New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Methodology Advisor

by FlorianBruniaux in FlorianBruniaux/claude-code-ultimate-guide

Reads a codebase silently, asks only what it cannot infer, and recommends one AI-assisted development methodology stack with a contextual quick start.

CC-BY-SA-4.0Auto-check passedAgent Workflows

Install Methodology Advisor

skills CLI
$ npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill source-command-methodology-advisor -a claude-code

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

GitHub CLI
$ gh skill install FlorianBruniaux/claude-code-ultimate-guide source-command-methodology-advisor --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/FlorianBruniaux/claude-code-ultimate-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/source-command-methodology-advisor .claude/skills/source-command-methodology-advisor && 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
source-command-methodology-advisor
GitHub stars
6.1k
Token cost
~1.9k tokens
SKILL.md length
652 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
CC-BY-SA-4.0

At a glance

Reads a codebase silently, asks only what it cannot infer, and recommends one AI-assisted development methodology stack with a contextual quick start.

  • Works in 4 steps: Silent codebase analysis → Score the 8 stacks → Ask only what you cannot infer → …
  • Choosing a methodology for AI-assisted work on a new or inherited project
  • SKILL.md covers Command Template, Phase 1 — Silent codebase…, Phase 2 — Score the 8 stacks and Phase 3 — Ask only what you…, plus 2 more sections
  • Calls git

What it does

This skill wraps a migrated command that takes two to four minutes. Its first phase is a silent analysis of the repository, with nothing printed yet: project identity from AGENTS.md and package.json, team size from unique contributors over the last 90 days and total commits, test maturity from the number of test files, spec and documentation signals such as spec, design, ADR and RFC files, codebase size and structure, and signs of LLM use such as imports of AI libraries.

The second phase scores eight stacks from 0 to 10 against those signals. Named in the visible text are solo-mvp (one contributor, few files, no CI), team-greenfield (new project with 2 to 10 contributors), microservices (packages, services, OpenAPI or proto files), brownfield-saas (many commits and files with few tests), enterprise-gov (10 or more contributors, CI, ADRs) and llm-native. The agent asks three targeted questions, and its output is a single recommended stack plus a quick start suited to the project.

When your agent uses it

  • Choosing a methodology for AI-assisted work on a new or inherited project
  • Matching the process to team size, test maturity and documentation habits
  • Getting a short quick start tailored to your repository

Example prompts

  • “Run the methodology advisor on this repo.”
  • “Which AI-assisted development stack fits our five-person team and large legacy codebase?”
  • “We are starting a greenfield microservices project; recommend a methodology and a quick start.”

Requirements

  • A git repository to analyze

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Silent codebase analysis
  2. Score the 8 stacks
  3. Ask only what you cannot infer
  4. Recommendation

What it can do on your machine

Read from SKILL.md and the folder at commit 585c203. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    Links to these hosts (documentation or services it may open):

    • cc.bruniaux.com

    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

Methodology Advisor loads about 1.9k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 652 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 FlorianBruniaux/claude-code-ultimate-guide at commit 585c203, republished under its CC-BY-SA-4.0 licence (© FlorianBruniaux). 652 words, ~1,904 tokens.

Download SKILL.mdSave it as .claude/skills/source-command-methodology-advisor/SKILL.md (or your agent's skills folder).
name
source-command-methodology-advisor
description
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack

source-command-methodology-advisor

Use this skill when the user asks to run the migrated source command methodology-advisor.

Command Template

Methodology Advisor

Analyze this project and recommend the best AI-assisted development methodology stack. Read what you can from the codebase first, then ask only what you cannot infer.

Time: 2-4 minutes | Output: One recommended stack + contextual quick start

Phase 1 — Silent codebase analysis

Run these reads silently. Do not output results yet — build an internal picture only.

