agentleFS
zhouguoqingzhouguoqing/QianYuan.AIAgenticFramework/.agents/skills/using-superpowers/SKILL.md

using-superpowers

Skill35 starsChanged 6 months agoApache-2.0View on GitHub

Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.

182 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 19 projects that use this

  • kntismSkill

    condition-based-waiting

    Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

    Also in 3 projects that use this

  • frankxaiSkill

    defense-in-depth

    Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

    Also in 3 projects that use this

  • MicrosoftSkill

    root-cause-tracing

    Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

    Also in 3 projects that use this

  • +3 more from Leodorareluctant259

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If there is even a 1% chance a skill applies to the current task, invoke it.

    line 10
  2. Distinctive:

    Ask: "Does any skill match what I'm about to do?"

    line 19
  3. Distinctive:

    If yes → load and follow the skill exactly

    line 20
  4. Distinctive:

    If no → proceed with default behavior

    line 21
  5. Distinctive:

    When you invoke a skill, say so:

    line 49
  6. Very specific:

    If a task will take more than ~20 minutes, check long-running-task-management first

    line 60

“Common” is measured: kept by at least 6 in 10 of the 168 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Using Superpowers

The Core Rule

If there is even a 1% chance a skill applies to the current task, invoke it.

Skills are cheap to load. Failing to use an applicable skill is expensive.

How to Find Skills

At the start of every new task:

  1. Review available skills (check ~/.openclaw/extensions/superpowers/skills/)
  2. Ask: "Does any skill match what I'm about to do?"
  3. If yes → load and follow the skill exactly
  4. If no → proceed with default behavior

In OpenClaw's persistent agent context, check skills at the start of every new task, not just new conversations. A long-running session may handle many different task types.

Decision Flowchart

New task received
    ↓
Does any skill apply? (even 1% chance → YES)
    ↓
YES → Announce: "Using [skill-name] to [purpose]"
      Load skill file
      Follow instructions exactly
      ↓
      Complete or hand off cleanly

NO → Proceed with default agent behavior

Priority Hierarchy

  1. User instructions — always highest priority
  2. Skills — override default behavior when applicable
  3. Default behavior — fallback when no skill applies

Announcing Skill Usage

When you invoke a skill, say so:

"Using brainstorming to explore approaches before writing code." "Using systematic-debugging to diagnose this error."

This keeps the human informed and lets them redirect if needed.

OpenClaw-Specific Notes

  • In persistent sessions, skills should be checked at the start of each new task, not just session start
  • Skills around task-handoff and agent-self-recovery matter more in OpenClaw than in session-based tools — don't skip them
  • If a task will take more than ~20 minutes, check long-running-task-management first

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.