agentleFS
Sign inStart free
pablocaegpablocaeg/claude-army/skills/analyze/SKILL.md

analyze

Skill2 starsChanged 8 months agoMITView on GitHub

Analyze a project's codebase, PR review patterns, and conventions. Run this first before creating agents. Outputs a structured analysis that create-team uses.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use constitution, revise and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArvorCoSkill

    constitution

    Create or update the project constitution - personalized governance and coding principles. Use when starting a project or updating project standards. Triggers on: create constitution, update principles, set project rules.

    Also in 4 projects that use this

  • stormlightlabsSkill

    revise

    Address review comments on an open pull request and push the fixes. Use for /edit, /revise, or when asked to respond to review feedback on a PR number.

    Also in 3 projects that use this

  • DockerSkill

    write

    Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.

    Also in 6 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 5 projects that use this

  • H-mmerSkill

    submit

    Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.

    Also in 3 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • +1 more from ArvorCo

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read these files if they exist:

    line 11
  2. Distinctive:

    Test framework, assertion library, coverage requirements

    line 22
  3. Distinctive:

    Read 5-10 key source files for patterns

    line 28
  4. Distinctive:

    Read 5-10 test files for testing conventions

    line 29
  5. Very specific:

    Read everything in .context/ if it exists.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 60 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analyze the current project to prepare for agent team creation. Read everything relevant and produce a structured analysis.

Step 1: Project Foundation

Read these files if they exist:

  • README.md, CONTRIBUTING.md, CHANGELOG.md
  • .github/pull_request_template.md
  • .github/ISSUE_TEMPLATE/

Step 2: Tech Stack

Identify:

  • Language and version (go.mod, package.json, Cargo.toml, pyproject.toml, etc.)
  • Build system and commands
  • Linter config with exact rules
  • Test framework, assertion library, coverage requirements
  • CI/CD workflows (.github/workflows/)

Step 3: Code Patterns

  • Map directory structure with Glob
  • Read 5-10 key source files for patterns
  • Read 5-10 test files for testing conventions
  • Identify the extension/plugin/registration pattern (how new features are added)

Step 4: PR Review Analysis

Find the lead reviewer:

gh pr list --state all --limit 100 --json number,reviews --jq '.[].reviews[].author.login' 2>/dev/null | sort | uniq -c | sort -rn | head -5

Find external contributor PRs:

gh pr list --state all --limit 200 --json number,title,state,author --jq '.[] | "\(.number) [\(.state)] \(.author.login): \(.title)"' 2>/dev/null

For each external PR with lead reviewer feedback, extract BOTH:

PR-level reviews:

gh api repos/OWNER/REPO/pulls/NUMBER/reviews --jq '.[] | select(.user.login == "REVIEWER") | .body' 2>/dev/null

Inline code comments:

gh api repos/OWNER/REPO/pulls/NUMBER/comments --jq '.[] | select(.user.login == "REVIEWER") | "FILE: \(.path):\(.line // .original_line)\nCOMMENT: \(.body[:400])"' 2>/dev/null

Analyze at least 15-20 PRs. Rank reviewer patterns by frequency into tiers.

Step 5: Context Folder

Read everything in .context/ if it exists.

Output

Save the analysis to .context/forge-analysis.md with these sections:

# Forge Analysis: [Project Name]

## Tech Stack
[language, build, linter, test framework, CI]

## Code Patterns
[file structure, naming conventions, registration pattern]

## Test Conventions
[package naming, assertion library, fixture patterns, coverage requirement]

## PR Review Patterns
### Lead Reviewer: [name]
### Tier 1 (50%+ of PRs)
[patterns with exact quotes]
### Tier 2 (25-50%)
[patterns with exact quotes]
### Tier 3 (10-25%)
[patterns with exact quotes]
### Things NOT to Flag
[verified false positives]

## PR Format
[title format, body structure, checklist]

## Contribution Type
[what external contributors typically add]

## Build/Generate Commands
[commands that must run before submitting]

Tell the user the analysis is complete and they can run /claude-army:create-team next.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free