1.1 Project identity
bash
# Config files
cat AGENTS.md 2>/dev/null || cat AGENTS.md 2>/dev/null
cat package.json 2>/dev/null | grep -E '"name"|"description"|"scripts"' | head -10
cat Cargo.toml 2>/dev/null | grep -E '^name|^description' | head -5
cat pyproject.toml 2>/dev/null | grep -E '^name|^description' | head -5
cat go.mod 2>/dev/null | head -3
1.2 Team size
bash
# Unique contributors in last 90 days
git log --since="90 days ago" --format="%ae" 2>/dev/null | sort -u | wc -l
# Total commits
git log --oneline 2>/dev/null | wc -l
1.3 Test maturity
bash
# Test files exist?
find . -name "*.test.*" -o -name "*.spec.*" -o -name "*_test.*" -o -name "test_*.py" \
  2>/dev/null | grep -v node_modules | grep -v ".git" | wc -l
# Test framework hints
grep -rn --include="*.json" --include="*.toml" --include="*.yaml" \
  -l "jest\|vitest\|pytest\|rspec\|mocha\|cypress\|playwright" \
  2>/dev/null | grep -v node_modules | head -5
# CI config
ls .github/workflows/*.yml 2>/dev/null | wc -l
ls .gitlab-ci.yml .circleci/config.yml 2>/dev/null | wc -l
1.4 Spec and documentation signals
bash
# Spec files
find . -name "*.spec.md" -o -name "SPEC*.md" -o -name "spec.md" -o -name "DESIGN*.md" \
  -o -name "ADR*.md" -o -name "RFC*.md" \
  2>/dev/null | grep -v node_modules | grep -v ".git" | head -10
# OpenAPI / contract files
find . -name "openapi*.yaml" -o -name "openapi*.json" -o -name "swagger*.yaml" \
  -o -name "*.proto" \
  2>/dev/null | grep -v node_modules | head -5
# BDD feature files
find . -name "*.feature" 2>/dev/null | grep -v node_modules | wc -l
1.5 Codebase size and structure
bash
# File count (rough)
find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.py" \
  -o -name "*.rs" -o -name "*.go" -o -name "*.java" -o -name "*.rb" \) \
  2>/dev/null | grep -v node_modules | grep -v ".git" | wc -l
# Services / packages (monorepo signal)
ls packages/ apps/ services/ 2>/dev/null | head -10
1.6 AI and LLM signals
bash
# LLM API usage in code
grep -rn --include="*.ts" --include="*.py" --include="*.js" \
  -l "anthropic\|openai\|groq\|mistral\|langchain\|llm\|ChatCompletion\|Codex" \
  2>/dev/null | grep -v node_modules | grep -v ".git" | head -5
# Eval framework hints
find . -name "evals*" -o -name "*eval*" -type d 2>/dev/null | grep -v node_modules | head -5

Phase 2 — Score the 8 stacks

Using what you found, score each stack 0-10 based on fit signals:

StackKey signals that boost the score
solo-mvp1 contributor, few files, no CI yet, greenfield
team-greenfield2-10 contributors, new project, no legacy files
microservicespackages/, services/, OpenAPI files, .proto
brownfield-saasHigh commit count, large file count, few test files
enterprise-gov10+ contributors, CI, ADR files, AGENTS.md
llm-nativeLLM imports, eval dirs, AI product signals
power-solo1 contributor, high commit rate, iterative commits
plan-moderateMixed signals, AGENTS.md present, moderate size

Phase 3 — Ask only what you cannot infer

After the silent analysis, present your preliminary picture to the user in 2-3 lines, then ask exactly 3 questions. No more.

Format:

From your codebase I can see: [2-3 concrete observations].
Before recommending, 3 quick questions:

1. [Pain point question — pick the most relevant from below]
2. [Deploy frequency — if not inferable from CI/CD signals]
3. [Setup appetite — how much ceremony are you willing to invest?]

Question bank — pick the 3 most relevant given what you found:

  • Pain: "What slows you down most right now — regressions, unclear requirements, context rot between sessions, or no traceability?"
  • Pain: "When Codex generates a large chunk of code, what is your biggest worry — quality, drift from spec, or losing track of what was built?"
  • Deploy: "How often do you ship to production — multiple times a day, weekly, or on longer release cycles?"
  • Deploy: "Is this a product with real users today, a prototype, or an internal tool?"
  • Governance: "How much initial setup are you willing to invest — none (just start), 30 minutes, or half a day?"
  • Governance: "Does anyone outside your dev team (PM, QA, compliance) need to validate what gets built?"
  • AI product: "Does your product expose AI-generated outputs directly to end users?"
  • Scale: "Do multiple services or teams need to agree on API contracts before implementing?"

Phase 4 — Recommendation

Output the recommendation in this structure:

Show full SKILL.md (279 more words)Show less
Your Stack: [Stack Name] [icon]

Why this fits your project:

  • [Finding from Phase 1] → [explains this stack choice]
  • [Finding from Phase 1] → [explains this stack choice]
  • [Answer to question N] → [explains this stack choice]

Methodologies included: [Method A] + [Method B] (+ [Method C] if applicable)

What this looks like in practice: [2-3 sentences describing the concrete workflow for THIS project, using actual file names or paths found.]

Quick start for your project:

  1. [Concrete first step using actual project context]
  2. [Second step]
  3. [Third step]

Before you start, note:

  • [One honest trade-off or limitation of this stack]
  • [One thing to watch out for given what you found]

Go deeper: https://cc.bruniaux.com/methodologies/ — interactive quiz and full stack comparison Full methodology guide: https://cc.bruniaux.com/guide/methodologies/

Stack reference (internal)

Use this to map your scoring to quick-start language:

solo-mvp (SDD + TDD): Write feature spec in AGENTS.md → "Write failing tests for this spec, then implement until green."

team-greenfield (Spec Kit + TDD + BDD): /speckit.constitution → Given/When/Then scenarios with PM → TDD each scenario.

microservices (CDD + Specmatic + TDD): Write OpenAPI spec first → Specmatic for contract tests → TDD implementation.

brownfield-saas (OpenSpec + BDD + JiTTesting): OpenSpec captures current state → BDD for changed behavior → pre-merge: "Generate tests that catch regressions in this diff."

enterprise-gov (BMAD + Spec Kit + Specmatic): constitution.md → agent role definitions → Spec Kit requirements → Specmatic contract enforcement.

llm-native (Eval-Driven + Multi-Agent): Define eval criteria (accuracy, safety, format) → build eval harness → iterate until evals pass.

power-solo (TDD + Ralph Loop + Iterative): Tight test loop → fresh context per task via git stash + progress files → "Keep iterating until all tests pass and lint is clean."

plan-moderate (Plan-First + SDD + Context Engineering): Every complex task starts in Plan Mode (Shift+Tab) → validate → write spec in AGENTS.md → execute with progressive context loading.

© FlorianBruniaux, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/source-command-methodology-advisor of FlorianBruniaux/claude-code-ultimate-guide.

Open the folder on GitHubat commit 585c203

Compare with similar skills

Methodology Advisor 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.

Methodology Advisor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Methodology Advisor this skillFlorianBruniaux/claude-code-ultimate-guide6.1k—~1.9kAutomated safety check: PassCC-BY-SA-4.0
Readyprekuter/dryforge4101 repos~6.8kAutomated safety check: PassApache-2.0
Goprekuter/dryforge4101 repos~7.2kAutomated safety check: PassApache-2.0
agtx Execute Phasefynnfluegge/agtx1.7k—~439Automated safety check: PassApache-2.0
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Adopt PR Branch Contextpydantic/pydantic-ai-harness948—~1.8kAutomated safety check: PassMIT

Similar skills

  • Ready

    prekuter/dryforge

    Understand what you mean before anything is built. An agent skill from prekuter/dryforge.

    410 GitHub starsUsed in 1 repo~6.8k tokens
    Agent WorkflowsAuto-check passed

  • Go

    prekuter/dryforge

    Carry out the intent approved in ready, as meant, and prove it with checks that actually ran.

    410 GitHub starsUsed in 1 repo~7.2k tokens
    Agent WorkflowsAuto-check passed

  • agtx Execute Phase

    fynnfluegge/agtx

    Carries out an approved plan for an agtx-managed task: implements the changes, runs tests, commits, writes a summary to .agtx/execute.md and then stops.

    1.7k GitHub stars~439 tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Adopt PR Branch Context

    pydantic/pydantic-ai-harness

    Official

    Fills in issue-brief.md and pr-decisions.md for an existing pull request, so you can pick up a PR mid-flight with its linked issue and past review decisions summarized.

    948 GitHub stars~1.8k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Migration

    prekuter/dryforge

    Bring an existing codebase into Dryforge, once. An agent skill from prekuter/dryforge.

