Agent skill

Review Behaviors

by mrinalwadhwa in mrinalwadhwa/fluent

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

Apache-2.0Auto-check passed

Install Review Behaviors

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

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

GitHub CLI
$ gh skill install mrinalwadhwa/fluent review-behaviors --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-behaviors .claude/skills/review-behaviors && 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-behaviors
GitHub stars
111
Token cost
~428 tokens
SKILL.md length
203 words
Files
2 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 4 steps: Read references/behaviors.md for… → For each in-scope behavior statement → Check the collection for coherence —… → …
  • Reviewing behavior changes in a diff
  • SKILL.md covers Purpose, Scope and Method
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review Behaviors is an agent skill from mrinalwadhwa/fluent. Reviews the quality and coherence of behavior statements. Use when reviewing behavior changes in a diff, checking a new or edited behavior statement, or auditing the behavior statements of a codebase.

Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/behaviors.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

  • Reviewing behavior changes in a diff
  • Edited behavior statement
  • Auditing the behavior statements of a codebase

Example prompts

  • “Use the review-behaviors skill to review the quality and coherence of behavior statements. An agent skill from mrinalwadhwa/fluent”
  • “/review-behaviors”

Workflow steps

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

  1. Read references/behaviors.md for behavior-writing standards.
  2. For each in-scope behavior statement
  3. Check the collection for coherence — vocabulary consistency, contradictions, coverage, and redundancy — using the "Coherence across…
  4. For each improvement, decide if it blocks shipping. Statements that leak implementation, combine multiple behaviors, or lack a way to…

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 Behaviors loads about 428 tokens when it runs, and up to ~436 if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~428
With references · SKILL.md plus every file in references/, read only if the agent opens them
~436

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). 203 words, ~428 tokens.

Download SKILL.mdSave it as .claude/skills/review-behaviors/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review-behaviors
description
Reviews the quality and coherence of behavior statements. Use when reviewing behavior changes in a diff, checking a new or edited behavior statement, or auditing the behavior statements of a codebase.

Purpose

Decide whether the behavior statements under review are fit to ship. Identify improvements that would make each statement more precise about what the system does, or the collection more coherent and complete as a whole.

Scope

The invoking layer decides what's in scope. For a diff-scoped review, that's the behavior statements changed in the diff. For a full-codebase audit, that's the entire set of behavior statements. Check each statement for quality and check the collection for coherence and completeness.

Method

  1. Read references/behaviors.md for behavior-writing standards.

  2. For each in-scope behavior statement:

    • Verify it uses one of the six EARS patterns from references/behaviors.md. Statements without a recognized trigger (WHEN, WHILE, IF, WHERE) or without "THE SYSTEM SHALL" are hard to verify.
    • Evaluate against the "Properties of a good behavior statement" and "What not to specify" sections in references/behaviors.md.
    • Identify improvements.
  3. Check the collection for coherence — vocabulary consistency, contradictions, coverage, and redundancy — using the "Coherence across behavior statements" section of references/behaviors.md.

  4. For each improvement, decide if it blocks shipping. Statements that leak implementation, combine multiple behaviors, or lack a way to verify typically block. Style issues and minor phrasing don't.

The invoking layer may add checks in addition to those above.

© 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 1 other file (references) in skills/review-behaviors of mrinalwadhwa/fluent.

  • SKILL.md
  • references/behaviors.md

Open the folder on GitHubat commit be19732

Compare with similar skills

Review Behaviors 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 Behaviors compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Behaviors this skillmrinalwadhwa/fluent111—~428Automated safety check: PassApache-2.0
Three-Statement Financial AnalysisHKUDS/Vibe-Trading35k—~1.2kAutomated safety check: PassMIT
Behavioral Finance for TradingHKUDS/Vibe-Trading35k—~2.7kAutomated safety check: PassMIT
Detecting Mobile Malware Behaviormukul975/Anthropic-Cybersecurity-Skills34k—~2.2kAutomated safety check: PassApache-2.0
Change Spf Behaviorvideojs/video.js40k—~451Automated safety check: PassCustom licence
Create Spf Behaviorvideojs/video.js40k—~389Automated safety check: PassCustom licence

Similar skills

  • Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text.

    35k GitHub stars~1.2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Turns behavioral-finance theory into trading signals and risk rules: overreaction and underreaction, momentum and reversal, sentiment extremes and a cognitive-bias checklist.

    35k GitHub stars~2.7k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Detecting Mobile Malware Behavior

    mukul975/Anthropic-Cybersecurity-Skills

    Detects and analyzes malicious behavior in mobile applications through behavioral analysis, permission abuse detection, network traffic monitoring, and dynamic instrumentation.

    34k GitHub stars~2.2k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Change Spf Behavior

    videojs/video.js

    Change SPF playback-engine behaviors. An agent skill from videojs/video.js.

    40k GitHub stars~451 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Create Spf Behavior

    videojs/video.js

    Create or extract one SPF playback-engine behavior. An agent skill from videojs/video.js.

    40k GitHub stars~389 tokensUpdated yesterday
    Auto-check passed
  • Official

    Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later.

    40k GitHub stars~2.7k tokensUpdated yesterday
    DevelopmentAuto-check passed

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 Skills

    mrinalwadhwa/fluent

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

    111 GitHub stars~511 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 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 Behaviors

What does Review Behaviors do?

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

When should I use Review Behaviors?

Review Behaviors fits situations like: reviewing behavior changes in a diff; edited behavior statement; auditing the behavior statements of a codebase.

How do I install Review Behaviors in Claude Code?

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

How do I install Review Behaviors in Codex?

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

Can I use Review Behaviors 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-behaviors -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-behaviors, .gemini/skills/review-behaviors, .github/skills/review-behaviors and .opencode/skills/review-behaviors in your project.

What does Review Behaviors need to run?

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

Does Review Behaviors 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 Behaviors 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 Behaviors use?

Review Behaviors 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 Behaviors use?

About 428 tokens (SKILL.md is roughly 1.7k 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 8 tokens, read only when the agent opens those files.

What are the alternatives to Review Behaviors?

Skills that share tags, products or a category with Review Behaviors: Three-Statement Financial Analysis (HKUDS/Vibe-Trading, 35k stars), Behavioral Finance for Trading (HKUDS/Vibe-Trading, 35k stars), Detecting Mobile Malware Behavior (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Change Spf Behavior (videojs/video.js, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Behaviors?

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.