GlaicerGlaicer/skill-picker/SKILL.md

skill-picker

Skill0 starsChanged 3 months agoMITView on GitHub

Select and link existing skills from a local curated collection into a project's configured skill directories. Use when the user asks to pick, recommend, install, or connect collection skills to a project, including bundles and nested skills. Not for downloading or authoring new skills.

3 other projects use a version of this.

Adopted by

Most recently taken up by

nyxandro/skill-picker-skilltheir own version, first seen Nov 8, 2026
trac3r00/agent-skillstheir own version, first seen Aug 26, 2026
qhuang20/skill-pickertheir own version, first seen Apr 6, 2026

Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
qhuang20/skill-picker★ 3same name
nyxandro/skill-picker-skill★ 1same name
trac3r00/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Run from the target project root.
line 12
Very specific:
Read DATABASE.md in the reported source_root.
line 18
Very specific:
If the user named skills or a bundle, resolve those names.
line 19
Distinctive:
Run the picker with the approved names and target project.
line 20
Distinctive:
Verify every resulting link and confirm that no unconfigured skill directories were created.
line 21
Very specific:
Use configured defaults—only .agents/skills unless changed:
line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Skill Picker

Link only the collection skills that the target project needs. .agents/skills is the sole default target; additional targets are opt-in configuration, never inferred from installed harnesses.

Workflow

Run from the target project root. Locate this skill's base directory and run:
```
python3 <skill-base>/scripts/pick_skills.py --show-config
```
Read DATABASE.md in the reported source_root. Treat it as the catalog for names, paths, descriptions, categories, and applicability. If it is missing, stop and report that the configured collection is incomplete.
If the user named skills or a bundle, resolve those names. If the user asks what to pick, inspect the project, shortlist the smallest relevant set from DATABASE.md, explain the recommendation, and wait for approval.
Run the picker with the approved names and target project. Do not add harness-specific targets unless the user requested them or they are present in configuration.
Verify every resulting link and confirm that no unconfigured skill directories were created.

The task is complete when each requested skill resolves to its collection source from every configured target and no unrelated target directory changed.

Configuration

Default configuration:

{
  "source_root": "~/Skills",
  "targets": ["agents"]
}

Store overrides in ~/.config/skill-picker/config.json, or set SKILL_PICKER_CONFIG to another JSON file. SKILL_PICKER_SOURCE_ROOT overrides only the collection path. Command-line flags override both environment and config.

Target aliases:

agents → .agents/skills
claude → .claude/skills
cline → .cline/skills

--target is repeatable and may also contain another project-relative directory. Supplying any --target values replaces the configured target list for that run.

Commands

Use configured defaults—only .agents/skills unless changed:

python3 <skill-base>/scripts/pick_skills.py typescript-best-practices --project-root .

Override the source collection:

python3 <skill-base>/scripts/pick_skills.py impeccable \
  --source-root /path/to/Skills --project-root /path/to/project

Opt into Claude Code as an additional target for one run:

python3 <skill-base>/scripts/pick_skills.py impeccable \
  --target agents --target claude

Names match hyphens and underscores equivalently. A bundle selects every descendant skill recursively. A nested skill name selects only that skill. Existing non-symlink paths are preserved and reported as errors.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free