Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Skillsmp Search

ASecurity

Use when finding, browsing, or installing community skills, or when a needed capability might exist as a marketplace skill. Triggers on "find a skill", "search skills", "install skill", "skillsmp", or "marketplace".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashreacttestinggitapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Lu1sDV/skillsmd --skill skillsmp-search --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skillsmp Search?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skillsmp Search
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lu1sdv-skillsmp-search/badge)](https://www.skillsdirectory.com/skills/lu1sdv-skillsmp-search)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: skillsmp-search
description: Use when finding, browsing, or installing community skills, or when a needed capability might exist as a marketplace skill. Triggers on "find a skill", "search skills", "install skill", "skillsmp", or "marketplace".
---

# SkillsMP Search & Installer

Search 11,000+ community skills and install them locally.

## When to Use

- User asks to find/search/install a skill
- User needs a capability that likely exists as a community skill

**Not for:** Project-specific conventions (CLAUDE.md), already-installed skills.

## Quick Reference

| Step | Action |
|------|--------|
| Search | `GET https://skillsmp.com/api/skills?q=<query>&sortBy=recent` |
| Present | Show top 3-5 results with name, author, description, install count |
| Install | `npx skills add <author>/<repo>` or copy to `~/.claude/skills/` |
| Verify | Ask Claude "What skills are available?" |

## API Config

- **Base**: `https://skillsmp.com/api/v1/skills`
- **Key**: `$SKILLSMP_API_KEY` environment variable
- **Auth**: `Authorization: Bearer $SKILLSMP_API_KEY` | **Limit**: 500/day

## Search

**Keyword** (fast, ~500ms) - specific terms, sort by stars:
```bash
curl -s "https://skillsmp.com/api/v1/skills/search?q=QUERY&limit=30&sortBy=stars" \
  -H "Authorization: Bearer $SKILLSMP_API_KEY"
```
Response: `data.skills[]` → `id`, `name`, `author`, `description`, `githubUrl`, `stars`, `updatedAt`

**AI Semantic** (smart, ~5s) - natural language, conceptual queries:
```bash
curl -s "https://skillsmp.com/api/v1/skills/ai-search?q=QUERY" \
  -H "Authorization: Bearer $SKILLSMP_API_KEY"
```
Response: `data.data[]` → `score` (0-1) + `skill` object. **Skip entries with `skill: null`.**

| Query type | Mode |
|------------|------|
| Specific tech ("react testing") | Keyword, `sortBy=stars` |
| Natural language / vague | AI semantic |
| "newest", "latest", "recent skills" | Keyword, `sortBy=recent` |

Fall back to keyword if AI returns few results.

## Present & Choose

Show **ALL** found skills in the ranked table — never truncate or omit results. Then **use `AskUserQuestion` to let user pick** - never auto-select.

Always include a **"Compare to find best"** option in addition to numbered skill choices:

```
| # | Skill | Author | Stars | Description |
|---|-------|--------|-------|-------------|
| 1 | name  | @author | 42   | ...         |
```

Include relevance score for AI results.

AskUserQuestion options: numbered skills + **"Compare to find best"**

### Compare to find best

When user selects "Compare to find best":

1. **Gather criteria**: Ask user to expand needs/priorities (optional)
2. **Load evaluation rubric**: Read `external/writing-skills-rubric.md` for the full scoring framework (6 dimensions, 0-2 each, /12 total)
3. **Fetch & evaluate**: Download SKILL.md from top candidates, score per rubric dimensions:
   - Description quality (CSO) | Token efficiency | Structure & organization
   - Degrees of freedom | Domain value | Code & examples
4. **Present comparison**: Side-by-side table with per-dimension scores (total /12), SKILL.md word count (`wc -w`), and 1-sentence key finding per candidate
5. **Final decision**: Use `AskUserQuestion` to let user pick the winner

Consult `external/anthropic-skills-best-practices.md` for edge-case evaluation details only.

## Install

After user picks:
1. **Transform URL**: `github.com/U/R/tree/B/P` → `raw.githubusercontent.com/U/R/B/P/SKILL.md` (replace domain, remove `/tree` from `/tree/BRANCH` leaving `/BRANCH`)
2. **Fetch**: `curl -s "RAW_URL"`
3. **Ask scope** via `AskUserQuestion`: global (`~/.claude/skills/`) or project-local (`.claude/skills/`)
4. **Save** as `{name}/SKILL.md`, verify frontmatter, confirm activation

## Mistakes & Errors

| Issue | Fix |
|-------|-----|
| Auto-selecting without asking | Always `AskUserQuestion` for user choice |
| Raw URL 404 | Verify `/tree` removed, domain replaced; try lowercase `skill.md` |
| `skill: null` in AI results | Filter out before presenting |
| 0-star vs high-star conflict | Cross-check both search modes; review content of 0-star skills before installing |
| 401 | Check `$SKILLSMP_API_KEY` is set — run `echo $SKILLSMP_API_KEY` |
| 429 | Daily quota hit, retry tomorrow |
| Curl exit 56 | Transient network error, retry |

## Common Mistakes

| Mistake | Fix |
|---------|-----|
| Installing without checking existing skills | Run "What skills are available?" first |
| Using wrong install path | Skills go in `~/.claude/skills/<skill-name>/SKILL.md` |
| Searching too broadly ("testing") | Be specific: "playwright e2e testing" |
| Installing multiple overlapping skills | Check descriptions for overlap before installing |
| Forgetting to verify after install | Always confirm skill loaded with a test prompt |

Attribution

Lu1sDVLu1sDV
View sourceMore from Lu1sDV →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →