evaluation
Use when creating or updating agent evaluation suites.
Skill by craigtkhill
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/craigtkhill-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: 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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/evaluation
What's inside
- Skill name
evaluation- Description
- Use when creating or updating agent evaluation suites. Defines eval structure, rubrics, and validation patterns.
- License
- unknown
- Instructions
- 81 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from craigtkhill/spec-driven-development
- 0.559score
pre-commit-hooks
craigtkhill
Use when running pre-commit hooks manually (e.g.
SkillAFreshness: AClaude Code +9 - 0.559score
update-dependencies
craigtkhill
Use when updating existing pinned dependencies.
SkillAFreshness: AClaude Code +9 - 0.559score
specifying-requirements
craigtkhill
Use when specifying a feature or adding requirements.
SkillAFreshness: AClaude Code +9 - 0.558score
write-commit-message
craigtkhill
Use when creating git commits.
SkillAFreshness: AClaude Code +9 - 0.558score
acceptance-test
craigtkhill
Use when writing acceptance tests or scenarios.
SkillAFreshness: AClaude Code +9 - 0.554score
create-skill
craigtkhill
Use when creating or modifying skills.
SkillAFreshness: AClaude Code +9 - 0.553score
sdd
craigtkhill
Defines complete workflow from specification through testing to implementation.
SkillAFreshness: AClaude Code +9 - 0.529score
test-driven-development
craigtkhill
Use when writing tests.
SkillAFreshness: AClaude Code +9 - 0.519score
error-handling
craigtkhill
Use when writing, reviewing, or refactoring a try/except (or try/catch) block, or any edge-case branch guarding against a failure.
SkillBFreshness: BClaude Code +9 - 0.518score
install-dependencies
craigtkhill
Use when adding project dependencies.
SkillBFreshness: BClaude Code +9 - 0.516score
refactoring-code
craigtkhill
Use during REFACTOR phase of TDD (after GREEN), when logic is duplicated, or when locality of behavior is violated.
SkillBFreshness: BClaude Code +9 - 0.301score
prototyping
craigtkhill
No description from the publisher yet.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 22, 2026 (8 months 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 craigtkhill
- 0.559score
pre-commit-hooks
craigtkhill
Use when running pre-commit hooks manually (e.g.
SkillAFreshness: AClaude Code +9 - 0.559score
specifying-requirements
craigtkhill
Use when specifying a feature or adding requirements.
SkillAFreshness: AClaude Code +9 - 0.559score
update-dependencies
craigtkhill
Use when updating existing pinned dependencies.
SkillAFreshness: AClaude Code +9 - 0.558score
acceptance-test
craigtkhill
Use when writing acceptance tests or scenarios.
SkillAFreshness: AClaude Code +9 - 0.558score
write-commit-message
craigtkhill
Use when creating git commits.
SkillAFreshness: AClaude Code +9 - 0.554score
create-skill
craigtkhill
Use when creating or modifying skills.
SkillAFreshness: AClaude Code +9
Cite this page
evaluation skill. Agent Mart. https://agentmart.dev/skills/craigtkhill-evaluation (last updated 2026-10-24)