[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79PMKBE8SYW0ZP14AEJDM5D":3,"skill-same:01M79PMKBE8SYW0ZP14AEJDM5D":56},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79PMKBE8SYW0ZP14AEJDM5D","worktrail-routing-config",null,"Configure Worktrail's agent routing table (`~\u002F.worktrail\u002Frouting.yaml`, or a repo-local `routing:` policy block) — which harness\u002Fmodel executes each role and tier, and how fallback between them works. Use when the operator wants to add or remove a harness\u002Fadapter (claude\u002Fcodex\u002Fopencode), add a model to an existing harness (e.g. adding a DeepSeek model to opencode), pin or change who does code review, add a new tier or purpose mapping, change the default tier, or is confused about which harness actually served a spawn (e.g. \"why did this use Codex when I only configured Claude\"). Trigger phrases: \"routing.yaml\", \"add a harness\", \"disable a harness\", \"add an adapter\", \"remove an adapter\", \"add a model\", \"add deepseek to opencode\", \"change the reviewer\", \"pin the reviewer\", \"routing tiers\", \"routing targets\", \"default_tier\", \"independent reviewer\", \"why did codex get called\". This skill is about *editing the config file*; it does not cover `\u002Fgo`'s own dispatch mechanics (see `worktrail-go`'s SKILL.md Phase 7 for how `tier_for()`\u002F`select_cell()` resolve it at runtime).","behindthedash\u002Fworktrail","behindthedash","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30299179?v=4","01M79PHT5395GJXDSNP7MYP63D","OC","01M79PHT68KHMYHPS9D9RCYFJZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-routing-config\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: worktrail-routing-config\ndescription: >\n  Configure Worktrail's agent routing table (`~\u002F.worktrail\u002Frouting.yaml`, or a repo-local\n  `routing:` policy block) — which harness\u002Fmodel executes each role and tier, and how\n  fallback between them works. Use when the operator wants to add or remove a harness\u002Fadapter\n  (claude\u002Fcodex\u002Fopencode), add a model to an existing harness (e.g. adding a DeepSeek model to\n  opencode), pin or change who does code review, add a new tier or purpose mapping, change the\n  default tier, or is confused about which harness actually served a spawn (e.g. \"why did this\n  use Codex when I only configured Claude\"). Trigger phrases: \"routing.yaml\", \"add a harness\",\n  \"disable a harness\", \"add an adapter\", \"remove an adapter\", \"add a model\", \"add deepseek to\n  opencode\", \"change the reviewer\", \"pin the reviewer\", \"routing tiers\", \"routing targets\",\n  \"default_tier\", \"independent reviewer\", \"why did codex get called\". This skill is about\n  *editing the config file*; it does not cover `\u002Fgo`'s own dispatch mechanics (see\n  `worktrail-go`'s SKILL.md Phase 7 for how `tier_for()`\u002F`select_cell()` resolve it at runtime).\nallowed-tools: Read, Edit, Write, Bash\n---\n\n# Routing Configuration\n\n## Overview\n\nWorktrail spawns headless agent workers (implement\u002Ffix\u002Fcleanup\u002Freview\u002F...) through one\nresolved routing table: `targets` (which harness\u002Fpool each named target uses) crossed with\n`tiers` (which model\u002Feffort each target runs at, per tier row), plus `roles`\u002F`purposes` that\npick a tier for a given task. This skill is the operator's cookbook for editing that table —\nadding\u002Fremoving harnesses and models, pinning the reviewer, adding tiers — and the gotchas that\nbite when two settings interact non-obviously.\n\n**File location:** `~\u002F.worktrail\u002Frouting.yaml` (machine-wide, `WORKTRAIL_ROUTING_FILE` env var\noverrides the path) is read whenever a repo's own policy has no `routing:` block. A repo-local\n`routing:` block in that repo's `.worktrail\u002Fpolicy.yaml` **replaces the machine-wide file\nentirely** for that repo — it is not merged key-by-key. A non-empty repo-local block means the\nmachine-wide file is never read for that repo at all.