- **Candidate skill:** Do not weaken its assertions or promote it. A held-out failure is evidence of a real skill gap; preserve the failure, classify the root cause, propose a targeted correction, and re-run fresh held-out evaluations against the current guidance and no-skill baseline. Promotion requires independent maintainer approval and verified evidence, with a pinned version, canary monitoring, and rollback to the last verified version. - **Evaluator:** Treat the incorrect rejection as a...
Pro scans all 16 files and shows the line behind each finding
Scanned 9/24/2026
npx -y skills add HoangNguyen0403/agent-skills-standard --skill common-session-retrospective --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Common Session Retrospective?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/hoangnguyen0403-common-session-retrospective-7aef39f4)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
- **Candidate skill:** Do not weaken its assertions or promote it. A held-out failure is evidence of a real skill gap; preserve the failure, classify the root cause, propose a targeted correction, and re-run fresh held-out evaluations against the current guidance and no-skill baseline. Promotion requires independent maintainer approval and verified evidence, with a pinned version, canary monitoring, and rollback to the last verified version.
- **Evaluator:** Treat the incorrect rejection as a separate evaluator/grader defect. Reproduce the valid answer, document the evaluator mismatch, and review or correct the evaluator independently. Do not weaken the candidate’s assertions to game an invalid grader; preserve the candidate’s genuine held-out failure and evaluate it with the corrected grader.
Because no explicit maintenance authorization was provided, make these proposal-only changes rather than editing the canonical registry or installed copies. If authorized later, update the canonical source, regenerate exports through existing tooling, and record redacted evidence, candidate status, source revision, evaluation run, review reference, and rollback version in `AGENTS_LEARNING.md`, following the applicable `AGENTS.md` guidance.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!