skill-search

skill-search is a Skill discovery & installation skill for AI agents, published by danielLublinsky in the Skill-Atlas repository on GitHub. Skillspace rates skill-search D (59/100) and it passed the safety scan; the rating is based on static analysis only.

Find the best skill for the current task across the entire skill library, including the dormant majority whose descriptions are never loaded into context. Use this before starting any nontrivial task — coding, debugging, git operations, planning, reviewing, writing docs, building UI, handling data or config — even when no loaded skill seems relevant and even when the user does not name a tool or domain: the library usually holds a specialist that stays invisible until searched. Also use when asked whether a skill exists for something. Returns one match: invoke it with the Skill tool if enabled, otherwise read the SKILL.md at the returned path and follow it. Skip only for trivial one-step requests, or when an already-loaded skill obviously covers the task.

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
23

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.