    410 GitHub starsUsed in 1 repo~3.2k tokens
    Agent WorkflowsAuto-check passed

More from FlorianBruniaux/claude-code-ultimate-guide

All 14 skills in this repo

  • Changelog Social Recap

    FlorianBruniaux/claude-code-ultimate-guide

    Turns CHANGELOG.md entries for a release or a week into LinkedIn, Twitter/X, newsletter and Slack posts in French and English.

    6.1k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes

  • Codex Skill Self-Assessment

    FlorianBruniaux/claude-code-ultimate-guide

    Runs an interactive quiz in a quick or comprehensive mode, scores your skill level by topic and generates a personalized learning path with practice projects.

    6.1k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Whitepaper Bare Section Prose Filler

    FlorianBruniaux/claude-code-ultimate-guide

    Adds two to four sentences of intro prose before each bare heading in the French and English whitepapers, splitting the work across nine parallel agents.

    6.1k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Audit Whitepapers

    FlorianBruniaux/claude-code-ultimate-guide

    Audits version freshness, French and English parity and metadata of whitepapers and recap cards in the claude-code-ultimate-guide repo, with optional fix suggestions.

    6.1k GitHub stars~3.8k tokensUpdated yesterday
    Auto-check passed

  • Guide and Landing Sync Check

    FlorianBruniaux/claude-code-ultimate-guide

    Check guide/landing synchronization status

    6.1k GitHub stars~692 tokensUpdated yesterday
    Auto-check passed

  • Track Online Mentions

    FlorianBruniaux/claude-code-ultimate-guide

    Searches the web for new mentions of the Claude Code Ultimate Guide or its author's public projects, checks them against YAML trackers and reports or adds the new ones.

    6.1k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Methodology Advisor

What does Methodology Advisor do?

Reads a codebase silently, asks only what it cannot infer, and recommends one AI-assisted development methodology stack with a contextual quick start. This skill wraps a migrated command that takes two to four minutes.json, team size from unique contributors over the last 90 days and total commits, test maturity from the number of test files, spec and documentation signals such as spec, design, ADR and RFC files, codebase size and structure, and signs of LLM use such as imports of AI libraries.

When should I use Methodology Advisor?

Methodology Advisor fits situations like: choosing a methodology for AI-assisted work on a new or inherited project; matching the process to team size, test maturity and documentation habits; getting a short quick start tailored to your repository.

How do I install Methodology Advisor in Claude Code?

Run `npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill source-command-methodology-advisor -a claude-code`. Or copy the skill folder (.agents/skills/source-command-methodology-advisor in FlorianBruniaux/claude-code-ultimate-guide) into .claude/skills/source-command-methodology-advisor in your project. Claude Code loads it when a task matches its description.

How do I install Methodology Advisor in Codex?

Run `npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill source-command-methodology-advisor -a codex`. Or copy the skill folder (.agents/skills/source-command-methodology-advisor in FlorianBruniaux/claude-code-ultimate-guide) into .agents/skills/source-command-methodology-advisor in your project. Codex loads it when a task matches its description.

Can I use Methodology Advisor 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 FlorianBruniaux/claude-code-ultimate-guide --skill source-command-methodology-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/source-command-methodology-advisor, .gemini/skills/source-command-methodology-advisor, .github/skills/source-command-methodology-advisor and .opencode/skills/source-command-methodology-advisor in your project.

What does Methodology Advisor need to run?

Going by SKILL.md and its folder, Methodology Advisor needs the command-line tools its instructions call (git). Our summary lists: A git repository to analyze.

Does Methodology Advisor access the network?

SKILL.md names 1 domain. As links in the text: cc.bruniaux.com. This is read from the text; nothing was executed.

Is Methodology Advisor 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 Methodology Advisor use?

Methodology Advisor is published under the CC-BY-SA-4.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Methodology Advisor use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Methodology Advisor?

Skills that share tags, products or a category with Methodology Advisor: Ready (prekuter/dryforge, 410 stars), Go (prekuter/dryforge, 410 stars), agtx Execute Phase (fynnfluegge/agtx, 1.7k stars) and CCPM Project Management (automazeio/ccpm, 8.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Methodology Advisor?

FlorianBruniaux (a GitHub user) maintains it in FlorianBruniaux/claude-code-ultimate-guide, which has 6,126 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

Source: FlorianBruniaux/claude-code-ultimate-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.