Claim Grader — Data & AI agent for Claude Code
Use when a contributor wants a soft-gate review of a commit message, PR body, sprint section, or journal entry — specifically asking "is this honest about what was actually done.
How to install Claim Grader
Installs to ~/.claude/agents/citratenetwork-agentile-claim-grader.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/CitrateNetwork/agentile/HEAD/.claude/agents/claim-grader.md -o ~/.claude/agents/citratenetwork-agentile-claim-grader.md Restart Claude Code, or start a new session, for it to be picked up.
What Claim Grader does
name: claim-grader description: Use when a contributor wants a soft-gate review of a commit message, PR body, sprint section, or journal entry — specifically asking "is this honest about what was actually done?" Runs the AI claim grader and interprets the output. Do not use for general writing review — only for claim-compression detection. tools: Bash, Read
You are an interpreter for the AI claim grader. The user wants to know whether a piece of text commits "claim compression": describ
Alternatives in Data & AI
- Read Research For Nyquist Validation Data — cat "$phase_dir"/-RESEARCH.md 2>/dev/null node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-pha 38.5k ★
- Comprehension Review — De-warmed cold comprehension-and-structure gate for design.md and track files: reads only the document, never 432 ★
- Prose Review — Reviews prose for AI patterns, banned phrases, voice drift, and structural issues 70 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Figure Critic
Reviews a generated or existing figure (data plot or diagram) against figure-quality rules before it goes in t
Reconciler
Close open tasks that are already done, by matching them against evidence across ALL channels (Gmail sent/inbo
Reviewer Methodology
Peer reviewer for methodological rigor. Checks arithmetic consistency, mock data use, reproducibility, and hon
LLM Provider Compat Reviewer
SkillForge LLM provider 兼容性专项 reviewer。对 skillforge-core/llm/ / ClaudeProvider / OpenAiProvider / ProviderProt
Askit Quality Grader
Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outpu
GPT Advisor
Obtains an independent GPT opinion on a disputed technical decision and provides an honest synthesis of the tw
Related Skills
Claim Grade
Run the AI claim grader on a piece of text — commit message, PR body, or sprint section
Accessibility
Read CLAUDE.md in this repo — specifically the Coding Conventions section on Accessibility.
Comfy Rickroll
The user wants to be rick rolled. Do it immediately without asking for confirmation.