[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DH2GW0AR9B613ST4W4CD4R":3,"skill-same:01M7DH2GW0AR9B613ST4W4CD4R":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7DH2GW0AR9B613ST4W4CD4R","health-check",null,"Read-only health report on the development harness — always-on budget headroom, eval cases, pending proposal age, specs stuck in flight, stale gate markers, vendor opt-in, required checks, main's CI, open pull requests with unresolved threads, and local branches whose pull request merged","turbokast\u002Fmythhelm","turbokast","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F335585049?v=4","01M7DGYYSHNA1BW1Y9GJFN6DVC","TurboKast","01M7DGYYT6GTPCFADDKS5ZXM1Y",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhealth-check\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: health-check\ndescription: Read-only health report on the development harness — always-on budget headroom, eval cases, pending proposal age, specs stuck in flight, stale gate markers, vendor opt-in, required checks, main's CI, open pull requests with unresolved threads, and local branches whose pull request merged\nargument-hint: \"[--offline] [--json] [--stale-days N]\"\n---\n\n# Health Check\n\nOne report on whether the harness is in a state to trust. It changes nothing: every finding comes with the command that would act on it, for a maintainer or another skill to run. The checks and their statuses are defined in `scripts\u002Fharness\u002Fhealth.py`; `knowledge\u002Flearning-loop.md` explains where each fits in the loop.\n\n## Input\n\n`$ARGUMENTS`, all optional: `--offline` (skip the GitHub checks), `--json` (the machine-readable report), `--stale-days N` (the age at which a proposal or an in-flight spec is reported, default 7).\n\n## Invocation contexts\n\n- **Slash command**: runs both steps and prints the report.\n- **Model-invoked**: the same.\n- **Non-interactive**: the same; the report is the final message. The skill writes nothing, so it has no gates.\n\n## Steps\n\n1. **Report.** Unless `--offline`, refresh the remote refs first so `origin\u002Fmain` is current (a fetch changes no branch or file):\n\n   ```bash\n   git fetch -q origin\n   python3 scripts\u002Fharness\u002Fhealth.py $ARGUMENTS\n   ```\n\n   The script prints every check with one status: `ok`, `warn`, `fail`, `unknown` or `skipped`. A check that could not run is `unknown` with its reason, never omitted, so the report shows `checks=10` on every run. Quote its output; do not re-derive or summarise away a status.\n2. **Next steps.** For each `warn`, `fail` or `unknown`, name the action, without taking it:\n\n   | Check | Action |\n   |---|---|\n   | `budget` | move always-on text to path-conditional rules or `knowledge\u002F` (`.claude\u002Frules\u002Fagent-config-conventions.md`) |\n   | `evals` | the named case lost its behaviour: fix the change that broke it, or update the case in the same pull request that deliberately changes the behaviour |\n   | `proposals` | `\u002Fapply-proposals` |\n   | `specs` | `\u002Frun-spec \u003Cspec>` or `\u002Ffinalize-spec \u003Cspec>` to resume, or `\u002Fevaluate-spec \u003Cspec>` |\n   | `gate-markers` | `scripts\u002Fharness\u002Fgate.sh \u003Cscope>` in that worktree before any completion claim |\n   | `required-checks` | a maintainer restores the ruleset, or updates `.claude\u002Fdata\u002Frequired-checks.json` and `docs\u002Fautomation.md` together |\n   | `main-ci` | `real`: a fix pull request; `infra` or `unknown`: the maintainer decides on a re-run |\n   | `open-prs` | answer and resolve the threads on each pull request |\n   | `merged-branches` | `scripts\u002Fharness\u002Fprune-merged.sh` lists what it would remove; with `--apply` it deletes each branch and its clean worktree after verifying the merge (a squash merge leaves `git branch -d` unable to tell) |\n\n   Never delete a branch or worktree, re-run a job, merge or edit anything from this skill.\n\n## Output\n\nThe script's report verbatim, followed by the next-step lines for every check that is not `ok` or `skipped`:\n\n```text\nHarness health\n  ok       budget           always-on 13291 of 16384 bytes, headroom 3093\n  warn     proposals        2 pending, oldest 21 days; decide them with \u002Fapply-proposals\n  ...\nchecks=10 ok=7 warn=2 fail=0 unknown=1 skipped=0\nNext: proposals -> \u002Fapply-proposals; ...\n```\n","# Health Check\n\nOne report on whether the harness is in a state to trust. It changes nothing: every finding comes with the command that would act on it, for a maintainer or another skill to run. The checks and their statuses are defined in `scripts\u002Fharness\u002Fhealth.py`; `knowledge\u002Flearning-loop.md` explains where each fits in the loop.\n\n## Input\n\n`$ARGUMENTS`, all optional: `--offline` (skip the GitHub checks), `--json` (the machine-readable report), `--stale-days N` (the age at which a proposal or an in-flight spec is reported, default 7).\n\n## Invocation contexts\n\n- **Slash command**: runs both steps and prints the report.\n- **Model-invoked**: the same.