Skip to content
Agentmart
Submit a tool

skill-evaluator

Evaluates a named skill by running its artifact checks and optionally invoking the skill against fixture inputs.

Skill by dmenezesgabriel

IndexedLicense unknown
Write a review

Chalk Labs

Need help deploying skill-evaluator?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/dmenezesgabriel-skill-evaluator

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.

We use your email only for this newsletter. Privacy

About

Evaluates a named skill by running its artifact checks and optionally invoking the skill against fixture inputs. Produces a structured eval report with deterministic structural checks (behave), LLM-as-judge qualitative checks, trigger routing checks, baseline comparison, and skill input size measurement. Use when asked to "evaluate a skill", "check skill output quality", "run evals for plan-it", "validate the dataviz skill", "measure skill input size", "check whether a skill triggers correctly", or "compare a skill against baseline".

Use cases: documents, ml

Reviews

Write a review

No 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
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/skill-evaluator

What's inside

Skill name
skill-evaluator
Description
Evaluates a named skill by running its artifact checks and optionally invoking the skill against fixture inputs. Produces a structured eval report with deterministic structural checks (behave), LLM-as-judge qualitative checks, trigger routing checks, baseline comparison, and skill input size measurement. Use when asked to "evaluate a skill", "check skill output quality", "run evals for plan-it", "validate the dataviz skill", "measure skill input size", "check whether a skill triggers correctly", or "compare a skill against baseline".
License
unknown
Compatibility
Requires Python 3.11+, uv, claude CLI.
Metadata
domain: skill-evaluation · version: 1.0
Instructions
130 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (65)

  • SKILL.md
  • environment.py · evals/
  • eval_queries.json · evals/
  • invalid_missing_input_size.md · evals/fixtures/golden/
  • valid_report.md · evals/fixtures/golden/
  • report.feature · evals/
  • report_steps.py · evals/steps/
  • evaluator-rules.md · references/
  • python-quality.yml · runner/.semgrep/
  • Makefile · runner/
  • pyproject.toml · runner/
  • __init__.py · runner/runner/
  • __init__.py · runner/runner/adapters/
  • behave.py · runner/runner/adapters/
  • claude_code.py · runner/runner/adapters/
  • contract.py · runner/runner/adapters/
  • judge_payloads.py · runner/runner/adapters/
  • opencode.py · runner/runner/adapters/
  • discovery.py · runner/runner/
  • eval_layout.py · runner/runner/
  • evaluation.py · runner/runner/
  • exceptions.py · runner/runner/
  • invocation.py · runner/runner/
  • judging.py · runner/runner/
  • log_setup.py · runner/runner/
  • metrics.py · runner/runner/
  • models.py · runner/runner/
  • ports.py · runner/runner/
  • reporting.py · runner/runner/
  • run.py · runner/runner/
  • __init__.py · runner/runner/strategies/
  • _timing.py · runner/runner/strategies/
  • all.py · runner/runner/strategies/
  • compare.py · runner/runner/strategies/
  • invoke.py · runner/runner/strategies/
  • judge.py · runner/runner/strategies/
  • trigger.py · runner/runner/strategies/
  • trigger.py · runner/runner/
  • check_test_module_parity.py · runner/scripts/
  • test_behave.py · runner/tests/adapters/
  • test_claude_code.py · runner/tests/adapters/
  • test_contract.py · runner/tests/adapters/
  • test_judge_payloads.py · runner/tests/adapters/
  • test_opencode.py · runner/tests/adapters/
  • __init__.py · runner/tests/strategies/
  • test__timing.py · runner/tests/strategies/
  • test_all.py · runner/tests/strategies/
  • test_compare.py · runner/tests/strategies/
  • test_invoke.py · runner/tests/strategies/
  • test_judge.py · runner/tests/strategies/
  • test_trigger.py · runner/tests/strategies/
  • test_discovery.py · runner/tests/
  • test_eval_layout.py · runner/tests/
  • test_evaluation.py · runner/tests/
  • test_exceptions.py · runner/tests/
  • test_invocation.py · runner/tests/
  • test_judging.py · runner/tests/
  • test_log_setup.py · runner/tests/
  • test_metrics.py · runner/tests/
  • test_models.py · runner/tests/
  • …and 5 more

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from dmenezesgabriel/agent-harness

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 24, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
License unknown
Repository
github.com/dmenezesgabriel/agent-harness
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from dmenezesgabriel

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get skill-evaluator running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying skill-evaluator?

CallGet help
Cite this page

skill-evaluator. Agent Mart. https://agentmart.dev/skills/dmenezesgabriel-skill-evaluator (last updated 2026-10-24)