\ntask issue create \"\u003Cthe question>\" --parent \u003Cmap> --workstream \u003Cws> \\\n  --body - \u003C\u003C'EOF'\n## Question\n\n\u003Cthe decision or investigation this resolves>\nEOF\n```\n\nClaim before any work — `task issue start \u003Cid> --as-agent \u003Cyou>` —\nso a concurrent session skips it. Wire blocking in a second pass, once\nids exist: `task issue relate \u003Ca> blocks \u003Cb>`.\n\nThe **frontier** is `task issue ready`: open, unblocked, unclaimed.\n\n## Types\n\nEvery workstream is either **HITL** — worked *with* a human who speaks\nfor themselves — or **AFK**. A HITL workstream resolves only through\nthat live exchange. **The agent never stands in for the human's side\nof it.** A grilling session that answers its own questions has broken\nthis, and so has an agent that decides a question is obvious.\n\n- **Research** (AFK) — reading docs or code to surface a fact a\n  decision waits on. Use `\u002Fresearch`.\n- **Prototype** (HITL) — make a cheap concrete thing to react to when\n  \"how should it behave\" is the question.\n- **Grilling** (HITL) — conversation. The default. Use `\u002Fgrilling` and\n  `\u002Fdomain-modeling`.\n- **Task** (HITL or AFK) — manual work that must happen before a\n  decision can be made. The one type that *does* rather than decides,\n  and it earns its place by unblocking a decision.\n\n## Fog of war\n\nThe map is deliberately incomplete. Beyond the live workstreams lies\nfog: decisions you can tell are coming but cannot yet pin down.\n\n**Fog or workstream?** Whether you can state the question precisely\nnow — *not* whether you can answer it. Ticket a sharp question even if\nit is blocked. Leave a vague one in *Not yet specified*, and don't\npre-slice it: one patch of fog may graduate into several workstreams,\nor none.\n\n## Out of scope\n\nFog gathers only *toward* the destination. Work past it is out of\nscope, not fog. When an existing workstream turns out to sit beyond the\ndestination, **close it** and leave one line under *Out of scope* with\nthe gist and why. It stays out of *Decisions so far*, which records the\nroute actually walked — a scope boundary is not a step on it.\n\n## Invocation\n\nNever resolve more than one workstream per session, research excepted.\n\n### Chart the map\n\n1. **Name the destination.** `\u002Fgrilling` + `\u002Fdomain-modeling`. The\n   destination fixes the scope, so it is settled first.\n2. **Map the frontier.** Grill again, breadth-first, across the whole\n   space. **If no fog surfaces**, the way is already clear and you do\n   not need a map — say so and stop.\n3. **Create the map** with Destination and Notes filled, Decisions\n   empty, the fog sketched into *Not yet specified*.\n4. **Create the workstreams you can specify**, then wire blocking in a\n   second pass.\n5. **Fire the research subagents** for any research workstreams.\n6. Stop. Charting is one session's work and resolves nothing.\n\n### Work through the map\n\n1. Load the map body — the low-res view, not every workstream.\n2. Choose a workstream. Without one named, take the first on the\n   frontier. **Claim it first.**\n3. Resolve it, zooming into related closed workstreams on demand.\n4. Post the answer, close it, append one line to *Decisions so far*.\n5. Graduate any fog the answer sharpened, clearing it from *Not yet\n   specified*. If the answer reveals something sits past the\n   destination, rule it out of scope rather than resolving it.\n\nExpect other sessions to be editing Task concurrently.\n","A loose idea has arrived — too big for one session, and wrapped in\nfog: the way from here to the **destination** isn't visible yet.\nWayfinding is about finding that way, not charging at the destination.\n\nRead [..\u002FISSUE-TRACKER.md](..\u002FISSUE-TRACKER.md) first. Everything here\nlives in Task.\n\n## Plan, don't do\n\nEach workstream resolves a decision. The map is done when nothing is\nleft to decide before someone goes and builds. The pull to just do the\nwork is usually the signal you've reached the edge of the map and it's\ntime to hand off.\n\n## Refer by name\n\nEvery map and workstream has a title. In everything a human reads,\nrefer to it by that title, never by a bare id. A wall of `a7c62905,\ndd1e00ab, ed88375c` is illegible; names read at a glance. The id rides\ninside the name, never stands in for it.\n\n## The map\n\nAn ordinary Task issue. Its body carries five sections, and the\nsections round-trip losslessly — anything you add between them\nsurvives, so hand edits are safe.\n\n```markdown\n## Destination\n\n\u003Cwhat reaching the end looks like. One or two lines; every session\norients to it before choosing what to work.>\n\n## Notes\n\n\u003Cdomain; skills to consult; standing preferences for this effort>\n\n## Decisions so far\n\n- [\u003Cclosed workstream title>](\u003Cid>) — \u003Cone-line gist of the answer>\n\n## Not yet specified\n\n\u003Cin-scope fog you cannot state sharply enough to ticket yet>\n\n## Out of scope\n\n\u003Cwork consciously ruled beyond the destination; never graduates>\n```\n\nThe map is an **index, not a store**. A decision lives in exactly one\nplace — its workstream — and the map only gists it and links.\n*Decisions so far* is append-only: never rewrite an entry, because\neach one is the only pointer to a closed workstream's reasoning.