Borrowing it
Nothing to install: this file belongs to egregore-labs/egregore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/create-skill/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/egregore-labs/egregore/create-skill)<a href="https://agentmods.dev/skills/egregore-labs/egregore/create-skill"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/create-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 6 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01220 |
| Opus 5 | $0.00015 | $0.00610 |
| Sonnet 5 | $0.00006 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
create-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an org-owned skill. Owned skills live in .claude/skills/<name>/ like
framework skills, but they belong to the org: /update never overwrites them,
and if upstream ever ships a skill with the same name, the org's version wins
and the collision is reported.
Arguments: an optional skill name and/or a description of what the skill should do.
When to invoke
User says: "create a skill", "make a skill for X", "I want a /foo command for
our team", "turn this workflow into a skill", /create-skill <name>
Not this: installing someone else's published skill → find-skills · changing
a framework skill's behavior → /contribute (upstream owns it)
Step 1: Name and scope
Derive a kebab-case name from the request. Rules:
- Lowercase letters, digits, hyphens only. No slashes, no leading dot.
- Must not collide with a framework skill. Check both the local tree and upstream when available:
NAME="<kebab-name>"
if [ -d ".claude/skills/$NAME" ]; then
echo "exists locally"
fi
git fetch upstream main --quiet 2>/dev/null || true
git ls-tree -d upstream/main ".claude/skills/$NAME" 2>/dev/null | grep -q . && echo "exists upstream"
If the name exists locally or upstream, propose 2–3 alternatives via AskUserQuestion instead of silently picking one. An org CAN deliberately own a name upstream also uses (their version then always wins), but that is an explicit choice — never a default.
If the user gave only a name and no behavior, ask what the skill should do before scaffolding — a skill with an empty body helps nobody.
Step 2: Scaffold
Write .claude/skills/$NAME/SKILL.md:
---
name: <name>
description: <one line — what it does and when an agent should reach for it>
---
<What this skill does, in 1–3 sentences.>
## When to invoke
User says: <trigger phrases>
Not this: <adjacent intents that route elsewhere>
## Steps
1. <concrete step — commands in fenced bash blocks>
2. <...>
Fill it with real content derived from the user's description — trigger
phrases an agent can match, concrete steps, actual commands. Follow
product-voice for any user-facing copy the skill emits.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 136 lines · 31 tokens per session scan A f80fe45b509a
create-skill is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 1,220 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
pulp-cinema-director
Higgsfield Supercomputer skill for original pulp-cinema video direction: nonlinear crime scenes, standoffs, trunk-level shots, grindhouse, kung-fu homage, spaghetti-western energy, neon diners, chapter structure, and dialogue-heavy cinematic prompts.
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…