Individual skill
plugin-feedback
Write development-skills feedback from observed work, or assess a report for useful simplifications.
plugins/reidemeister94/development-skills/skills/plugin-feedback/SKILL.md
Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,532
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- awesome Repository topic
- awesome-list Repository topic
- codex Repository topic
- codex-plugins Repository topic
- openai Repository topic
- codex-skill Repository topic
- codex-skills Repository topic
- marketplace Repository topic
- codex-marketplace Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 1,021 bytes
Read excerpt
# Plugin feedback
`produce` writes `docs/reports/development-skills-feedback-YYYY-MM-DD.md` from the current session.
Include the task, used capabilities, observed delays or errors, evidence, and reproducible improvement ideas.
Explain decision reasons. Do not include private reasoning traces or invent token and time measurements.
`ingest <report-path>` treats the report as claims to verify against the current files and observed behavior.
Apply changes within the user's authorization when they fix a demonstrated problem or repeated waste.
Prefer deletion or merging. Keep project facts and avoid a universal rule for one model mistake.
Add an eval only when it can expose a meaningful regression, and tag its owning paths.
Report changes, rejected suggestions with reasons, and verification limits.