\n- **Non-interactive**: the same; the report is the final message. The skill writes nothing, so it has no gates.\n\n## Steps\n\n1. **Report.** Unless `--offline`, refresh the remote refs first so `origin\u002Fmain` is current (a fetch changes no branch or file):\n\n   ```bash\n   git fetch -q origin\n   python3 scripts\u002Fharness\u002Fhealth.py $ARGUMENTS\n   ```\n\n   The script prints every check with one status: `ok`, `warn`, `fail`, `unknown` or `skipped`. A check that could not run is `unknown` with its reason, never omitted, so the report shows `checks=10` on every run. Quote its output; do not re-derive or summarise away a status.\n2. **Next steps.** For each `warn`, `fail` or `unknown`, name the action, without taking it:\n\n   | Check | Action |\n   |---|---|\n   | `budget` | move always-on text to path-conditional rules or `knowledge\u002F` (`.claude\u002Frules\u002Fagent-config-conventions.md`) |\n   | `evals` | the named case lost its behaviour: fix the change that broke it, or update the case in the same pull request that deliberately changes the behaviour |\n   | `proposals` | `\u002Fapply-proposals` |\n   | `specs` | `\u002Frun-spec \u003Cspec>` or `\u002Ffinalize-spec \u003Cspec>` to resume, or `\u002Fevaluate-spec \u003Cspec>` |\n   | `gate-markers` | `scripts\u002Fharness\u002Fgate.sh \u003Cscope>` in that worktree before any completion claim |\n   | `required-checks` | a maintainer restores the ruleset, or updates `.claude\u002Fdata\u002Frequired-checks.json` and `docs\u002Fautomation.md` together |\n   | `main-ci` | `real`: a fix pull request; `infra` or `unknown`: the maintainer decides on a re-run |\n   | `open-prs` | answer and resolve the threads on each pull request |\n   | `merged-branches` | `scripts\u002Fharness\u002Fprune-merged.sh` lists what it would remove; with `--apply` it deletes each branch and its clean worktree after verifying the merge (a squash merge leaves `git branch -d` unable to tell) |\n\n   Never delete a branch or worktree, re-run a job, merge or edit anything from this skill.\n\n## Output\n\nThe script's report verbatim, followed by the next-step lines for every check that is not `ok` or `skipped`:\n\n```text\nHarness health\n  ok       budget           always-on 13291 of 16384 bytes, headroom 3093\n  warn     proposals        2 pending, oldest 21 days; decide them with \u002Fapply-proposals\n  ...\nchecks=10 ok=7 warn=2 fail=0 unknown=1 skipped=0\nNext: proposals -> \u002Fapply-proposals; ...\n```\n",{"name":5,"description":7,"argument-hint":24},"[--offline] [--json] [--stale-days N]","main","6e250ec86158119da148ddc017b960ed3b2bee2b",".claude\u002Fskills\u002Fhealth-check",1,"https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm","https:\u002F\u002Fgithub.com\u002Fturbokast","https:\u002F\u002Fturbokast.com","2026-11-10 17:37:03",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add turbokast\u002Fmythhelm --skill health-check",{"tool":39,"command":40},"bunx","bunx skills add turbokast\u002Fmythhelm --skill health-check",{"tool":42,"command":43},"pnpm","pnpm dlx skills add turbokast\u002Fmythhelm --skill health-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhealth-check\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DH77QH78C95S7A5V1GFKKF","mythhelm-deliver-backlog","Coordinate a MYTHHELM backlog run with the shared stage checks and maintainer checkpoints.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-deliver-backlog\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DH748EXYG9RVBWPBJ73M27","mythhelm-bootstrap","Orient a Grok Build session in the MYTHHELM repository before task or spec work.","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.grok\u002Fskills\u002Fmythhelm-bootstrap\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DH70XJE0DZA4T5DYR1TWKZ","vendor-consult","Run one advisory stage consult (premise-ground, spec-validate, task-review, change-review, stuck-oracle, dossier) with an optional external vendor, then adjudicate the answer at its anchors","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvendor-consult\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DH6X9HSQ308P5FNDSKYR5R","update-docs","Bring README, docs\u002F, knowledge\u002F, WORKFLOW.md and CLAUDE.md in line with what a shipped spec or a merged change actually did — find every statement the change made stale, fix it where readers look, and add only the new facts they need","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DH6T82XR40XQFNRTN4AHGN","triage","Score an idea or a GitHub issue against the master spec's stages, gates and commitments, check it for duplicates, and recommend whether it becomes a backlog card; read-only","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DH6Q17PM4ESX978QYFV6H6","test-driven-development","Red-green-refactor for Go — use when implementing any feature, bug fix or behaviour change, before writing implementation code","https:\u002F\u002Fgithub.com\u002Fturbokast\u002Fmythhelm\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]