tk-studio-measure-push
Push the local measurement ledger into the shared repo as a membrane PR — feature branch, per-user-per-machine file, sanitization re-check pre-commit, review as the gate. Use when the user says "push my measurements", "tk measure push", or a job's invoke-skill directive names this skill.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- tk-studio-measure-push
- description
- Push the local measurement ledger into the shared repo as a membrane PR — feature branch, per-user-per-machine file, sanitization re-check pre-commit, review as the gate. Use when the user says "push my measurements", "tk measure push", or a job's invoke-skill directive names this skill.
02 资源文件 1
- 其他customize.toml500 B
03 SKILL.md 正文
tk-studio-measure-push
The mover half of the measurement membrane (ST-7.1, AD-12): the local ledger
becomes measurements/<user>-<machine>.jsonl on the shared repo through
plain git governance. Review is the membrane — this skill never pushes a
base branch and never merges anything. It is a mover, not an emitter: it
appends no measurement event of its own; the events it moves were each
emitted by their one named emitter.
Behavior (both modes)
-
Check first (read-only, no network):
uv run "${CLAUDE_PLUGIN_ROOT}/lib/measurepush.py" check --directory <studio-repo-root>Reports unpushed-event count and the sanitization verdict. Zero unpushed is a first-class clean no-op, not an error.
-
Push through the core (never hand-drive git for this):
uv run "${CLAUDE_PLUGIN_ROOT}/lib/measurepush.py" push --directory <studio-repo-root>The core re-checks sanitization pre-commit (a credential-shaped finding blocks before any branch exists), lands only new ledger lines append-only on the stable branch
measurements/<user>-<machine>, stages only this machine's file, pushes, and opens the PR — or recognizes the open one the push just updated (repeat pushes update the same PR, never a duplicate).A
dry_runpayload rides the core's own flag —push --dry-run— which walks every gate (studio-root check, dirty tree, sanitization) without landing a branch, commit, or PR. Never substitute a check-only summary for the push verb: the check step reports, onlypushenforces. -
Attended: summarize what moved — event count, branch, PR URL — and surface a
committed-localresult (offline push) orunavailablePR step as the retry guidance the core returned. Headless: aPushBlockedrefusal (exit 2 — wrong directory, dirty tree, sanitization finding) endsblockedwith the core's error asreason— identically underdry_run: true: the core refusing a dry-run push is still a refusal, never downgraded tocomplete; a push or PR step that could not reach the remote endspartial(useful work landed: the local branch commit) — never a prompt (AD-11). End headless runs with the status block:{"status": "complete", "intent": "tk-studio-measure-push", "artifacts": ["measurements/<user>-<machine>.jsonl"], "reason": null}
If the deterministic core is unrunnable — a tool call denied by permissions, uv/python 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).
Rules
- Never push a base branch, never merge, never close or approve the PR — review is the promotion gate (AD-12).
- Per-user-per-machine file only; another machine's file under
measurements/is never staged, edited, or deleted. - Append-only: a line already on the shared file is never rewritten or removed by a push.
- A sanitization finding is a hard stop, not a warning — fix the ledger, rerun; never hand-edit the finding away on the branch (NFR5).
- All paths resolve through
${CLAUDE_PLUGIN_ROOT}.
04 同仓库更多 Skills
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.
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/budget trigger says the session must split.
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.
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".
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".
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/stories.