\n\n**Where the actual resolution logic lives** (read only if you need to verify behavior, not to\nedit routing): `src\u002Fworktrail\u002Frouter\u002Fpolicy.py` (`resolve_routing`, validation\u002Flegacy-key\nrejection), `src\u002Fworktrail\u002Fruntime\u002Fselection.py` (`select_cell` — the fallback walk),\n`src\u002Fworktrail\u002Forchestrator\u002Fdispatch.py` (`tier_for` — role → tier resolution). The formal\nbehavioral contract is `openspec\u002Fspecs\u002Fmodel-tier-routing\u002Fspec.md` and\n`openspec\u002Fspecs\u002Fdrain-operator-config\u002Fspec.md`.\n\n## Concepts, briefly\n\n| Key | What it is |\n|---|---|\n| `targets` | Named launch targets, each `{harness: claude\\|codex\\|opencode, pool: subscription\\|free\\|api, api_opt_in?, auth?}`. **File order is the fallback order** for any tier row that doesn't reorder it via `prefer`. |\n| `env_profiles` | Named environment sources a target's `auth.profile` points at: `{from: \u003Cjson file>, keys: [...], expect?: {...}}`. Names *where* values live and *which* to copy — never stores a value. See \"point a harness at a custom endpoint\" in `references\u002Fhow-to.md`. |\n| `tiers` | `{tier_name: {target_name: {model, effort?}}}`. A target with no cell in a row cannot serve that tier — the walk skips straight past it. |\n| `roles` | Per-role override (`review`\u002F`resolve`\u002F`ci-fix`\u002F`assembly-resolve`\u002F`implement`\u002F`fix`\u002F`cleanup`): `{tier, prefer?, independent?}`. |\n| `purposes` | `{purpose_value: tier_name}` — routes implement\u002Ffix\u002Fcleanup tasks by their `purpose` frontmatter instead of `complexity`. |\n| `default_tier` | The tier used when nothing more specific matches. |\n| `drain` | Drain-loop-only settings: `max_workers` (concurrent drain-worker slots) and `exclude_repos` (repo directory names never drained unattended, as `discover_repo_names()` reports them — e.g. `worktrail`, not `\u002Fhome\u002Fyou\u002Fprojects\u002Fworktrail` or `owner\u002Fworktrail`). `exclude_repos` is **machine-wide only** — a repo-local `routing:` block declaring it is ignored with a warning — and it reaches the drain's repo sweeps and codex sandbox roots, both pre-passes, the ready-brief count, and automatic brief selection (skip reason `repo-excluded`); `--go-repo`\u002F`--auto-repo` beat it, and an entry matching no repo is inert and reported. No `agent`\u002F`fallback_agents` keys — those are retired, rejected loudly with a migrate hint. |\n\nFull mechanics (precedence order, `prefer` vs `independent`, purpose vs complexity) are in\n`worktrail-go`'s SKILL.md Phase 7 — this skill won't restate them, only the parts you need to\nmake a specific edit safely.\n\n## How-tos\n\nSee `references\u002Fhow-to.md` for the specific recipes:\n- Add a new harness\u002Fadapter (target)\n- Disable a harness\u002Fadapter without deleting its config\n- Add a new model to an existing harness (including adding e.g. a DeepSeek model to `opencode`)\n- Point a harness at a custom Anthropic-compatible endpoint with an env profile\n- Add or remove a tier\n- Route a purpose to a tier\n- Pin, change, or unpin the code reviewer\n- Change `default_tier`\n- Validate a change before trusting it\n\n## Gotchas\n\nSee `references\u002Fgotchas.md` for the non-obvious interactions this table produces, especially:\n- `worktrail-routing --check` is a **spawn readiness probe, not a schema linter**: after the\n  schema\u002Flegacy-key pass it builds each cell's command and child environment from the resolved\n  table *in the checking shell*, so a cell whose auth lane cannot resolve there (e.g. a claude\n  `api` cell whose `auth.env` variable isn't exported in that shell) reports `FAIL` and exits\n  non-zero on an otherwise valid YAML file. A drain now runs the same probe before spawning and\n  **refuses to start** (exit 2, naming the cell and the routing file) instead of routing around\n  the cell — only a *capacity*-gated cell (`model_unavailable` in\n  `~\u002F.worktrail\u002Fagent-capacity.json`) is still walked past. Fix the config or export the\n  variable in the environment that spawns; this is not a condition to wait out.