swe:create-skill

swe:create-skill is a skill for Claude Code from ckorhonen/swe-skills. It costs 97 tokens per session (1,554 once invoked), scanned A, original, MIT.

A repeatable workflow for creating or revising repository-local skills, which are instruction packages for coding agents.

In plain words
What is it for?
Use it to add a new skill, tighten an existing one, create matching evaluation files, and update related repository guidance.
Why use it?
It helps keep skills focused, consistently structured, and checked against realistic use cases.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the swe-skills plugin — 17 skills shipped together

Good fit Use it to add a new skill, tighten an existing one, create matching evaluation files, and update related repository guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/swe-skills/create-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ckorhonen/swe-skills --skill create-skill
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/swe-skills

Made for: Claude Code.

Or install swe-skills, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

agentmods badge for swe:create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/swe-skills/create-skill.svg)](https://agentmods.dev/skills/ckorhonen/swe-skills/create-skill)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/create-skill"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01554
Opus 5 $0.00048 $0.00777
Sonnet 5 $0.00019 $0.00311
Haiku 4.5 $0.00010 $0.00155

Measured 8d ago against content hash 8bcd5027da8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swe: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.

skills/create-skill/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE Create Skill

What This Skill Does

Use this skill to author or revise a swe: skill package for this repository in a way that is:

  • grounded in concrete user workflows
  • narrow enough to trigger reliably
  • consistent with this repo's skill and eval conventions
  • easy to validate and improve over time

This skill distills the Anthropic skill-building guidance into a repo-specific authoring workflow.

The outcome should usually include:

  • one skills/<slug>/SKILL.md
  • one matching evals/<slug>/README.md
  • one matching evals/<slug>/rubric.md
  • one matching evals/<slug>/cases.json
  • any required updates to README.md or AGENTS.md

When To Use

Use this skill when the user wants to:

  • add a new swe: skill to this repository
  • revise an existing skill that is too broad, too narrow, or structurally weak
  • turn an external guide or repeated workflow into a reusable repo-local skill
  • standardize how future skill authors package instructions and evals

Do Not Use

Do not use this skill for:

  • implementing the engineering workflow that the skill would later describe
  • generic repo documentation cleanup with no skill-authoring goal
  • one-off prompts that are not repeatable enough to justify a skill
  • large repository policy rewrites unrelated to skill authoring

Inputs To Confirm

Confirm or infer:

  • whether the work is a new skill or a revision to an existing one
  • the target workflow, user outcome, and success criteria
  • 2-3 realistic trigger phrases a user would actually say
  • the important non-goals or negative triggers
  • whether the skill depends on local tooling, MCP integrations, or external references
  • whether matching eval assets already exist or must be created

If the request is underspecified, ask only for the missing workflow boundary needed to keep the skill narrow.

Instructions

Step 1: Start With Concrete Use Cases

Define 2-3 specific use cases before writing the skill.

For each use case, capture:

  • user request
  • workflow steps Claude should perform
  • result the user should get

Read the full file on GitHub · 226 lines

Changes

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.

  1. 8d ago First seen · 226 lines · 97 tokens per session scan A 8bcd5027da8d

Subscribe to this mod's changes

swe:create-skill is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,554 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

design-sync-upload

An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.

modu-ai/moai-cowork · 211 tokens