Common Session Retrospective
ASecurityAssumption: `route handler` is an indirect phrase for an existing skill, not a reason to create a new skill. **Trigger miss** - Skill: affected existing skill ID, confirmed from `AGENTS.md` - Missed phrase: `route handler` - Root cause: routing/trigger gap - Evidence: the task used `route handler`, but the matching skill was not loaded - Proposed fix: add the exact keyword `route handler` to that skill’s canonical trigger list; update `AGENTS.md` only if its index must reflect the change - Sc...
- 571 stars
- 0 votes
- 0 copies
- 0 views
- Added September 24, 2026
Security analysis
100/100Pro scans all 16 files and shows the line behind each finding
npx -y skills add HoangNguyen0403/agent-skills-standard --skill common-session-retrospective --agent claude-codeAre you the author of Common Session Retrospective?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hoangnguyen0403-common-session-retrospective-4a05ddaf)Assumption: `route handler` is an indirect phrase for an existing skill, not a reason to create a new skill.
**Trigger miss**
- Skill: affected existing skill ID, confirmed from `AGENTS.md`
- Missed phrase: `route handler`
- Root cause: routing/trigger gap
- Evidence: the task used `route handler`, but the matching skill was not loaded
- Proposed fix: add the exact keyword `route handler` to that skill’s canonical trigger list; update `AGENTS.md` only if its index must reflect the change
- Scope: edit the canonical registry source, regenerate exports with existing tooling, and do not modify installed copies
Before promotion, require:
- Concrete correction evidence linked to the session or redacted log; never persist credentials, customer identifiers, or raw incident data.
- Held-out evaluation comparing current guidance, the candidate, and a no-skill baseline with model and tools fixed.
- Preserved failures and separate review of any invalid grader or benchmark result.
- Fresh evaluation results showing the trigger now loads the intended skill without material regressions.
- Independent maintainer approval. The proposing agent cannot approve its own patch; its offered approval is not independent or authenticated.
- A `common/common-learning-log` entry in `AGENTS_LEARNING.md` recording the redacted evidence, candidate status, source revision, evaluation run, review reference, and rollback version.
Until those proofs and independent approval exist, the patch remains unpromoted.
Files in this skill
- eval-1.baseline.md
- eval-1.with-skill.md
- eval-2.baseline.md
- eval-2.with-skill.md
- eval-3.baseline.md
- eval-3.with-skill.md
- eval-4.baseline.md
- eval-4.with-skill.md
- trigger-1.md
- trigger-2.md
- trigger-3.md
- trigger-4.md
- trigger-5.md
- trigger-6.md
- trigger-7.md
Attribution
Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.