Agent skill

Search Skills

by clacky-ai in clacky-ai/openclacky

Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword.

MITAuto-check passedAI & LLM Engineering

Install Search Skills

skills CLI
$ npx skills add clacky-ai/openclacky --skill search-skills -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install clacky-ai/openclacky search-skills --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/clacky-ai/openclacky.git skills-src && mkdir -p .claude/skills && cp -r skills-src/lib/clacky/default_skills/search-skills .claude/skills/search-skills && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
search-skills
GitHub stars
1.2k
Token cost
~619 tokens
SKILL.md length
254 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword.

  • Works in 3 steps: Extract keywords → Match against the inventory above → Return a ranked summary
  • Mentions a domain not covered by visible skills
  • SKILL.md covers Complete Skill Inventory, Workflow and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Search Skills is an agent skill from clacky-ai/openclacky. Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword. Use this whenever you suspect a fitting skill might exist but is not listed in your system prompt — for example before building a new skill, when the user mentions a domain not covered by visible skills, or after seeing the (N more skills installed) hint. Triggers on phrases like search skills, find a skill for, is there a skill that, 查找skill, 有没有skill做.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Prompt engineering. The repository describes itself as: The most Token-efficient open-source AI Agent. The licence is MIT.

When your agent uses it

  • Mentions a domain not covered by visible skills
  • After seeing the (N more skills installed) hint
  • Phrases like search skills
  • Find a skill for

Example prompts

  • “/search-skills”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Extract keywords
  2. Match against the inventory above
  3. Return a ranked summary

What it can do on your machine

Read from SKILL.md and the folder at commit e16b639. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Search Skills loads about 619 tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 254 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~619

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from clacky-ai/openclacky at commit e16b639, republished under its MIT licence (© clacky-ai). 254 words, ~619 tokens.

Download SKILL.mdSave it as .claude/skills/search-skills/SKILL.md (or your agent's skills folder).
name
search-skills
description
Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword. Use this whenever you suspect a fitting skill might exist but is not listed in your system prompt — for example before building a new skill, when the user mentions a domain not covered by visible skills, or after seeing the (N more skills installed) hint. Triggers on phrases like search skills, find a skill for, is there a skill that, 查找skill, 有没有skill做.
name_zh
搜索技能
description_zh
按关键词在所有已安装的技能中查找合适的技能。
disable-model-invocation
false
user-invocable
true
fork_agent
true
auto_summarize
true
forbidden_tools
write, edit, terminal, web_search, web_fetch, browser

Search Skills Subagent

You are a Skill Search Subagent. Given a keyword or topic from the parent agent, scan the complete list of installed skills below and return the best matches.

The AVAILABLE SKILLS section in the parent agent system prompt is capped (~30 entries). The list below is the FULL list — pre-loaded for you, no scanning required. Your job is to look beyond that cap so the parent does not redundantly create a new skill when one already exists.

Complete Skill Inventory

This list was pre-loaded — do NOT re-scan the filesystem or call any tools.

<%= all_skills_meta %>

Workflow

Step 1 — Extract keywords

Pull 2-4 keywords from the input task. Both English and Chinese terms are valid (skill descriptions are bilingual).

Step 2 — Match against the inventory above

For each skill in the inventory, judge relevance against the keywords:

  • Strong match: keyword appears in the skill name or clearly in the description's purpose statement
  • Weak match: keyword appears only in the trigger examples or peripheral mentions
Step 3 — Return a ranked summary

Return at most 5 results, strongest matches first:

Found N matching skill(s) for: <keywords>

1. <name>  (<source>)
   <description trimmed to ~200 chars>

2. ...

If nothing genuinely matches, return exactly: No installed skill matches: <task>

Rules

  • Do NOT invoke any tool. The inventory above is authoritative; just match and return.
  • Do NOT recommend creating a new skill — that is the parent agent's call.
  • If the task is vague, return what genuinely matched, do not invent relevance.
  • Default skills (built-in) are part of the inventory but typically also visible to the parent — flagging them is still useful as a reminder.

© clacky-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in lib/clacky/default_skills/search-skills of clacky-ai/openclacky.

