Establish a routine for checking and invoking relevant skills before answering or taking action. It prioritizes skills that define the workflow, then guides the agent toward task-specific skills and any checklists they contain.
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Review the instructions the agent will receive before you install.
IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.
This is not negotiable. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>
Invoke relevant or requested skills BEFORE any response or action — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.
Before entering plan mode: if you haven't already brainstormed, invoke the brainstorming skill first.
Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.
These thoughts mean STOP—you're rationalizing:
| Thought | Reality |
|---|---|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
If your harness appears here, read its reference file for special instructions:
references/codex-tools.mdreferences/pi-tools.mdreferences/antigravity-tools.mdreferences/hermes-tools.mdUser instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Turn development ideas into clear designs through guided discussion. The skill clarifies goals, requirements, and constraints, then adapts the process to a feasibility investigation, a small existing-code change, or a larger architectural design.
Find academic papers, retrieve publication details, and build BibTeX reference files for scholarly writing. Check identifiers, missing information, duplicate entries, and mismatches between manuscript citations and the bibliography, with tools for formatting and validation.
Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.
Carry out a written implementation plan in a separate session, reviewing it before starting and tracking each task through verification. The workflow pauses for blockers and hands completed work to a development branch finishing process.
Plan experiments before collecting data by choosing how to assign samples, combine conditions, and order runs. Generate reproducible allocation schedules and experimental layouts while checking for design flaws that could make results difficult to interpret.
Explore scientific data files to understand their structure, statistical patterns, and quality. References cover over 200 formats, with workflows for producing Markdown reports that summarize findings and recommend preprocessing, visualizations, and further analysis.