Skip to content
Agentmart
Submit a tool

critic

Verification-first habit for brayness.

Skill by scott-fryxell

IndexedMIT★ 125
Write a review

Chalk Labs

Need help deploying critic?

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/scott-fryxell-critic

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

Verification-first habit for brayness. Run cheap deterministic checks before expensive or final steps; never let the producer grade its own homework. Use on every task before calling work done - structural checks (does it build, do the tests pass, is the expected item present) before any LLM judge, cost-heavy review, or user sign-off.

Use cases: ml, productivity

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

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/critic

What's inside

Skill name
critic
Description
Verification-first habit for brayness. Run cheap deterministic checks before expensive or final steps; never let the producer grade its own homework. Use on every task before calling work done - structural checks (does it build, do the tests pass, is the expected item present) before any LLM judge, cost-heavy review, or user sign-off.
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Critic

Most errors are caught by cheap checks. Order all verification cheapest-first so expensive confidence only runs on survivors.

## Hierarchy

1. **Deterministic / structural** (free, always run): does it build, does `npm run test` pass, is the expected output actually present, did the file write. Check the thing the task promised, programmatically where possible.
2. **Cheap review**: read your own diff/output once, against the goal, and state plainly what is missing or wrong.
3. **Expensive judgment** (only if the cheap tiers passed): LLM-style quality review, cross-checking choices, art direction. Spend tokens only on survivors.

## Rules

- Always run the cheap tier first; a failing cheap check is the next thing to fix.
- The producer never grades its own homework - for anything that matters, review from evidence, not from intent.
- If an expensive check would be skipped under pressure, say so instead of quietly dropping verification.
- One failing check is a reason to stop and fix, not to proceed and note it.

From scott-fryxell/brayness, MIT.

More from scott-fryxell/brayness

Signals

Stars
125
Forks
15
Open issues
0
Last commit (this folder)
Aug 22, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/scott-fryxell/brayness
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from scott-fryxell

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 critic 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 critic?

CallGet help
Cite this page

critic skill. Agent Mart. https://agentmart.dev/skills/scott-fryxell-critic (last updated 2026-10-24)