\n\n## Workstreams\n\nWhat upstream calls a *decision ticket*. Each is one session's worth of\ncontext, created as a subtask of the map:\n\n```bash\ntask issue create \"\u003Cthe question>\" --parent \u003Cmap> --workstream \u003Cws> \\\n  --body - \u003C\u003C'EOF'\n## Question\n\n\u003Cthe decision or investigation this resolves>\nEOF\n```\n\nClaim before any work — `task issue start \u003Cid> --as-agent \u003Cyou>` —\nso a concurrent session skips it. Wire blocking in a second pass, once\nids exist: `task issue relate \u003Ca> blocks \u003Cb>`.\n\nThe **frontier** is `task issue ready`: open, unblocked, unclaimed.\n\n## Types\n\nEvery workstream is either **HITL** — worked *with* a human who speaks\nfor themselves — or **AFK**. A HITL workstream resolves only through\nthat live exchange. **The agent never stands in for the human's side\nof it.** A grilling session that answers its own questions has broken\nthis, and so has an agent that decides a question is obvious.\n\n- **Research** (AFK) — reading docs or code to surface a fact a\n  decision waits on. Use `\u002Fresearch`.\n- **Prototype** (HITL) — make a cheap concrete thing to react to when\n  \"how should it behave\" is the question.\n- **Grilling** (HITL) — conversation. The default. Use `\u002Fgrilling` and\n  `\u002Fdomain-modeling`.\n- **Task** (HITL or AFK) — manual work that must happen before a\n  decision can be made. The one type that *does* rather than decides,\n  and it earns its place by unblocking a decision.\n\n## Fog of war\n\nThe map is deliberately incomplete. Beyond the live workstreams lies\nfog: decisions you can tell are coming but cannot yet pin down.\n\n**Fog or workstream?** Whether you can state the question precisely\nnow — *not* whether you can answer it. Ticket a sharp question even if\nit is blocked. Leave a vague one in *Not yet specified*, and don't\npre-slice it: one patch of fog may graduate into several workstreams,\nor none.\n\n## Out of scope\n\nFog gathers only *toward* the destination. Work past it is out of\nscope, not fog. When an existing workstream turns out to sit beyond the\ndestination, **close it** and leave one line under *Out of scope* with\nthe gist and why. It stays out of *Decisions so far*, which records the\nroute actually walked — a scope boundary is not a step on it.\n\n## Invocation\n\nNever resolve more than one workstream per session, research excepted.\n\n### Chart the map\n\n1. **Name the destination.** `\u002Fgrilling` + `\u002Fdomain-modeling`. The\n   destination fixes the scope, so it is settled first.\n2. **Map the frontier.** Grill again, breadth-first, across the whole\n   space. **If no fog surfaces**, the way is already clear and you do\n   not need a map — say so and stop.\n3. **Create the map** with Destination and Notes filled, Decisions\n   empty, the fog sketched into *Not yet specified*.\n4. **Create the workstreams you can specify**, then wire blocking in a\n   second pass.\n5. **Fire the research subagents** for any research workstreams.\n6. Stop. Charting is one session's work and resolves nothing.\n\n### Work through the map\n\n1. Load the map body — the low-res view, not every workstream.\n2. Choose a workstream. Without one named, take the first on the\n   frontier. **Claim it first.**\n3. Resolve it, zooming into related closed workstreams on demand.\n4. Post the answer, close it, append one line to *Decisions so far*.\n5. Graduate any fog the answer sharpened, clearing it from *Not yet\n   specified*. If the answer reveals something sits past the\n   destination, rule it out of scope rather than resolving it.\n\nExpect other sessions to be editing Task concurrently.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","a40932117efadcace0179d510514d6470df318cd","skills\u002Fagent-lane\u002Fwayfinder",1,"https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask","https:\u002F\u002Fgithub.com\u002FFastTrackStudios","2026-11-06 08:57:53",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":23},[33,36,39],{"tool":34,"command":35},"npx","npx skills add FastTrackStudios\u002Ftask --skill wayfinder",{"tool":37,"command":38},"bunx","bunx skills add FastTrackStudios\u002Ftask --skill wayfinder",{"tool":40,"command":41},"pnpm","pnpm dlx skills add FastTrackStudios\u002Ftask --skill wayfinder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fwayfinder\u002FSKILL.md",[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7AQEBTWH75FJHTVBAV8EKST","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7AQE7ZPBK6G7BK3NYDTWM0Z","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7AQE4589DSXSB3YC6HJW882","wait-what","Stop. That last message did not land — re-pitch it.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7AQE1J3X5TTYSDEGBVZHKDJ","triage","Move issues into the agent lane — decide who does it, what proves it done, and which machine can take it. Agents triage; humans get surfaced only what needs them.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7AQDYCT400E1KYQB86DY6RQ","to-tickets","Break a plan, spec, or the current conversation into tracer-bullet tickets in Task, each declaring its blocking edges, its verify command, and the capabilities a runner needs to take it.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7AQDWF029ET9G3ZDRR1KTPM","to-spec","Turn the current conversation into a spec and publish it to Task — no interview, just synthesis of what you have already discussed.","https:\u002F\u002Fgithub.com\u002FFastTrackStudios\u002Ftask\u002Fblob\u002Fmain\u002Fskills\u002Fagent-lane\u002Fto-spec\u002FSKILL.md",[],[]]