메뉴
Skill quality lens — review a skill against skill-writing best practices,
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Cut a Flowpad release — bump the version (patch by default; minor/major on request), build the wheel (UI baked in), publish to PyPI, tag + push to GitHub, and validate the install. Then, if the electron/ directory changed since the previous release, trigger the desktop build. Use when asked to deploy/release Flowpad, publish to PyPI, or cut a new version (including a new minor like 0.3.0).
toplog — topic-tracing assistant for debugging. `run` activates the right trace topics for a given issue (in code or tests) so RCA has better traceability; `scan` reconciles the topics referenced in code against the topic catalog; `learn` consolidates post-RCA findings (enrich a topic, add a new one with its trace points, or retire a stale one). Use when debugging a hard failure and you want richer logs before or alongside RCA, when adding or auditing toplog topics, or after proving a root cause to capture the traceability that helped. Also triggers on "turn on tracing for X", "what topics cover Y", "add a toplog topic", or "audit toplog topics".
Root Cause Analyzer — prove the real cause of a failure by finding its
Find a product online within a location and price range, verify availability and shipping, and report the findings.
Analyze an agentic execution from its session transcript and produce
Where to find the on-disk logs for Flowpad — the local backend instances (Alice / Bob), the Electron desktop app (shell / monitor / server), and the local hub. Use when you need to read backend or desktop logs to debug the running processes instead of asking the user to copy-paste console output.
| id | 9ad58753-7eb4-501a-a8d2-65001e264330 |
| name | skillit |
| description | Skill quality lens — review a skill against skill-writing best practices, |
| tags | |
| version | 4 |
Skillit is the static-artifact half of a teaching loop: it reviews and corrects the recipes (skill files) themselves — it does not scan live sessions or measure runtime usage.
This file only routes. Load a file when its row matches the task at hand, and follow routing chains until you reach instructions.
| Request shape | Mode |
|---|---|
| "review / audit / check / lint this skill" — no run-time issues given; optionally with a context document (transcript, spec) to judge against | review |
| issues observed while running the skill are supplied | correct |
Run-time issues force correct mode even if the user says "review".
Resolve the target skill before loading anything else: a path, or a name under
.claude/skills/ (project) / ~/.claude/skills/ (user). The target is the
whole folder — SKILL.md plus everything it routes to.
| When you need to… | Load |
|---|---|
| run a review pass (incl. deciding whether to stop on a re-review) | modes/review.md |
| apply corrections for reported issues | modes/correct.md |
| judge the target against best practices (either mode) | rubric/rubric.md — an index itself; it routes to the specific criterion |
Never delete knowledge from a target skill — fix its routing, structure, or content instead; unused is not a reason to remove. Unused today is a retrieval problem, not a content problem; tomorrow's reader may need it.
Integrate edits in place — edit the existing instruction so the nuance becomes part of it, keeping the file readable as if it were always correct. When you append changelogs, dated bullets, or mistakes-log sections, they accumulate into a changelog nobody reads; integrating ensures the skill guidance stays current and navigable for each reader.
At most 5 findings or corrections per pass — small batches keep each correction attributable and reviewable; large batches hide which change caused a side effect.
After any edit, audit the touched files against structure.md #1 (indexes
stay thin) and structure.md #6 (every routing reference resolves, every
file reachable). If the audit fails, revert the edit.
