find-plugin
Helps users discover and install Claude Code plugins from the pleaseai marketplace. Use this skill whenever a user asks "how do I do X", "find a plugin for X", "is there a plugin that can...", "recommend a plugin", "what plugins are available", wants to extend Claude Code capabilities, or mentions a technology/framework and could benefit from a plugin they haven't installed yet. Also use when the user is stuck on a task that an available plugin could solve, even if they don't explicitly ask for a plugin.
What this skill does
# Find Plugin
Search the pleaseai marketplace to discover and recommend Claude Code plugins that match the user's needs.
## How It Works
The marketplace provides two layers of discovery:
1. **Plugin catalog** — the marketplace manifest lists every available plugin with its name, description, category, and keywords.
2. **Skill index** — installed plugins expose skills (SKILL.md files) that describe specific capabilities in detail. Searching skill descriptions surfaces more precise matches than plugin metadata alone.
## Step 1: Read the Marketplace Catalog
```bash
cat ~/.claude/plugins/marketplaces/pleaseai/.claude-plugin/marketplace.json
```
Parse the `plugins` array. Each entry contains:
- `name` — plugin identifier (used in install command)
- `description` — what the plugin does
- `category` — broad domain (framework, tooling, database, ai, etc.)
- `keywords` — searchable tags
## Step 2: Search Installed Plugin Skills
Skills offer richer descriptions than the top-level plugin metadata. Scan skill files for matches:
```bash
# List all available skill directories
find ~/.claude/plugins/marketplaces/pleaseai/plugins/*/skills -maxdepth 1 -type d 2>/dev/null
# Search skill descriptions for the user's query terms (covers both skills/ and .agents/skills/ layouts)
grep -rilFi "<search-terms>" ~/.claude/plugins/marketplaces/pleaseai/plugins/*/{skills,.agents/skills}/*/SKILL.md 2>/dev/null
```
Read the SKILL.md frontmatter (`name` and `description` fields) of matching skills to understand what each one provides.
## Step 3: Match and Rank
Score each plugin against the user's query:
1. **Direct keyword match** — plugin name, keywords, or category directly matches the query
2. **Skill-level match** — a skill description within the plugin matches the query
3. **Semantic match** — the plugin's description addresses the user's underlying need even without exact keyword overlap
Prioritize plugins that solve the user's immediate problem over tangentially related ones. Deduplicate the combined results from Step 1 and Step 2 before ranking — the same plugin may appear in both the catalog and skill search.
## Step 4: Present Recommendations
For each recommended plugin, show:
```
**{plugin-name}** — {description}
Category: {category}
Install: claude plugin install {plugin-name}@pleaseai
```
Group results by relevance:
- **Best matches** — directly address the user's need
- **Related** — might be useful depending on context
If a plugin is already installed, indicate that:
```
**{plugin-name}** (installed) — {description}
```
Check installed status from the installed plugins registry:
```bash
jq -r '.plugins | keys[]' ~/.claude/plugins/installed_plugins.json
```
Check if `{plugin-name}@pleaseai` appears in the output. A plugin is installed if its key exists in this file.
## Step 5: Offer Installation
After presenting recommendations, offer to install:
> "Want me to install any of these? Just say which ones."
Install with:
```bash
claude plugin install {plugin-name}@pleaseai
```
## When No Plugin Exists
If no plugin matches the user's need:
1. Say so clearly — don't force a bad match
2. Offer to help directly with the task using available tools
3. If the need is common enough, suggest it could become a plugin
## Plugin Categories
Quick reference for the types of plugins available:
| Category | Examples |
|----------|----------|
| **Framework** | nuxt, vue, react, next, vitepress, slidev, tiptap |
| **Mobile** | flutter, react-native |
| **Database** | prisma, supabase, mcp-neo4j |
| **Tooling** | vite, pnpm, turborepo, tsdown, gatekeeper, ast-grep |
| **AI** | nanobanana, ai-sdk, mastra, gemini |
| **Monitoring** | grafana, sentry, posthog |
| **Cloud/Deploy** | firebase, vercel |
| **Payments** | stripe, tosspayments, revenuecat |
| **Browser** | chrome-devtools-mcp, agent-browser, playwright-cli |
| **Productivity** | google-workspace, notion |
| **Security** | gemini-cli-security |
| **Review** | code-review, cubic |
| **Document** | markitdown, edgeparse, fetch |
| **Development** | plugin-dev, mcp-dev, please-plugins, git-ai |
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.