tkhribech/claude-founder-os / skills-library/SKILL-TEMPLATE
skill-name-in-kebab-case
UnverifiedOne or two sentences optimized for TRIGGERING — say when to use this skill, in the words a user would actually say, including the trigger phrases ("run the X", "check Y", "how are Z doing"). The harness matches requests against this line; a vague description means the skill never fires.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.7 KB |
SKILL.md
View on GitHub---
name: skill-name-in-kebab-case
description: One or two sentences optimized for TRIGGERING — say when to use this skill, in the words a user would actually say, including the trigger phrases ("run the X", "check Y", "how are Z doing"). The harness matches requests against this line; a vague description means the skill never fires.
---
<!-- Anatomy of a good SKILL.md. Delete these comments in your real skill.
Principles:
- The description is for ROUTING; the body is for EXECUTION. Different audiences.
- Write the body for an assistant with zero session context: name exact file paths,
exact commands, exact output format.
- Encode decisions, not vibes: "if A then B" beats "use judgment".
- State what the skill must NOT do as explicitly as what it does.
- If the skill produces an artifact, specify where it's written and what "done" looks like. -->
# Skill Name
One paragraph: what this skill does and what exists when it finishes.
## When to use / when NOT to use
- Use when: …
- Do NOT use for: … (route those to <other skill / plain work> instead)
## Inputs
What the skill needs before it can run: files to read, credentials location (a git-ignored folder, read at runtime — never echoed), founder decisions that must already exist.
## Steps
1. …exact, ordered, with the real commands/paths…
2. …
3. Verify: state HOW the result is checked, at the layer of the claim.
## Output
The exact artifact + where it's written + the report format (lead with the answer; separate verified from assumed).
## Guardrails
- The standing rules this skill must respect (link the memory files).
- The irreversible actions inside it that always require founder confirmation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse 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. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |