Skill Claude CodeCodex
Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10-year-old, $0 budget), scores, clusters, prunes traps, and deepens top survivors. Use on /adhd, "ADHD mode", brainstorm/ideate intents, or open-ended design, architecture…
Skill Claude CodeCodex
Benchmark a product claim against a named baseline or competitor. Asks whether the comparison is inside (our own past) or outside (a rival product, the alternative we skipped, a bar someone set), drills down from the answer, then holds both sides to the same conditions. Use when a claim of faster, cheaper, better…
Skill Claude CodeCodex
Reviews code changes with deterministic scope selection, isolated review units, evidence-backed findings, exact line anchoring, and a final falsification pass. Use when reviewing workspace changes, commits, branch ranges, pull request diffs, patches, or any unified diff across languages, models, and Git hosts.
Skill Claude CodeCodex
Re-review a pull request after the author has pushed fixes for your earlier findings. Establishes which bugs are new versus ones you missed, checks each prior finding closed end-to-end rather than at the patched line, and treats the fix commit itself as unreviewed code. Use when returning to a PR you already reviewed…
Skill Claude CodeCodex
Get a second opinion from a subagent that has none of your context, either to independently corroborate a diagnosis or to adversarially break your work. Use before a conclusion blocks or justifies significant work, before merging security-sensitive code, when you have already changed your mind once on the same…
Skill Claude CodeCodex
Manages isolated development worktrees with git gtr, including creation, validation, command execution, tool launch, and safe cleanup. Use when the user mentions git-worktree-runner, git gtr, parallel branch worktrees, or running coding agents in isolated worktrees.
Skill Claude CodeCodex
Verify a change in both directions before claiming it works. Confirm it passes, then break it on purpose and confirm it fails. Use when a fix ships with a test, when touching anything that detects or gates (linter, secret scanner, CI check, validator, rate limiter, auth guard, allowlist), when resolving a merge…
Skill Claude CodeCodex
Research a URL (repo, gist, article, doc) with one dedicated subagent per URL, producing a fixed-format distilled report plus entries in the project learnings file. Use when the user drops a link and asks to research it, learn from it, or extract tips, rules, or lessons ("research this URL", "have an agent learn from…
Skill Claude Code
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Skill Claude CodeCodex
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
Cursor rule Cursor
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Activate whenever editing prose-heavy files (Markdown, documentation, blog posts, READMEs, release notes, emails). Cursor port of the avoid-ai-writing skill v3.16.0. See https://github.com/conorbronsdon/avoid-ai-writing.
Skill Claude CodeCodex
Expert backend engineering playbook for APIs, databases, auth, distributed systems, observability, performance, and production hardening. Use when designing or reviewing server-side code, building REST/GraphQL/gRPC/WebSocket APIs, debugging database or latency issues, choosing monolith vs services, adding…
Skill Claude CodeCodex
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Skill Claude CodeCodex
Generate, preview, and apply a brand color palette (plus typography, gradients, and tone/voice) to a frontend project. Use when a user says "pick brand colors", "choose a color palette", "brand design", "generate a palette", "theme this project", "what colors should I use", "brand identity", "design my brand", "set up…
Skill Codex
Guide a developer through building a Solana data pipeline or indexer. Use when a user says "build an indexer", "data pipeline", "analytics", "track transactions", "monitor wallets", "webhook", "index accounts", or "real-time data". Reads build-context.md from a prior scaffold phase if available.
Skill Codex
Guide a developer through building a DeFi protocol on Solana. Use when a user says "build a DEX", "AMM", "lending protocol", "vault", "yield", "liquidity pool", "DeFi protocol", "swap program", "build a DeFi app", "perpetual futures", "perps protocol", "leverage trading", or "derivatives". Reads build-context.md from…
Skill Codex
Guide a developer through building a Solana mobile app. Use when a user says "build a mobile app", "React Native Solana", "Solana mobile", "mobile wallet", "mobile dApp", "Android Solana", or "iOS Solana". Reads build-context.md from a prior scaffold phase if available.
Skill Codex
Guide a developer through building their Solana MVP step by step using Claude Code. Use when a user says "help me build this", "start the MVP", "guide me through implementation", "what should I build first", or "walk me through the code". Reads build-context.md from a prior scaffold phase if available.
Skill Claude CodeCodex
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result…
Skill Claude CodeCodex
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
Skill Claude CodeCodex
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
Skill Claude CodeCodex
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Skill Claude CodeCodex
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Skill Claude CodeCodex
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: