dotfiles

Use when executing a preflight checklist. Triggers: 'fly', 'launch execution', 'run the checklist', or when given a preflight checklist file path.

Use when the user says '/learn', 'learn this', 'document this', 'capture this', 'remember this for next time', 'update the docs', asks to capture a durable project learning, or after fixes/reviews reveal reusable patterns.

Use when the user asks to merge, land, rebase before landing, resolve landing conflicts, or advance an integration branch such as main, master, or m3.

Use when the user asks to close, end, clean up, tear down, or finish a worktree/session after work is landed.

Use when starting an interactive parent task session, when the user gives feedback about agent behavior, or when the user asks about observations, skill improvements, or observation logs. Skip delegated/non-interactive subagents, review-only workers, verify-only workers, Codex/Claude print-mode reviewers, and sessions that only report back to a parent agent.

Use when the user says 'deep review', 'thorough review', 'full review', 'triple review', or 'ultra review'.

Use when the user says 'new session', 'start a session', 'new worktree', 'start fresh', or 'spin up a workspace'.

any input (code, docs, papers, images, videos) to knowledge graph. Use when user asks any question about a codebase, documents, or project content - especially if graphify-out/ exists, treat the question as a /graphify query.

Use when reading large files, multiple medium/large files, broad codebase context, long logs, diffs, transcripts, generated output, or when drafting repetitive tests, fixtures, docs, config, or boilerplate.

Use when the user says 'extract docs', 'split AGENTS.md', 'split CLAUDE.md', 'refactor the docs', 'slim AGENTS.md', or has sprawling root instructions to break up.

Use when the user says 'set up adaptive docs', 'init docs', 'add agent docs to this project', or wants to bootstrap the three-layer docs/ai/ + AGENTS.md structure in a new project.

Use when the user reports a bug or says 'fix', 'broken', 'doesn't work', 'regression', or describes unexpected behavior.

Use when the user says '/dashboard', 'open the learning dashboard', 'show learning dashboard', or wants to review project learnings.

Use when the user says '/learn-init', 'initialize learnings', 'set up the learning system', or wants to add project learnings to a repo.

Use when the user says 'QA test', 'test the UI', 'click through it', or 'test the flows', or when end-to-end browser validation is needed.

Save session progress: update PROGRESS.md coordination board, route learnings to docs, update TECH_DEBT.md.

Use when preparing an implementation plan for disciplined execution, typically after /superpowers:writing-plans and before /fly. Triggers: 'preflight', 'checklist the plan', 'prep for execution', or when given a plan file path to process.

Use when committing, rebasing, merging, resolving conflicts, amending commits, switching branches, creating branches, pushing, or working with worktrees.

Use when the user says 'critique', 'how does it look', 'check the UI', 'visual review', or 'polish the UI'. Also use proactively after frontend changes.

Use when the user asks to build web components, pages, or apps. Generates distinctive, polished frontend code that avoids generic AI aesthetics.

Use when the user needs to navigate websites, interact with pages, fill forms, take screenshots, or test web apps in a real browser.

Use when the user says 'sync architecture', 'update the architecture diagram', 'refresh architecture', or 'audit the diagram'. Also auto-invoked by /save and /deep-review, or after adding, removing, or renaming a top-level module.