Agent skill

Review Skills

by mrinalwadhwa in mrinalwadhwa/fluent

Reviews Agent Skills. An agent skill from mrinalwadhwa/fluent.

Apache-2.0Auto-check passed

Install Review Skills

skills CLI
$ npx skills add mrinalwadhwa/fluent --skill review-skills -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mrinalwadhwa/fluent review-skills --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mrinalwadhwa/fluent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/review-skills .claude/skills/review-skills && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-skills
GitHub stars
111
Token cost
~511 tokens
SKILL.md length
262 words
Files
3 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reviews Agent Skills. An agent skill from mrinalwadhwa/fluent.

  • Works in 3 steps: Read references/skills.md for… → For each skill under review → For each improvement, decide if it…
  • Auditing skills in a codebase
  • SKILL.md covers Purpose, Scope and Method
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review Skills is an agent skill from mrinalwadhwa/fluent. Reviews Agent Skills. Use when auditing skills in a codebase, checking a new or edited SKILL.md, or verifying that a skill follows the Agent Skills spec.

Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/documentation.md` and `references/skills.md`).

The repository describes itself as: Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software. The licence is Apache-2.0.

When your agent uses it

  • Auditing skills in a codebase
  • Edited SKILL.md
  • Verifying that a skill follows the Agent Skills spec

Example prompts

  • “Use the review-skills skill to review Agent Skills. An agent skill from mrinalwadhwa/fluent”
  • “/review-skills”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Read references/skills.md for skill-writing standards and references/documentation.md for writing quality.
  2. For each skill under review
  3. For each improvement, decide if it blocks shipping. Missing or invalid frontmatter, broken references, or instructions that contradict the…

What it can do on your machine

Read from SKILL.md and the folder at commit be19732. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Skills loads about 511 tokens when it runs, and up to ~527 if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~511
With references · SKILL.md plus every file in references/, read only if the agent opens them
~527

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mrinalwadhwa/fluent at commit be19732, republished under its Apache-2.0 licence (© mrinalwadhwa). 262 words, ~511 tokens.

Download SKILL.mdSave it as .claude/skills/review-skills/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
review-skills
description
Reviews Agent Skills. Use when auditing skills in a codebase, checking a new or edited SKILL.md, or verifying that a skill follows the Agent Skills spec.

Purpose

Decide whether each skill under review is fit to ship. Identify improvements that would make a skill more discoverable, more efficient, or more likely to succeed at its purpose.

Scope

The invoking layer decides which skills to review: the changed skills for a diff-scoped review, or all skills for a full-codebase audit.

For each skill in scope, assess it as a whole: the SKILL.md, its supporting files under references/, scripts/, and assets/, and how the skill is invoked in its codebase. Skills can be invoked by name from a prompt template, through a hook, or by agent auto-activation.

When an agent picks among skills based on their descriptions, an overlap can cause it to pick the wrong one. Compare each in-scope skill's description against sibling skills invoked the same way, including siblings that aren't part of this review.

Method

  1. Read references/skills.md for skill-writing standards and references/documentation.md for writing quality.

  2. For each skill under review:

    • Read the SKILL.md and files under references/, scripts/, and assets/.
    • Understand how the skill is invoked in its codebase — by name from a prompt template, through a hook, or by agent auto-activation.
    • Compare descriptions against siblings invoked the same way.
    • Identify improvements using the standards in references/skills.md (skill-writing) and references/documentation.md (writing quality).
  3. For each improvement, decide if it blocks shipping. Missing or invalid frontmatter, broken references, or instructions that contradict the invoking layer's specifications (output format, error handling) typically block. Lighter versions — a vague but present description, load triggers that could be sharper, duplication that's aligned rather than conflicting — and style issues typically don't.

© mrinalwadhwa, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/review-skills of mrinalwadhwa/fluent.

  • SKILL.md
  • references/documentation.md
  • references/skills.md

Open the folder on GitHubat commit be19732

Compare with similar skills

Review Skills next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Skills this skillmrinalwadhwa/fluent111—~511Automated safety check: PassApache-2.0
Production Auditaffaan-m/ECC277k1 repos~1.9kAutomated safety check: PassMIT
Audited Boundary Checkmohitagw15856/pm-claude-skills1.4k—~1.8kAutomated safety check: PassMIT
Audit Dependenciespayloadcms/payload45k—~2.8kAutomated safety check: PassMIT
Aims Auditalirezarezvani/claude-skills28k—~1.3kAutomated safety check: PassMIT
Soroban Contract Auditsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Production Audit

    affaan-m/ECC

    Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions without sending repo data to an external audit service.

