capture-eval-issues
Capture noteworthy review violations for the eval framework.
Skill by Codagent-AI
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
npx agentmarket install skill/codagent-ai-capture-eval-issues-812974
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
capture-eval-issues- Description
- Capture noteworthy review violations for the eval framework. Use when validator-run finds review failures — judges violations and saves notable ones to evals/inventory.yml.
- License
- MIT
- Allowed tools
- Bash,, Task,, Read
- Instructions
- 18 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (3)
- SKILL.md
- judge-prompt.md
- append-inventory.ts · scripts/
SKILL.md (first lines)
# /capture-eval-issues Capture noteworthy review violations into the eval inventory. ## Input This skill receives one or more review JSON file paths as arguments (space-separated). Example: `/capture-eval-issues validator_logs/review_src_claude@1.0.json validator_logs/review_src_gemini@2.0.json` ## Procedure 1. Read `judge-prompt.md` from this skill's directory 2. Spawn a subagent to judge and capture violations: - **Task tool**: `Task` with `subagent_type="general-purpose"`, `model="sonnet"`, `prompt=` judge-prompt content + `"\n\nReview JSON files: <file paths>\n\nSkill directory: <this skill's directory path>"` - The subagent handles everything: reading files, judging, calling the append script 3. Report the subagent's capture summary (the `CAPTURED:` line)
From Codagent-AI/agent-validator, MIT.
More from Codagent-AI/agent-validator
- 0.653score
validator-setup
Codagent-AI
Scans the project and configures checks and reviews for Agent Validator for requests such as "set up validator", "configure checks and reviews", or…
SkillAFreshness: A★ 30Claude Code +9 - 0.653score
validator-help
Codagent-AI
Diagnoses and explains validator behavior from runtime evidence for requests such as "why did validator fail", "explain validator behavior", "diagnose…
SkillAFreshness: A★ 30Claude Code +9 - 0.651score
capture-eval-issues
Codagent-AI
Capture noteworthy review violations for the eval framework.
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-status
Codagent-AI
Shows a summary of the most recent validator session for requests such as "show validator status", "summarize last validator run", or "what failed in the last…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-run
Codagent-AI
Activates only for explicit full-validator requests such as "run the validator", "run the gauntlet", "run validation", or validation before commit, push, or…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-commit
Codagent-AI
Activates only for explicit validator-aware commit requests such as "commit with validator", "run validator then commit", "run checks before commit", or "skip…
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-issue
Codagent-AI
Files structured GitHub bug reports for agent-validator when users ask to file, report, or open an issue for a suspected defect
SkillAFreshness: A★ 30Claude Code +9 - 0.644score
validator-check
Codagent-AI
Activates only for explicit checks-only validation requests such as "run validator checks", "checks only", "check without reviews", or validation without AI…
SkillAFreshness: A★ 30Claude Code - 0.643score
validator-skip
Codagent-AI
Advances the validator execution state baseline without running checks for requests such as "skip validator", "advance validator baseline", or "mark current…
SkillAFreshness: A★ 30Claude Code +9
Signals
- Stars
- 30
- Forks
- 2
- Open issues
- 14
- Last commit (this folder)
- May 13, 2026 (5 months ago)
- Last release
- Sep 29, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Codagent-AI/agent-validator
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Codagent-AI
- 0.653score
validator-setup
Codagent-AI
Scans the project and configures checks and reviews for Agent Validator for requests such as "set up validator", "configure checks and reviews", or…
SkillAFreshness: A★ 30Claude Code +9 - 0.653score
validator-help
Codagent-AI
Diagnoses and explains validator behavior from runtime evidence for requests such as "why did validator fail", "explain validator behavior", "diagnose…
SkillAFreshness: A★ 30Claude Code +9 - 0.651score
capture-eval-issues
Codagent-AI
Capture noteworthy review violations for the eval framework.
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-status
Codagent-AI
Shows a summary of the most recent validator session for requests such as "show validator status", "summarize last validator run", or "what failed in the last…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-run
Codagent-AI
Activates only for explicit full-validator requests such as "run the validator", "run the gauntlet", "run validation", or validation before commit, push, or…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-commit
Codagent-AI
Activates only for explicit validator-aware commit requests such as "commit with validator", "run validator then commit", "run checks before commit", or "skip…
SkillAFreshness: A★ 30Claude Code
Cite this page
capture-eval-issues skill. Agent Mart. https://agentmart.dev/skills/codagent-ai-capture-eval-issues-812974 (last updated 2026-10-24)