\n- `independent: true` silently overrides `prefer` when the preferred target shares a harness\n  with whichever harness implemented the task — this is the #1 cause of \"I only configured\n  Claude, why did Codex just get spawned.\"\n- `prefer` only reorders a tier row; the *entire* row (in target file order) is the fallback\n  chain — there is no separate fallback list to also check.\n- Legacy top-level keys (`routing.agents`, `routing.fallback`, `routing.purpose_tiers`,\n  `drain.agent`, `drain.fallback_agents`) are rejected outright, not silently ignored — a\n  ruleset written against an older Worktrail version needs `worktrail-routing --migrate`.\n- `api`-pool targets (`openrouter`\u002F`api`) are dropped from selection unless the target sets\n  `api_opt_in: true` — this is deliberate, not a bug, to keep subscription-first spend honest.\n- Effort vocabulary differs per harness: `claude`\u002F`codex` take `low`\u002F`medium`\u002F`high` (`codex`\n  also accepts `minimal`); `opencode` has none — its `effort` field is ignored and model\n  selection is the only lever.\n- A cell can be stuck `unavailable` in `~\u002F.worktrail\u002Fagent-capacity.json` after a stale billing\n  gate outlives its `retry_after` — check that file before assuming a routing-table edit didn't\n  take effect.\n- A worker never sees your **user-level** `~\u002F.claude\u002Fsettings.json`: every claude spawn carries\n  `--setting-sources project,local`, which excludes it. That is deliberate (a user-level Stop\n  hook corrupts a worker's report-back JSON), but it also drops that file's `env` block — so a\n  provider configured *only* there reaches no worker, and the spawn makes **zero API calls while\n  exiting 0**. Reach for an `env_profiles` entry instead of editing `--setting-sources`.\n\n## Verify a change took effect\n\nAny **already-running** drain loop or long-lived orchestrator process loaded `routing.yaml`\ninto memory at startup — it will not see an edit until restarted. A one-off `\u002Fgo` invocation\npicks up the current file on its next run with no restart needed.\n\n```bash\nworktrail-routing --check                 # schema + legacy keys + spawn readiness of every cell\nworktrail-policy --repo \u003Crepo> --resolve-routing \"x:x\" --json   # prints the fully resolved table\n```\n","# Routing Configuration\n\n## Overview\n\nWorktrail spawns headless agent workers (implement\u002Ffix\u002Fcleanup\u002Freview\u002F...) through one\nresolved routing table: `targets` (which harness\u002Fpool each named target uses) crossed with\n`tiers` (which model\u002Feffort each target runs at, per tier row), plus `roles`\u002F`purposes` that\npick a tier for a given task. This skill is the operator's cookbook for editing that table —\nadding\u002Fremoving harnesses and models, pinning the reviewer, adding tiers — and the gotchas that\nbite when two settings interact non-obviously.\n\n**File location:** `~\u002F.worktrail\u002Frouting.yaml` (machine-wide, `WORKTRAIL_ROUTING_FILE` env var\noverrides the path) is read whenever a repo's own policy has no `routing:` block. A repo-local\n`routing:` block in that repo's `.worktrail\u002Fpolicy.yaml` **replaces the machine-wide file\nentirely** for that repo — it is not merged key-by-key. A non-empty repo-local block means the\nmachine-wide file is never read for that repo at all.\n\n**Where the actual resolution logic lives** (read only if you need to verify behavior, not to\nedit routing): `src\u002Fworktrail\u002Frouter\u002Fpolicy.py` (`resolve_routing`, validation\u002Flegacy-key\nrejection), `src\u002Fworktrail\u002Fruntime\u002Fselection.py` (`select_cell` — the fallback walk),\n`src\u002Fworktrail\u002Forchestrator\u002Fdispatch.py` (`tier_for` — role → tier resolution). The formal\nbehavioral contract is `openspec\u002Fspecs\u002Fmodel-tier-routing\u002Fspec.md` and\n`openspec\u002Fspecs\u002Fdrain-operator-config\u002Fspec.md`.