Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.
EnglishSystematic debugging loop — reproduce, analyze root cause, fix, then challenge with a fresh verification pass to distinguish fundamental fixes from workarounds. Use when debugging issues or when unexpected behavior needs a methodical approach.
EnglishWrite or update documentation with code-verified accuracy. Use when creating, reviewing, or updating docs, READMEs, guides, or API references.
EnglishCreate a real-world whip case-study or lessons-learned markdown file under .whip/lesson-learn/ .md. Use when the user wants to capture an actual whip run, prompts, decisions, IRC coordination, outcomes, or lessons learned. Prefer the explicitly requested language; otherwise use the user's conversation language.
EnglishIterative review-fix loop — dispatch a fresh codex reviewer each round, apply fixes, repeat until LGTM. Use when you want rigorous code quality validation before merge.
EnglishTurn a multi-agent request into a concrete 6-phase whip plan, get user approval, save it under ~/.whip/plans, then hand off to $whip-start for execution.
EnglishTriage unresolved PR review threads via webform and dispatch fixes through whip-start. Use after receiving review feedback on your own PR.
EnglishRun multi-agent simulations to measure output consistency. Use when you want to A/B test, validate behavioral equivalence, or stress-test non-deterministic behavior at scale.
EnglishSpawn whip agent sessions to handle tasks. Dispatch a single agent or assemble a small team with explicit backend, scope, and ownership.
English
AGENT SKILLS ATLASIncludes Rewind Analyze, Whip Debug, Whip Lesson Learn, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Rewind Analyze
Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.
Whip Debug
Systematic debugging loop — reproduce, analyze root cause, fix, then challenge with a fresh verification pass to distinguish fundamental fixes from workarounds. Use when debugging issues or when unexpected behavior needs a methodical approach.
Whip Docs
Write or update documentation with code-verified accuracy. Use when creating, reviewing, or updating docs, READMEs, guides, or API references.
Whip Lesson Learn
Create a real-world whip case-study or lessons-learned markdown file under .whip/lesson-learn/ .md. Use when the user wants to capture an actual whip run, prompts, decisions, IRC coordination, outcomes, or lessons learned. Prefer the explicitly requested language; otherwise use the user's conversation language.
Whip Lgtm
Iterative review-fix loop — dispatch a fresh codex reviewer each round, apply fixes, repeat until LGTM. Use when you want rigorous code quality validation before merge.
Whip Plan
Turn a multi-agent request into a concrete 6-phase whip plan, get user approval, save it under ~/.whip/plans, then hand off to $whip-start for execution.
Whip PR Followup
Triage unresolved PR review threads via webform and dispatch fixes through whip-start. Use after receiving review feedback on your own PR.
Whip Simulate
Run multi-agent simulations to measure output consistency. Use when you want to A/B test, validate behavioral equivalence, or stress-test non-deterministic behavior at scale.
Whip Start
Spawn whip agent sessions to handle tasks. Dispatch a single agent or assemble a small team with explicit backend, scope, and ownership.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Rewind Analyze skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.