Claimcheck Run — Development skill for Claude Code
Run a claimcheck A/B evaluation comparing tool policies on a real agent CLI.
How to install Claimcheck Run
Installs to ~/.claude/skills/pawankumar94-claimcheck-claimcheck-run/SKILL.md
mkdir -p ~/.claude/skills/pawankumar94-claimcheck-claimcheck-run && curl -fsSL https://raw.githubusercontent.com/pawankumar94/claimcheck/HEAD/commands/claimcheck-run.md -o ~/.claude/skills/pawankumar94-claimcheck-claimcheck-run/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Claimcheck Run does
description: Run a claimcheck A/B evaluation comparing tool policies on a real agent CLI argument-hint: "[agent] [example] [--trials N]"
Run a claimcheck evaluation and report whether the tool-policy difference is real.
Arguments the user gave: `$ARGUMENTS` (may be empty).
Steps:
Call the `list_agent_profiles` MCP tool to see which agent profiles are available, which policies each supports, and which example task sets ship with the package. Do not guess these names.
Deci
Alternatives in Development
- Privacy Policy — Draft privacy policies with GDPR compliance considerations 7.8k ★
- Hive — Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real 473 ★
- Quick Eval — Quick job evaluation 473 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Mark Profiler
Deep company evaluation for a career decision. Scored dimensions, the real day-to-day role, 12 to 24 month tra
Clojure Skills
Claude Code / Gemini CLI / Codex skill for Clojure development — parenthesis repair, nREPL evaluation, clojure
Skill Evaluation Graph
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claud
Claimcheck Agents
List the coding agents claimcheck can measure, and what has actually been verified
Claude Code CLI Acp
ACP adapter for the real Claude Code CLI: Rust PTY bridge for Zed and other Agent Client Protocol clients.
Cursor2api
Use your Cursor subscription as an OpenAI-compatible API. Direct agent.v1 protocol — real tool_calls, streamin
Related Agents
Risk Engine
Use this agent proactively whenever code changes are made that could affect risk policies, evaluation logic, s
Evaluation Guidance Checker
Checks whether the agency policies, evaluation guidance and donor requirements cited in the evaluation-questio
Karen
Verify claims that a task, fix, feature, or project is complete by exercising the real path and comparing obse