\n\n## Concepts, briefly\n\n| Key | What it is |\n|---|---|\n| `targets` | Named launch targets, each `{harness: claude\\|codex\\|opencode, pool: subscription\\|free\\|api, api_opt_in?, auth?}`. **File order is the fallback order** for any tier row that doesn't reorder it via `prefer`. |\n| `env_profiles` | Named environment sources a target's `auth.profile` points at: `{from: \u003Cjson file>, keys: [...], expect?: {...}}`. Names *where* values live and *which* to copy — never stores a value. See \"point a harness at a custom endpoint\" in `references\u002Fhow-to.md`. |\n| `tiers` | `{tier_name: {target_name: {model, effort?}}}`. A target with no cell in a row cannot serve that tier — the walk skips straight past it. |\n| `roles` | Per-role override (`review`\u002F`resolve`\u002F`ci-fix`\u002F`assembly-resolve`\u002F`implement`\u002F`fix`\u002F`cleanup`): `{tier, prefer?, independent?}`. |\n| `purposes` | `{purpose_value: tier_name}` — routes implement\u002Ffix\u002Fcleanup tasks by their `purpose` frontmatter instead of `complexity`. |\n| `default_tier` | The tier used when nothing more specific matches. |\n| `drain` | Drain-loop-only settings: `max_workers` (concurrent drain-worker slots) and `exclude_repos` (repo directory names never drained unattended, as `discover_repo_names()` reports them — e.g. `worktrail`, not `\u002Fhome\u002Fyou\u002Fprojects\u002Fworktrail` or `owner\u002Fworktrail`). `exclude_repos` is **machine-wide only** — a repo-local `routing:` block declaring it is ignored with a warning — and it reaches the drain's repo sweeps and codex sandbox roots, both pre-passes, the ready-brief count, and automatic brief selection (skip reason `repo-excluded`); `--go-repo`\u002F`--auto-repo` beat it, and an entry matching no repo is inert and reported. No `agent`\u002F`fallback_agents` keys — those are retired, rejected loudly with a migrate hint. |\n\nFull mechanics (precedence order, `prefer` vs `independent`, purpose vs complexity) are in\n`worktrail-go`'s SKILL.md Phase 7 — this skill won't restate them, only the parts you need to\nmake a specific edit safely.\n\n## How-tos\n\nSee `references\u002Fhow-to.md` for the specific recipes:\n- Add a new harness\u002Fadapter (target)\n- Disable a harness\u002Fadapter without deleting its config\n- Add a new model to an existing harness (including adding e.g. a DeepSeek model to `opencode`)\n- Point a harness at a custom Anthropic-compatible endpoint with an env profile\n- Add or remove a tier\n- Route a purpose to a tier\n- Pin, change, or unpin the code reviewer\n- Change `default_tier`\n- Validate a change before trusting it\n\n## Gotchas\n\nSee `references\u002Fgotchas.md` for the non-obvious interactions this table produces, especially:\n- `worktrail-routing --check` is a **spawn readiness probe, not a schema linter**: after the\n  schema\u002Flegacy-key pass it builds each cell's command and child environment from the resolved\n  table *in the checking shell*, so a cell whose auth lane cannot resolve there (e.g. a claude\n  `api` cell whose `auth.env` variable isn't exported in that shell) reports `FAIL` and exits\n  non-zero on an otherwise valid YAML file. A drain now runs the same probe before spawning and\n  **refuses to start** (exit 2, naming the cell and the routing file) instead of routing around\n  the cell — only a *capacity*-gated cell (`model_unavailable` in\n  `~\u002F.worktrail\u002Fagent-capacity.json`) is still walked past. Fix the config or export the\n  variable in the environment that spawns; this is not a condition to wait out.\n- `independent: true` silently overrides `prefer` when the preferred target shares a harness\n  with whichever harness implemented the task — this is the #1 cause of \"I only configured\n  Claude, why did Codex just get spawned.\"\n- `prefer` only reorders a tier row; the *entire* row (in target file order) is the fallback\n  chain — there is no separate fallback list to also check.