colomet/skill-boilerplate / template
my-new-skill
Verified[FILL IN: what this skill does and exactly when to use it -- the phrases a user would actually type, not just the topic]
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 116 B |
| SKILL.md | skill md | 1.9 KB |
SKILL.md
View on GitHub---
name: my-new-skill
description: "[FILL IN: what this skill does and exactly when to use it -- the phrases a user would actually type, not just the topic]"
---
# My New Skill
[FILL IN: what this does, in a sentence or two.]
## When NOT to use this
- [A situation this should not fire for -- especially if a neighbouring skill
covers it. This section is what stops two skills competing for the same
triggers.]
## Instructions
[FILL IN: the steps, rules or knowledge to follow.]
## Output
[FILL IN: what "done" looks like. A skill that doesn't say produces something
different every run.]
<!-- ---------------------------------------------------------------------
Three optional folders exist in the format. None ships with this template,
because a folder created before it has content is a promise nobody keeps --
and an empty one still has to be opened, checked and closed by every reader
who wonders what's in it.
Create one when you have something to put in it, not before:
references/ Documentation the skill consults. Loaded on demand, so this
is where detail belongs that isn't needed on every run.
scripts/ Executable code. Use it when logic is more reliable as
deterministic code than as prose instructions.
assets/ Templates, images, fonts -- files used as-is, never read as
instructions.
mkdir references
Or let the scaffolder do it, which is the intended path:
python3 scaffold_skill.py my-new-skill --references --scripts
Once a folder grows past a handful of files, subdivide inside it
(references/<area>/) rather than adding a fourth folder at the top level:
references/<area>/ is predictable to anyone who knows the format, an invented
top-level name is not.
Delete this comment once the skill is written.
---------------------------------------------------------------------- -->
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 | Unverified | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |