⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

skills-library

@lindblomstefan⭐ 3 stars

Get guided AI skill recommendations for your repo or team.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 3 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

skills-library

A Claude Code skill that runs a guided interview and recommends the right AI skills for your repo or team.

If it's useful, a star helps others find it.

The skill runs entirely inside Claude — no CLI, no server, no external dependencies. The interview, recommendations, onboarding, and feedback flows are all driven by SKILL.md and Claude Code's native tooling.

Install

Paste this into any Claude Code session:

Install the skills-library skill from https://github.com/lindblomstefan/skills-library and set it up so I can type /skills-library to start it.

Claude will clone the repo, copy .claude/skills/skills-library/ into ~/.claude/skills/, and add the trigger lines to ~/.claude/CLAUDE.md. Nothing else runs.

Use

Type /skills-library in any Claude Code session to start the guided interview. Claude will:

  1. Check if you're in a git repo and offer to inspect it
  2. Ask how you want to share context (describe freely, problem only, or chat)
  3. Ask narrowing questions — work area, stack, constraints, sensitivity
  4. Recommend up to 5 skills with license state, status, and blockers

Claude will also suggest /skills-library automatically when you ask what AI skills, tools, or AI-powered workflows to use for a project or team.

After using a recommended skill, say "I have feedback on [skill name]." Claude appends a dated entry to a local feedback file at ~/.claude/skills/skills-library/feedback/<skill-id>.md. Once a skill reaches 3 entries it is marked validated — confirmed working in practice, not universally recommended.

To read the feedback for any skill, ask Claude: "Show me the feedback for graphify" — or open the file directly.

Catalog

Over 100 skills tracked across all stages. The skill recommends from the full catalog — status is always shown so you know the confidence level.

See CATALOG.md for the full list. Skills move from candidate → evaluating → approved through real usage and community feedback.

Contributing

This library is still young. The catalog has over 100 skills but very few have real-world feedback yet. That is the gap. If you have feedback of a skill that is not in the library, add it first.

The most valuable thing you can do is use a skill and leave feedback. No GitHub account needed:

  • Give feedback on a skill — use a skill, then say "I have feedback on [skill name]" in any Claude Code session. Claude appends a dated entry to a local file. Once a skill reaches 3 real-session entries it is marked validated. This is how the library earns trust.
  • Add a skill — type /skills-library and say "I have a skill to add." Only when there is something genuinely missing.
  • Improve the library — fork, edit, open a PR. Run npm test before pushing.

See CONTRIBUTING.md for the validation model and what makes a good skill addition.

This repository

The installable artifact is the skill folder:

.claude/skills/skills-library/
├── SKILL.md          # Interview, recommendation, onboarding, and feedback instructions
├── VERSION           # Used for update detection
├── feedback/         # Per-skill feedback files; read before recommending
│   ├── _template.md  # Template for new skills
│   ├── gstack.md
│   └── graphify.md
├── agents/           # Claude agent descriptor
└── references/       # Catalog overview for offline use

The rest of the repo is catalog governance tooling — YAML manifests, evaluation runs, and validation scripts. It is not part of the installed skill.

catalog/      # Library skill manifests and taxonomies
evaluations/  # Evaluation runs and evidence
tools/        # Catalog validation and guardrail checks
docs/         # Engineering decisions and guardrails

// HOW IT'S BUILT

KEY FILES

.claude/skills/skills-library/SKILL.mdREADME.md

// REPO STATS

3 stars

// SHARE

Share on XShare on LinkedIn