    277k GitHub starsUsed in 1 repo~1.9k tokens
    Product & Project ManagementAuto-check passed
  • Audited Boundary Check

    mohitagw15856/pm-claude-skills

    A skill your agent uses when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is…

    1.4k GitHub stars~1.8k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Audit Dependencies

    payloadcms/payload

    A skill your agent uses when fixing dependency vulnerabilities, running pnpm audit, or when the audit-dependencies CI check fails

    45k GitHub stars~2.8k tokensUpdated yesterday
    SecurityAuto-check passed
  • Aims Audit

    alirezarezvani/claude-skills

    /cs:aims-audit <scope — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation.

    28k GitHub stars~1.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Soroban Contract Audit

    sickn33/agentic-awesome-skills

    Soroban smart contract security audit register: authorization checks, panic pathways, integer overflows, and storage footprint verification for Stellar.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    SecurityAuto-check passed
  • Geo Audit

    sickn33/agentic-awesome-skills

    Full website GEO+SEO audit with parallel subagent delegation.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Marketing & SEOAuto-check: notes

More from mrinalwadhwa/fluent

  • Review Documentation

    mrinalwadhwa/fluent

    Reviews the accuracy and writing quality of documentation. An agent skill from mrinalwadhwa/fluent.

    111 GitHub stars~666 tokensUpdated today
    Auto-check passed
  • Review Architecture

    mrinalwadhwa/fluent

    Reviews the structural quality of code. An agent skill from mrinalwadhwa/fluent.

    111 GitHub stars~394 tokensUpdated today
    Auto-check passed
  • Review Behaviors

    mrinalwadhwa/fluent

    Reviews the quality and coherence of behavior statements. An agent skill from mrinalwadhwa/fluent.

    111 GitHub stars~428 tokensUpdated today
    Auto-check passed
  • Review Tests

    mrinalwadhwa/fluent

    Reviews test quality and coverage. An agent skill from mrinalwadhwa/fluent.

    111 GitHub stars~414 tokensUpdated today
    Auto-check passed

Questions about Review Skills

What does Review Skills do?

Reviews Agent Skills. An agent skill from mrinalwadhwa/fluent. Review Skills is an agent skill from mrinalwadhwa/fluent. Reviews Agent Skills.

When should I use Review Skills?

Review Skills fits situations like: auditing skills in a codebase; edited SKILL.md; verifying that a skill follows the Agent Skills spec.

How do I install Review Skills in Claude Code?

Run `npx skills add mrinalwadhwa/fluent --skill review-skills -a claude-code`. Or copy the skill folder (skills/review-skills in mrinalwadhwa/fluent) into .claude/skills/review-skills in your project. Claude Code loads it when a task matches its description.

How do I install Review Skills in Codex?

Run `npx skills add mrinalwadhwa/fluent --skill review-skills -a codex`. Or copy the skill folder (skills/review-skills in mrinalwadhwa/fluent) into .agents/skills/review-skills in your project. Codex loads it when a task matches its description.

Can I use Review Skills in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mrinalwadhwa/fluent --skill review-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-skills, .gemini/skills/review-skills, .github/skills/review-skills and .opencode/skills/review-skills in your project.

What does Review Skills need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Skills is instructions for the agent only.

Does Review Skills access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Skills safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review Skills use?

Review Skills is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Skills use?

About 511 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16 tokens, read only when the agent opens those files.

What are the alternatives to Review Skills?

Skills that share tags, products or a category with Review Skills: Production Audit (affaan-m/ECC, 277k stars), Audited Boundary Check (mohitagw15856/pm-claude-skills, 1.4k stars), Audit Dependencies (payloadcms/payload, 45k stars) and Aims Audit (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Skills?

mrinalwadhwa (a GitHub user) maintains it in mrinalwadhwa/fluent, which has 111 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.

Source: mrinalwadhwa/fluent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.