Triage Critic — Development agent for Claude Code
Independently grades a submittal/RFI triage brief PDF against the source package and returns a 1-10 score with row-level findings.
How to install Triage Critic
Installs to ~/.claude/agents/sow2754-submittal-rfi-triage-triage-critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/SOW2754/submittal-rfi-triage/HEAD/agents/triage-critic.md -o ~/.claude/agents/sow2754-submittal-rfi-triage-triage-critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Triage Critic does
name: triage-critic description: Independently grades a submittal/RFI triage brief PDF against the source package and returns a 1-10 score with row-level findings. Use after generating a triage brief, before handing it to anyone. tools: Read, Glob, Grep, Bash model: opus
You grade submittal and RFI triage briefs for an MEP engineering firm. You did not write the brief and you owe it nothing.
First, read the rubric and apply it exactly as written:
`~/.claude/skills/submittal-rfi-triage
Alternatives in Development
- Cs Guardian — Customer success partner for account health, churn risk, renewals, escalations, and QBRs 1.3k ★
- Verify Claim Faithfulness — A verification agent that independently checks, at the sentence level, whether each cited source actually SUPP 134 ★
- Auth Engineer — Authentication and access-control specialist for SMB Product-Builder products 83 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Question Answerer
Draft an application's free-text answers from the user's real resume, the JD brief, and the fit report, handin
Scoring
Score a Notion lead row against the user-editable scoring schema. Reads schema tab + enriched lead, computes w
Sme Eval Triage
Triage a golden-set failure from the compliance-SME seat before anyone edits ground truth. Use whenever make e
Cha Adjudicator
Settles review claims by executing them and returns true / false-with-counter-evidence / unmeasurable. Use whe
Run Triage
Reads a failed run's artifacts and returns an environment-vs-automation-vs-product verdict before anyone re-ru
LinkedIn Post Reviewer
Reviews a LinkedIn post draft against the quality checklist. Grades A/B/C/D. Returns specific violations with
Related Skills
Audit Updates
Triage pnpm audit findings and produce a prioritized, supply-chain-cautious package-update plan, then apply ap
Evaluator
Use when the user invokes /evo:evaluator or asks to evaluate, assess, score, or independently audit code quali
Craft Research Verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree