Skip to content
Agentmart
Submit a tool

review-skills

Review ShakerScan skills, commands, and subagents for broken references, invalid Claude Code configuration, prompt anti-patterns, missing hard gates, missing…

Skill by andriyze

IndexedAGPL-3.0
Write a review

Chalk Labs

Need help deploying review-skills?

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/andriyze-review-skills

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

Review ShakerScan skills, commands, and subagents for broken references, invalid Claude Code configuration, prompt anti-patterns, missing hard gates, missing outputs, and weak operational guidance. Use when asked to audit, review, or quality-check the skill system itself.

Use cases: security, agent-building

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/review-skills

What's inside

Skill name
review-skills
Description
Review ShakerScan skills, commands, and subagents for broken references, invalid Claude Code configuration, prompt anti-patterns, missing hard gates, missing outputs, and weak operational guidance. Use when asked to audit, review, or quality-check the skill system itself.
License
AGPL-3.0
Instructions
60 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Review Skills

Use this skill to review the entire ShakerScan skill and command surface like a code review, not as a lightweight summary.

## Scope

Review all of these unless the user explicitly narrows scope:

- `skills/*.md`
- `skills/**/SKILL.md`
- `skills/**/references/*`
- `skills/**/agents/openai.yaml`
- `.claude/commands/*.md`
- `.claude/agents/*.md`

## Review Goals

Look for:

- broken or stale file references
- unsupported or risky Claude Code frontmatter
- contradictory instructions across skills, commands, and agents
- prompt wording that increases false positives or weakens evidence standards
- missing machine-usable outputs
- missing fallback behavior
- missing checklists or hard gates for long tasks
- poor model/tool selection for the intended workload

## Mandatory Checklist

Maintain this checklist in markdown while you work. Do not move on to synthesis or a final answer until every item is `[x]` or `[n/a]` with a short reason.

- [ ] Enumerate all in-scope skill, command, and agent files
- [ ] Read every in-scope skill file
- [ ] Read every in-scope command file
- [ ] Read every in-scope agent file
- [ ] Verify references between files resolve correctly
- [ ] Verify frontmatter fields are supported and coherent
- [ ] Verify each skill has a clear workflow, outputs, fallbacks, and guardrails
- [ ] Verify long-task checklist and hard-gate behavior where needed
- [ ] Produce findings ordered by severity with file references

## Output

Return:

1. Findings first, ordered by severity, with file references.
2. Open questions or assumptions.
3. A short change summary or health summary.

If there are no issues, say so clearly and still note any residual risk or test gaps.

## Rules

- Review behavior, not branding.
- Prefer concrete failures over stylistic nits.
- If a prompt is likely to create fabricated findings, call that out explicitly.
- Do not move on until the checklist is complete.

From andriyze/shakerscan, AGPL-3.0.

Signals

Stars
0
Forks
0
Open issues
5
Last commit (this folder)
Jul 17, 2026 (3 months ago)
Last release
Oct 18, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from andriyze

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 review-skills 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 review-skills?

CallGet help
Cite this page

review-skills. Agent Mart. https://agentmart.dev/skills/andriyze-review-skills (last updated 2026-10-24)