\n- Legacy top-level keys (`routing.agents`, `routing.fallback`, `routing.purpose_tiers`,\n  `drain.agent`, `drain.fallback_agents`) are rejected outright, not silently ignored — a\n  ruleset written against an older Worktrail version needs `worktrail-routing --migrate`.\n- `api`-pool targets (`openrouter`\u002F`api`) are dropped from selection unless the target sets\n  `api_opt_in: true` — this is deliberate, not a bug, to keep subscription-first spend honest.\n- Effort vocabulary differs per harness: `claude`\u002F`codex` take `low`\u002F`medium`\u002F`high` (`codex`\n  also accepts `minimal`); `opencode` has none — its `effort` field is ignored and model\n  selection is the only lever.\n- A cell can be stuck `unavailable` in `~\u002F.worktrail\u002Fagent-capacity.json` after a stale billing\n  gate outlives its `retry_after` — check that file before assuming a routing-table edit didn't\n  take effect.\n- A worker never sees your **user-level** `~\u002F.claude\u002Fsettings.json`: every claude spawn carries\n  `--setting-sources project,local`, which excludes it. That is deliberate (a user-level Stop\n  hook corrupts a worker's report-back JSON), but it also drops that file's `env` block — so a\n  provider configured *only* there reaches no worker, and the spawn makes **zero API calls while\n  exiting 0**. Reach for an `env_profiles` entry instead of editing `--setting-sources`.\n\n## Verify a change took effect\n\nAny **already-running** drain loop or long-lived orchestrator process loaded `routing.yaml`\ninto memory at startup — it will not see an edit until restarted. A one-off `\u002Fgo` invocation\npicks up the current file on its next run with no restart needed.\n\n```bash\nworktrail-routing --check                 # schema + legacy keys + spawn readiness of every cell\nworktrail-policy --repo \u003Crepo> --resolve-routing \"x:x\" --json   # prints the fully resolved table\n```\n",{"name":5,"description":24,"allowed-tools":25},"Configure Worktrail's agent routing table (`~\u002F.worktrail\u002Frouting.yaml`, or a repo-local `routing:` policy block) — which harness\u002Fmodel executes each role and tier, and how fallback between them works. Use when the operator wants to add or remove a harness\u002Fadapter (claude\u002Fcodex\u002Fopencode), add a model to an existing harness (e.g. adding a DeepSeek model to opencode), pin or change who does code review, add a new tier or purpose mapping, change the default tier, or is confused about which harness actually served a spawn (e.g. \"why did this use Codex when I only configured Claude\"). Trigger phrases: \"routing.yaml\", \"add a harness\", \"disable a harness\", \"add an adapter\", \"remove an adapter\", \"add a model\", \"add deepseek to opencode\", \"change the reviewer\", \"pin the reviewer\", \"routing tiers\", \"routing targets\", \"default_tier\", \"independent reviewer\", \"why did codex get called\". This skill is about *editing the config file*; it does not cover `\u002Fgo`'s own dispatch mechanics (see `worktrail-go`'s SKILL.md Phase 7 for how `tier_for()`\u002F`select_cell()` resolve it at runtime).\n","Read, Edit, Write, Bash","main","db448e94704b506e1a5a0665d349fc422611fe9e","skills\u002Fworktrail-routing-config","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail","https:\u002F\u002Fgithub.com\u002Fbehindthedash","2026-11-14 18:34:42",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add behindthedash\u002Fworktrail --skill worktrail-routing-config",{"tool":38,"command":39},"bunx","bunx skills add behindthedash\u002Fworktrail --skill worktrail-routing-config",{"tool":41,"command":42},"pnpm","pnpm dlx skills add behindthedash\u002Fworktrail --skill worktrail-routing-config","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-routing-config\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fgotchas.md","REFERENCE","参考文档",11157,"https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-routing-config\u002Freferences\u002Fgotchas.