ai-tools

Triage unresolved PR review threads via webform and dispatch fixes through whip-start. Use after receiving review feedback on your own PR.

Triage unresolved PR review threads via webform and dispatch fixes through whip-start. Use after receiving review feedback on your own PR.

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.

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.

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.

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.

Run multi-agent simulations to measure consistency of non-deterministic behavior. Use when the user wants to A/B test, validate behavioral equivalence, or stress-test outputs at scale.

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.

Spawn whip agent sessions to handle tasks. Dispatch a single agent or assemble a small team with explicit backend, scope, and ownership.

Spawn whip agent sessions to handle tasks. Dispatch a single agent or assemble a small team with explicit backend, scope, and ownership.

Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.

Analyze a session transcript with AI and generate structured insights (prompt quality, strategy critique, key decisions, takeaways) for the rewind viewer.

Write or update documentation with code-verified accuracy. Use when creating, reviewing, or updating docs, READMEs, guides, or API references.

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.

Write or update documentation with code-verified accuracy. Use when creating, reviewing, or updating docs, READMEs, guides, or API references.

Analyze work, design a stacked task plan, and get user approval before execution. Use when starting a multi-task project that needs planning.

Create a real-world whip case-study or lessons-learned markdown file under .whip/lesson-learn/<file-name>.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.

Create a real-world whip case-study or lessons-learned markdown file under .whip/lesson-learn/<file-name>.md. Use when the user wants to capture an actual whip run, prompts, decisions, IRC coordination, outcomes, or lessons learned.