Skip to content

avibebuilder/claude-prime / .claude/skills/optimus-prime

optimus-prime

Verified

Generates a Claude Code configuration tailored to a specific project. Use whenever the user wants to prime a project, set up claude for a repo, bootstrap claude config, or re-prime/refresh an already-primed project (for example after `/prime-sync` pulled new starter content). Triggers on 'prime', 'prime this project', 'optimus-prime', 're-prime', 'refresh claude config', 'regenerate CLAUDE.md', 'set up claude for this repo'. Deeply analyzes the real codebase and builds project-specific skills, rules, and CLAUDE.md — not generic boilerplate. For ongoing config health checks and proposal review, use `self-evolve` instead.

FileKindSize
SKILL.mdskill md5.8 KB
references/analysis-checklist.mdmarkdown2.3 KB
references/setup-project.mdmarkdown8.3 KB

references/analysis-checklist.md

View on GitHub
# Project Analysis Checklist

What to inspect before proposing changes. The goal is to understand what makes this project unique — what conventions, patterns, and constraints Claude needs to know to work well here.

## 1. Existing Claude Config

Check what is already present and whether it looks intentional:
- `CLAUDE.md`, `CLAUDE.local.md`
- `.claude/skills/` — existing project skills
- `.claude/rules/` — path-scoped files besides `_apply-all.md`
- `.claude/project/` — agent-oriented references
- `.claude/starter-skills/` — unprocessed reference material

Answer:
- What should be preserved as intentional project knowledge?
- What is generic, stale, duplicated, or unfinished?
- Which files are personal vs team-shared?

## 2. Skill Needs

Identify what domain knowledge Claude needs for this project:
- What frameworks, libraries, and tools does the project actually use?
- Which domains need dedicated skills? (e.g., frontend framework, backend API, deployment)
- Do any existing skills in `.claude/skills/` already cover these well?
- Are there starters in `.claude/starter-skills/` that provide useful reference for building skills via `/skill-creator`?

Focus on what the project needs, not what starters happen to be available.

## 3. Signals Worth Closer Attention

Conventions agents commonly miss:
- custom response wrappers, error envelopes, or API shapes
- non-default utility choices (`cn()` vs `clsx()`, custom fetch client, internal form library)
- monorepo boundaries or ownership rules
- unusual test/lint/typecheck commands
- deployment constraints that influence code shape
- generated-code boundaries — files that must not be edited directly

These are candidates for placement decisions, not automatic rules.

## 4. Existing Docs Worth Reusing

Prefer pointing to good docs over duplicating them into `CLAUDE.md`:
- root and package-level READMEs
- architecture docs, ADRs, runbooks
- onboarding docs
- CI config, scripts, or Make targets that reveal canonical commands

## 5. Facts to Verify Before Claiming Them

Do not assert conventions without evidence:
- package manager and workspace layout
- frontend/backend boundaries
- test/lint/typecheck commands actually in use
- whether TypeScript/ESLint/Biome/Prettier are really present
- whether "all X lives in Y" is actually true
- whether a supposed shared utility is the standard path
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall