skill-evaluation
Evaluate a Codex skill's routing accuracy and task quality with a human-approved, isolated workflow.
Skill by nayounsang
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nayounsang-skill-evaluation
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
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/skill-evaluation
What's inside
- Skill name
skill-evaluation- Description
- Evaluate a Codex skill's routing accuracy and task quality with a human-approved, isolated workflow. Run only when the user explicitly invokes $younsang-codex-plugin:skill-evaluation; do not start from an implicit request to evaluate a skill.
- License
- unknown
- Instructions
- 118 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- openai.yaml · agents/
- case-design.md · references/
- collect-skill-invocations.mjs · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from nayounsang/younsang-codex-plugin
- 0.587score
strict-review
nayounsang
Perform an explicit, read-only, high-recall review of a code change for concrete defects, security, performance, reachability and defense proportionality…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
api-scenario-forge
nayounsang
Control MSW HTTP and WebSocket scenarios from an AI agent, then verify the resulting browser or Node application behavior end to end.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
angry-insight
nayounsang
Analyze newly collected prompts and research ways to prevent mistakes from recurring, but only when the user explicitly invokes `$angry-insight`.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
dev-docs-review
nayounsang
Audit developer documentation against a repository's implementation, public contracts, user journeys, and authoritative ecosystem sources, reporting…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
install-complex-prompt
nayounsang
Install or update Codex Complex Prompt for Codex CLI when the user asks to set it up.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
write-pr-content
nayounsang
Index the focused Markdown fragment skills used to document pull request changes; invoke a child skill for the requested fragment instead of using this…
SkillAFreshness: A★ 1Claude Code +9 - 0.577score
install-plannotator
nayounsang
Install Plannotator and its Codex integration on macOS, Linux, WSL, or Windows when the user explicitly asks to install it.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 14
- Last commit (this folder)
- Oct 9, 2026 (19 days ago)
- Last release
- Oct 11, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nayounsang
- 0.587score
strict-review
nayounsang
Perform an explicit, read-only, high-recall review of a code change for concrete defects, security, performance, reachability and defense proportionality…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
api-scenario-forge
nayounsang
Control MSW HTTP and WebSocket scenarios from an AI agent, then verify the resulting browser or Node application behavior end to end.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
angry-insight
nayounsang
Analyze newly collected prompts and research ways to prevent mistakes from recurring, but only when the user explicitly invokes `$angry-insight`.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
dev-docs-review
nayounsang
Audit developer documentation against a repository's implementation, public contracts, user journeys, and authoritative ecosystem sources, reporting…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
install-complex-prompt
nayounsang
Install or update Codex Complex Prompt for Codex CLI when the user asks to set it up.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
write-pr-content
nayounsang
Index the focused Markdown fragment skills used to document pull request changes; invoke a child skill for the requested fragment instead of using this…
SkillAFreshness: A★ 1Claude Code +9
Cite this page
skill-evaluation. Agent Mart. https://agentmart.dev/skills/nayounsang-skill-evaluation (last updated 2026-10-24)