agent-qa-run-review
Review recorded agent-qa runs and memidex provenance to explain a QA verdict, identify missing evidence, and propose the smallest…
Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk.
Claude Code
$ npx -y skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition --agent claude-code
Codex
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a codex -y
Cursor
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a cursor -y
Gemini CLI
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a gemini-cli -y
GitHub Copilot
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a github-copilot -y
OpenCode
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a opencode -y
Windsurf
$ npx skills add DevelopersGlobal/ai-agent-skills --skill task-decomposition -a windsurf -y
name: task-decomposition description: Breaks features into atomic, independently verifiable tasks. No task should take more than 4 hours. Unblocks parallel work and reduces integration risk. category: plan applies-to: [claude, gemini, cursor, copilot, any] version: 1.0.0
Large tasks fail in large ways. Decomposed tasks fail in small, fixable ways. This skill breaks any feature or project into atomic tasks — each independently implementable, testable, and deployable.
1. State what "done" looks like for the whole feature. 2. List all the things that must be true when it's complete. 3. Identify dependencies: what must exist before any task can start?
**Verify:** You can state the full feature goal in 2 sentences.
4. Break the feature into tasks where each task:
5. Each task should be: `[verb] [noun] so that [outcome]`
**Verify:** Every task is under 4 hours. Every task has a clear verify condition.
6. Draw the dependency graph — what blocks what? 7. Identify tasks that can be done in parallel. 8. Sequence tasks so integration happens incrementally (not as one big bang at the end).
**Verify:** The dependency order is clear. No unnecessary sequential dependencies.
9. For each task, estimate: best case / worst case / expected. 10. If any task's worst case > 1 day: decompose further. 11. Total estimate sanity check: does it add up to a reasonable timeline?
| Excuse | Rebuttal | |--------|----------| | "I'll figure it out as I go" | Decomposition takes 30 minutes. Rework from poor planning takes days. | | "It's too complex to break down" | Everything can be decomposed. Start with what you know, decompose the rest later. | | "The tasks are too granular" | Granular tasks ship continuously. Coarse tasks ship never. |
Review recorded agent-qa runs and memidex provenance to explain a QA verdict, identify missing evidence, and propose the smallest…
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output…
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the…
Guides agents to engage and transact with citruscoastai, an AI venture-operator agent, when they need hired AI labor or an…
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.