
skill-retro
Grade an agent setup from real conversation history — a rebuild of warpdotdev/common-skills' skill-doctor (MIT). Harvests recent local Claude Code and Codex sessions scoped to one repo, condenses and secret-redacts transcripts (12-pattern redactor, chmod-0600 artifacts, nothing uploaded), has the agent judge each transcript against two verbatim-preserved rubrics (efficiency, code quality — labels only), then runs a deterministic aggregation gate that derives every number from the label tables, refuses scores for unsampled sessions and suggestions that cite no scored session, and renders one self-contained zero-JS HTML report (dark-mode, print-to-PDF). Proposed skill edits stay staged as diffs until an explicit per-skill yes; zero suggestions is a valid, reportable success. Ships cs-skill-retro agent, /cs-skill-retro command, 3 stdlib tools, 3 references citing 7 sources each.
- version
- 2.14.6
- GitHub stars
- 29.6K
Install
/plugin install skill-retro@claude-code-skillsRun it inside Claude Code after adding the marketplace with /plugin marketplace add alirezarezvani/claude-skills.
Contents
Discovered from sourceSkills 1
Commands 1
Agents 1
Sponsors
Details
- Marketplace
- alirezarezvani/claude-skills
- Source
- engineering/skill-retro
- Author
- Alireza Rezvani
- Category
- development
- Keywords
- skill-retro, skill-grading, session-mining, llm-as-judge, rubric-scoring, transcript-analysis, skill-coverage, secret-redaction, agent-evals, engineering
More from alirezarezvani/claude-skills
All 121- skill-security-auditorv2.2.0
- skillopt-sleepv2.14.5
- slo-architectv2.14.5
- snowflake-developmentv2.14.5
- spinning-up-deep-rlv2.14.6
- statistical-analystv2.14.9
- swedish-mentorv2.14.5
- syllabusv2.14.6
- terraform-patternsv2.14.6
- universal-scraping-architectv2.14.9
- video-content-strategistv2.14.5
- vpe-advisorv2.14.5
- weekly-reviewv2.14.5
- workflow-builderv2.14.5
- write-a-skillv2.14.9
- youtube-fullv2.14.5
- zero-hallucination-coderv2.14.5
- a11y-auditv2.14.5
- access-lifecyclev2.14.5
- aeov2.14.6
- agent-harnessv2.14.11
- agent-launcher-skillsv2.14.5
- agent-memoryv2.14.6
- agent-regression-evalsv2.14.5