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".
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- tk-studio-report
- description
- 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".
02 资源文件 2
- 其他customize.toml419 B
- 脚本scripts/report.py2.9 KB
03 SKILL.md 正文
tk-studio-report
The explicit human-authored defect verb (AD-12). Human-observed defects enter the same measurement stream as telemetry and ride the same PR membrane toward the issues ledger.
Behavior
Attended: elaborate before recording — ask (briefly, once) for whatever is missing from: what happened vs. what was expected, which skill/surface is suspected, and which project it was in. Then emit:
uv run "${CLAUDE_PLUGIN_ROOT}/skills/tk-studio-report/scripts/report.py" \
--description "<expected vs actual, operator's words>" \
--surface <suspected-skill> --project <key> --skill <skill-running> --mode attended
Confirm to the user what landed (the script echoes the sanitized envelope —
show its description back so they can spot over-redaction).
Headless: the payload arrives complete in the invocation; pass it straight
through with --mode headless — never prompt (AD-11). A missing
--description is the script's validation error → end blocked. End with the
status block:
{"status": "complete", "intent": "tk-studio-report", "artifacts": ["~/.tk-studio/measurements/<user>-<machine>.jsonl"], "reason": null}
If the deterministic core is unrunnable — a tool call denied by permissions, uv/python unavailable — end blocked with the status block naming the unrunnable core as reason: never a question, never a headless run that ends without the block (AD-11).
Rollup (Story 35.8): the Stage Log read like a timesheet
report.py rollup rolls a story's or an epic's ## Stage Log rows up
(elapsed derived from started/ended, never stored):
uv run "${CLAUDE_PLUGIN_ROOT}/skills/tk-studio-report/scripts/report.py" rollup \
--directory <project-root> --epic <N> [--post --id <EP-NNN>]
(--story <key> for one story.) The JSON names per story and per epic the
cycle time (first start to the merge), hands-on time (the sum of the spans;
a row wholly inside another engine row's span, a consult inside its review
pass, is listed under nested and not counted twice),
the planning share, review rounds, re-runs, every gap between a stop and
the next start, tokens and cost per stage type, and Jira's own stamps
(_bmad-output/tracking/stage-posts.json) beside them with each boundary's
skew (created minus the comment body's timestamp) and the max named.
The epic rollup counts each span once: shared supervisor rows (host-leg,
re-run, close-out, merge — one run resolving several stories) are
matched on stage, pass, started and ended, and a span inside another story's
engine span is counted as nested; each story's own numbers stay as they are.
--post --id <EP-NNN> adds one rollup comment to the epic's Jira issue
(idempotent by [stage-rollup:epic-<N>]; not bound: posted: "skipped: not bound"). The retrospective reads this rollup for stage times and cost
instead of inferring them from PR timestamps. It ends with the status
block (intent tk-studio-report); a story or epic with no rows, or a
refused post, ends blocked naming why.
Rules
- The description is the operator's account, not your diagnosis — record what they said, don't fix the defect in this flow.
- Sanitization happens in the ledger library; still, never coax credentials or machine paths into the description.
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-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.
tk-studio-orchestrator
The studio's front door — resolve who you are (role, per-user store), what this project needs (confirmed working_set.<role>), and route to resources by name, statelessly. Use when the user says "enter the studio", "tk studio", "orchestrate", "convene the council", or asks what to work on through the studio.