skills/todo/SKILL.md
Add tasks or ideas discovered during work to docs/todo
npx skillsauth add api-haus/my-claude-workflow todoInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Save tasks, ideas, or follow-ups discovered while working.
| Directory | Tracked | Purpose |
|-----------|---------|---------|
| docs/todo/ | Yes | Public tasks safe for git history |
| docs/_internal/todo/ | No (gitignored) | Tasks with sensitive references or internal notes |
Default: docs/todo/. Use docs/_internal/todo/ when the task references proprietary implementations or external codebases.
/todo <slug>: <description> - Add a task with explicit slug
/todo <description> - Add to an existing category file
| Component | Format | Example |
|-----------|--------|---------|
| Todo file | docs/todo/<slug>.md or docs/_internal/todo/<slug>.md | docs/todo/player-collision.md |
| Worktree | .claude/worktrees/<slug> | .claude/worktrees/player-collision |
| Branch | <type>/<slug> | feat/player-collision |
docs/todo/<slug>.md with task descriptionplayer-integration.md - Player collision, tools, camerarefactoring.md - Code quality, complexity reductionmodularity.md - Generic framework refactoringfuture-features.md - New features, procedural generation, particlessmall-tasks.md - Miscellaneous, doesn't fit elsewhere- [ ] <description>Standalone task (for /picktodo):
# <Title>
<Description of what needs to be done>
## Tasks
- [ ] Subtask 1
- [ ] Subtask 2
Category file:
# [Category] Tasks
## High Priority
- [ ] Brief task description
## Low Priority
- [ ] Another task
data-ai
Extract research content from YouTube presentations, PDFs, or PPTX files into structured markdown. Dispatches each pass to a dedicated sub-agent (research-extractor / research-vision / research-refiner) so per-deck vision passes scale to hundreds of slides without bloating the parent context.
development
Build, run, and analyze Unity profiler data with perf-report-style call-stack attribution
documentation
Write a handoff prompt for a future session. A handoff is a continuation-link — minimal context plus a kickoff line the user can copy-paste. Never a diagnosis, never an investigation script, never a prescribed deliverable.
testing
Multi-agent orchestration mode. The orchestrator never reads, edits, runs, or tests directly — it scopes work, runs a re-implementation audit, presents a freeform method brief with grounded recommendations, then dispatches every step to sub-agents through shared context files at `docs/orchestrate/<topic>/`. Use when invoked via /delegate, when the user asks to orchestrate or coordinate multi-agent work, or when the task explicitly calls for delegation.