Skill Authoring
Plugin
crafter-station-skills
Agent skills extracted from real work. Each one shipped something first.
Plugin Signal63/100Solid
maintained76
capable48
documented75
adopted44
Install on Claude Code
> /plugin marketplace add crafter-station/skills
Stats
113
Stars
15
Forks
Maintained
Maintenance
Shell
Language
MIT
License
1mo ago
Last commit
9mo ago
Created
3h ago
Added
What's inside
Skill(9 skills)
/cli-auditAudit an existing CLI against cli-build: how well an agent can operate it and how well a human can read it. Use when the user wants to audit a CLI, check whether a tool is agent-first, find out what a published CLI got wrong, grade a CLI's human output, verify that named safety/cli-buildDesign and build a CLI that an AI agent can operate safely and a human can supervise. Use when the user wants to build a CLI, wrap an API in a command-line tool, build a CRUD or local-first tool over a database or filesystem the user already owns, add --json or --dry-run to an/generate-brand-assetsGenerate OG images and favicon based on project branding. Use when: (1) user needs social media preview images for their project, (2) user wants to generate a favicon, (3) user is setting up branding assets for a website or app, (4) user has brand colors and wants
README
crafter skills
Agent skills extracted from real work. Each one shipped something first.
Install
npx skills add crafter-station/skills
That lists every skill and lets you pick. To install one directly:
npx skills add crafter-station/skills --skill supply-chain-audit -g
Works with Claude Code, Cursor, Copilot, and 10+ more agents.
Skills
Grouped by what the skill does for you. The Status column is explained under Maturity.
Audit
Read-only. Produces a verdict, never modifies anything.
| Skill | Version | Status | What it does |
|---|---|---|---|
| supply-chain-audit | 1.0.0 | stable | Scans a developer machine for npm/PyPI supply-chain compromise (Shai-Hulud 2.0, Mini Shai-Hulud / TeamPCP, Axios DPRK). Versioned IOC pack, three-phase scan, PASS/FAIL verdict, and 48h bake-period remediation |
Build
Produces a new artifact from scratch.
| Skill | Version | Status | What it does |
|---|---|---|---|
| generate-brand-assets | 1.0.0 | stable | Generates OG images (1200x630) and favicon formats from a project's branding, with brand colors, gradients, PNG/WebP/ICO |
| surface-recon | 0.8.0 | candidate | Maps authorized targets across network, interactive, command, artifact, device, firmware, and runtime planes, with explicit acceptance proofs and consequence gates |
| cli-build | 0.12.0 | candidate | Builds a CLI an agent can operate and a human can supervise. Distribution target first, then the command surface, polished human output by default, and safety proportional to stakes. Delegates TypeScript primitive adoption to the canonical cligentic skill instead of carrying a copied catalog |
| skill-gen | 0.9.0 | deprecated | Generated skills from documentation. See Maturity before installing |
Publish
Orchestrates a release without missing steps.
| Skill | Version | Status | What it does |
|---|---|---|---|
| obsidian-plugin-release | 1.0.0 | stable | Atomic release flow for Obsidian community plugins. Bumps the version across manifest.json, package.json, and versions.json, builds, lints, signs an annotated tag, and triggers a workflow that publishes with build-provenance attestation (SLSA in-toto). Passes the Obsidian Community automated review |
Context
Structures a repository so agents navigate it well.
| Skill | Version | Status | What it does |
|---|---|---|---|
| intent-layer | 1.0.0 | stable | Sets up hierarchical AGENTS.md files so agents navigate your codebase like senior engineers. Built on The Intent Layer by Tyler Brandt |
Maturity
Category and maturity are separate axes. The category says what a skill does; the maturity says how much evidence stands behind it. A build skill can be stable, and an audit skill can be experimental.
The source of truth is maturity.json, which carries the evidence for each status in one sentence.
| Status | Meaning |
|---|---|
stable | Used on real work. Recommended |
candidate | Works, with thin evidence so far |
experimental | Coherent method and trigger boundary, no real-work use yet |
deprecated | Kept for provenance. Not recommended |
How a skill moves:
- Nothing enters as stable. Extracted from work actually done starts at
candidate. Written from documentation starts atexperimental. - Promotion needs a named reason, not a feeling. Which work it ran on, and what it caught.
deprecatedis not deletion. The folder stays and the install command keeps resolving. Anyone who already installed it deserves to find out it is unmaintained rather than hit a dead link.- Demotion is normal. A skill that stopped earning its place says so.
Versioning
Each skill carries a version in its frontmatter, tracking the skill as a document rather than any tool it wraps.
| Bump | Means |
|---|---|
| major | The method changed: a phase added or removed, a reordered flow. Following the old version gives different results |
| minor | Material added, or a claim corrected, without changing the flow |
| patch | Wording, links, typos |
A skill reaches 1.0.0 when it becomes stable: run on real work with the evidence recorded. Candidates stay on 0.x, which is the honest signal that the contract can still move.
Skills that ship from their own repo
A skill that documents one tool belongs with that tool, so it cannot drift from the commands it describes. Those live in the tool's repository:
| Skill | Install |
|---|---|
| skillkit | npx skills add crafter-station/skill-kit |
| spoti-cli | npx skills add crafter-station/spoti-cli |
| sismo-cli | npx skills add crafter-station/sismo-abierto |
| cligentic | bunx --bun skills add Railly/cligentic --skill cligentic |
This repo keeps the skills that are not tied to a single codebase.
Repository structure
skills/<name>/SKILL.md the installable catalog, flat
.claude-plugin/marketplace.json plugin manifest
maturity.json category, status, and evidence per skill
The layout is flat on purpose. The skills CLI discovers skills/<name>/SKILL.md, and skills placed outside that container are invisible to the installer. Measured: a nested skills/<category>/<name>/ layout found 1 of 3 skills in an isolated test, while the flat layout found 3 of 3.
So category is metadata, not a directory. It lives in maturity.json and drives the README grouping, which also means a skill can be recategorized without moving files or breaking a link.
Contributing
- Fork
- Follow the Agent Skills spec
- Add an entry to
maturity.jsonwith the evidence behind its status - PR
License
MIT
File tree
FAQ
crafter-station-skills is a Claude Code plugin with 9 hand-picked skills, indexed on Flowy in the Skill Authoring category. Install it with the command on its page. It includes cli-audit, cli-build, generate-brand-assets. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is crafter-station-skills?
- Agent skills extracted from real work. Each one shipped something first.
- How do I install crafter-station-skills?
- Run these in Claude Code: /plugin marketplace add crafter-station/skills. Then prompt normally.
- Does crafter-station-skills auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is crafter-station-skills free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it