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fhow-to.md",11580,"https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-routing-config\u002Freferences\u002Fhow-to.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M79PMY53NKDHVZ2AFSGNNJH7","worktrail-sdd-workflow","Internal SDD workflow executor invoked by \u002Fgo only. Do not call directly. Executes classified routes A–J: feature planning, implementation (parallel orchestration, PR generation), defect repair, refactoring, spec changes, investigation, and workflow evolution.","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-sdd-workflow\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M79PMB24YTZTZVVAKA4A4R38","worktrail-repo-init","Bootstrap a new repo, or migrate an existing single-branch repo, onto the workspace's repo-standards doctrine (~\u002Frules\u002FCLAUDE.repo.md): the AGENTS.md-is-truth\u002FCLAUDE.md-imports-it split, a dev\u002Fprd, dev\u002Fstg\u002Fprd, or main-only (trunk) branch model with matching GitHub rulesets, an OpenSpec scaffold, an auto-merge workflow, and a seeded .worktrail\u002Fpolicy.yaml. Trigger phrases: \"onboard this repo\", \"apply repo standards\", \"initialize repo standards\", \"set up this repo like the rest of the fleet\", \"bring this repo into line with the repo standards doctrine\".","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-repo-init\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M79PM54RFP51Q2JPQGE13ZP8","worktrail-help","Show the Worktrail front-door commands and accepted positional arguments. Use when the user asks how to invoke worktrail-go, wants the available handoff, spec, pr, repo, or route forms, invokes worktrail-go with help or with a bare noun, or asks how to answer a filed product decision (worktrail-decision).","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-help\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M79PKVZVBF4VFT5XEPCPNM9S","worktrail-handoff","Capture a discovered problem, gap, tech debt, or deferred work into a local work queue so a future agent session can pick it up cold. Use mid-session whenever you set work aside instead of doing it now — a fix you judge out of scope for this PR, work that belongs in a follow-up or a separate\u002Flater PR, an item you're deferring, or something worth fixing you won't tackle now — so the outstanding item isn't lost without derailing current work; can be called multiple times per session. Trigger phrases: \"defer this\", \"item deferred\", \"out of scope for this PR\", \"follow-up work\", \"leave for another PR\", \"capture for later\", \"outstanding item\". This skill captures only. Picking a brief back up is the front door's job: worktrail-go \u003Cbrief-id>.","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-handoff\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"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},"01M79PKJZD9MPN7Q8GWR01KX0J","worktrail-go","Use when the user invokes worktrail-go, asks to pick up queued work, resume active specs, implement or fix a spec, route engineering work, or orient across repositories. Renders the orientation dashboard, classifies free-text requests, claims\u002Fresumes handoff briefs, and dispatches SDD work without requiring the user to know sdd-workflow. Grammar: worktrail-go [REPO] \u003Cnoun> \u003Cverb>, nouns handoff \u002F spec \u002F pr \u002F decision. Triggers: worktrail-go, worktrail-go help, worktrail-go spec fix, worktrail-go spec implement, worktrail-go spec route F, worktrail-go handoff new, worktrail-go handoff auto, worktrail-go decision answer, worktrail-go BRIEF-ID, bare worktrail-go, multi-repo orientation.","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fworktrail-go\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M79PKF5TJCEH2ATW902XMSZ3","openspec-update-change","Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.","https:\u002F\u002Fgithub.com\u002Fbehindthedash\u002Fworktrail\u002Fblob\u002Fmain\u002Fskills\u002Fopenspec-update-change\u002FSKILL.md",[],[]]