skill-search

skill-search is a skill for Claude Code from danielLublinsky/Skill-Atlas. It costs 150 tokens per session (602 once invoked), scanned A, original, Apache-2.0.

A skill that searches a local library of coding-agent skills to find one suited to the current task. It checks categories and detailed entries before work begins.

In plain words
What is it for?
Use it to identify the best available skill for a task, report when the search is unavailable, and then continue with the selected skill or without one.
Why use it?
It helps avoid starting a non-trivial task without relevant instructions, including tasks such as coding, debugging, documentation, planning, and reviews.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skill-atlas plugin — 2 skills, 1 command, 2 hooks shipped together

Good fit Use it to identify the best available skill for a task, report when the search is unavailable, and then continue with the selected skill or without one.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daniellublinsky/skill-atlas/skill-search
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 danielLublinsky/Skill-Atlas --skill skill-search
Clone the repo
git clone --depth 1 https://github.com/danielLublinsky/Skill-Atlas

Made for: Claude Code.

Or install skill-atlas, the plugin that ships this one along with the rest of its 2 skills, 1 command, 2 hooks.

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 skill-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/daniellublinsky/skill-atlas/skill-search/github.svg)](https://agentmods.dev/skills/daniellublinsky/skill-atlas/skill-search)
Your own site
<a href="https://agentmods.dev/skills/daniellublinsky/skill-atlas/skill-search"><img src="https://agentmods.dev/badge/skills/daniellublinsky/skill-atlas/skill-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/daniellublinsky/skill-atlas/skill-search"><img src="https://agentmods.dev/badge/skills/daniellublinsky/skill-atlas/skill-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 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 $0.00150 $0.00602
Opus 5 $0.00075 $0.00301
Sonnet 5 $0.00030 $0.00120
Haiku 4.5 $0.00015 $0.00060

Measured 12d ago against content hash 711523b3b340, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-search 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 12d 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/skill-search/SKILL.md · 57 lines

What it actually says

Read _index.md, then one shard, from ./.claude/skill-atlas/catalog/ (cwd-relative). Missing → say search is unavailable, suggest /skill-atlas, work without a skill; never use another directory's catalog.

1 — category

Index lines are name(count) — description — tokens. The description decides; its …; see <other> carve-out is the strongest signal — treat it as routing. Tokens only corroborate: the list truncates, so a hit favours a category and a miss proves nothing. Counts overlap; a right bucket suffices.

2 — shard

Entries are ## <id> [enabled|searchable] (stale), description, path, and also in: — its other categories, where a sharper sibling may live. Prefer specific over broad; between near-identical entries take [enabled], then the sharper description, silently.

A second shard only if the winner's also in: names an unread category, or nothing rose above weak. Never a third. uncategorized.md counts; serving from it, say so and suggest /skill-atlas.

3 — name it, then work

One line, then continue the task in the same turn: Using <id>. — or No skill fits — proceeding without one.

Nothing else, ever: never narrate the search, name a category or shard, list runners-up, echo a path, announce intent, ask permission, or summarise after. Reading a [searchable] SKILL.md is internal work.

Using it

[enabled] → Skill tool. [searchable] → Read that path and follow it as plain instructions; allowed-tools and auto-triggering do not apply. Never look outside catalog/ — absent from every shard means disabled by choice, and "no skill fits" is a first-class answer. Never force one.

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. 12d ago First seen · 57 lines · 150 tokens per session scan A 711523b3b340

Subscribe to this mod's changes

skill-search is a skill published in the GitHub repository danielLublinsky/Skill-Atlas (23 stars, last pushed 26d ago), licensed Apache-2.0. It adds 150 tokens to every session and 602 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

tauri-updater

Use when adding software auto-update to a Tauri 2 desktop app, or when users ask about tauri-plugin-updater integration, app update checking, distinguishing installer vs portable builds for updates, or generating update manifests for GitHub Releases.

luochang212/skill-zoo · 53 tokens

app-release

Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.

luochang212/skill-zoo · 43 tokens

worth-fix

A verification and decision-making guide for checking whether bug reports, claims, proposals, or refactoring ideas are true and worth acting on.

luochang212/skill-zoo · 134 tokens

npm-release

Use when publishing or preparing to publish an npm package from this repository, especially the Skill Zoo CLI package under packages/cli. Also use when npm publish fails because of duplicate versions, npm authentication, browser authentication, dist-tag propagation, tarball contents, bin entry issues, or…

luochang212/skill-zoo · 66 tokens

antv-x6-editor

A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.

antvis/chart-visualization-skills · 253 tokens

gpt-vis

A chart-generation tool that recommends visual formats for data and produces either chart settings or runnable code. It uses GPT-Vis, a library for rendering data visualisations.

antvis/chart-visualization-skills · 63 tokens