Open the folder on GitHubat commit e16b639

Compare with similar skills

Search Skills next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Search Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Search Skills this skillclacky-ai/openclacky1.2k—~619Automated safety check: PassMIT
Prompt Improverseverity1/claude-code-prompt-improver1.9k1 repos~1.7kAutomated safety check: PassMIT
Prompt Engineering Patternsynulihao/AgentSkillOS61814 repos~1.7kAutomated safety check: PassNone
Patch CreationPiebald-AI/tweakcc2.5k—~1.6kAutomated safety check: PassMIT
Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit2603 repos~1.4kAutomated safety check: PassCustom licence
Codex Fable5baskduf/FableCodex437—~1.6kAutomated safety check: PassAGPL-3.0

Similar skills

  • Prompt Improver

    severity1/claude-code-prompt-improver

    This skill enriches vague prompts with targeted research and clarification before execution.

    1.9k GitHub starsUsed in 1 repo~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Prompt Engineering Patterns

    ynulihao/AgentSkillOS

    Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.

    618 GitHub starsUsed in 14 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Patch Creation

    Piebald-AI/tweakcc

    Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc.

    2.5k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Senior Prompt Engineer

    maslennikov-ig/claude-code-orchestrator-kit

    Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

    260 GitHub starsUsed in 3 repos~1.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Codex Fable5

    baskduf/FableCodex

    Apply a Claude Fable 5 inspired operating style inside Codex.

    437 GitHub stars~1.6k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.

    40k GitHub stars~1.3k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed

More from clacky-ai/openclacky

All 20 skills in this repo
  • Skill Add

    clacky-ai/openclacky

    Install skills from a zip URL or local zip file path. An agent skill from clacky-ai/openclacky.

    1.2k GitHub stars~560 tokensUpdated today
    Auto-check passed
  • Media Gen

    clacky-ai/openclacky

    Generate or edit images, videos, or audio in the current task.

    1.2k GitHub stars~7.5k tokensUpdated today
    Auto-check passed
  • Browser Setup

    clacky-ai/openclacky

    Configure the browser tool for Clacky. An agent skill from clacky-ai/openclacky.

    1.2k GitHub stars~3.1k tokensUpdated today
    Auto-check: notes
  • Cron Task Creator

    clacky-ai/openclacky

    Create, manage, and run scheduled automated tasks (cron jobs) in Clacky.

    1.2k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Deploy

    clacky-ai/openclacky

    Deploy Rails applications to Railway. An agent skill from clacky-ai/openclacky.

    1.2k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • MCP Manager

    clacky-ai/openclacky

    Manage MCP (Model Context Protocol) servers for openclacky: add, list, probe, remove, reconfigure.

    1.2k GitHub stars~3k tokensUpdated today
    Auto-check passed

Questions about Search Skills

What does Search Skills do?

Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword. Search Skills is an agent skill from clacky-ai/openclacky. Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword.

When should I use Search Skills?

Search Skills fits situations like: mentions a domain not covered by visible skills; after seeing the (N more skills installed) hint; phrases like search skills; find a skill for.

How do I install Search Skills in Claude Code?

Run `npx skills add clacky-ai/openclacky --skill search-skills -a claude-code`. Or copy the skill folder (lib/clacky/default_skills/search-skills in clacky-ai/openclacky) into .claude/skills/search-skills in your project. Claude Code loads it when a task matches its description.

How do I install Search Skills in Codex?

Run `npx skills add clacky-ai/openclacky --skill search-skills -a codex`. Or copy the skill folder (lib/clacky/default_skills/search-skills in clacky-ai/openclacky) into .agents/skills/search-skills in your project. Codex loads it when a task matches its description.

Can I use Search Skills in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add clacky-ai/openclacky --skill search-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search-skills, .gemini/skills/search-skills, .github/skills/search-skills and .opencode/skills/search-skills in your project.

What does Search Skills need to run?

SKILL.md names no scripts, command-line tools or credentials: Search Skills is instructions for the agent only.

Does Search Skills access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Search Skills safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Search Skills use?

Search Skills is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Search Skills use?

About 619 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Search Skills?

Skills that share tags, products or a category with Search Skills: Prompt Improver (severity1/claude-code-prompt-improver, 1.9k stars), Prompt Engineering Patterns (ynulihao/AgentSkillOS, 618 stars), Patch Creation (Piebald-AI/tweakcc, 2.5k stars) and Senior Prompt Engineer (maslennikov-ig/claude-code-orchestrator-kit, 260 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Search Skills?

clacky-ai (a GitHub organization) maintains it in clacky-ai/openclacky, which has 1,204 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 10, 2026.

Source: clacky-ai/openclacky on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.