agentleFS
bakhod1rbakhod1r/awesome-agents/.claude/skills/marketplace/SKILL.md

marketplace

Skill0 starsChanged 3 months agoMITView on GitHub

Install external Claude Code plugins from official marketplaces, and install this repository's own agent plugins. Use when the user wants a capability this roster does not cover, asks about plugins or marketplaces, or wants to share these agents with a team.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use release.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the source before installing anything that touches production credentials, deploys, or customer data.

    line 72
  2. Very specific:

    Prefer vendor-official plugins (datadog, mongodb) over community forks of the same thing.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Marketplaces

Plugins are installed, never copied into this repository. A vendored plugin never receives upstream fixes and silently rots.

This repository is a marketplace

/plugin marketplace add <your-org>/awesome-agents
/plugin install agent-workflow@awesome-agents      # commands + skills
/plugin install security-team@awesome-agents       # one team's agents

One plugin per team, plus agent-workflow for the shared commands and skills. plugins/ and .claude-plugin/marketplace.json are generated — run python3 scripts/generate.py.

Official Anthropic marketplaces

Claude Code adds claude-plugins-official automatically on first interactive start.

/plugin marketplace add anthropics/skills
/plugin marketplace add anthropics/claude-plugins-community
/plugin                                            # browse and install

What to install, by gap

These fill gaps this roster deliberately does not cover: vendor-specific tooling and live data access. Verify the plugin still exists with /plugin before recommending it — this table was accurate when written and marketplaces change.

NeedPluginPairs with
Cloud build and deployaws-core, azure, cloudflareplatform-engineer, cloud-operations-engineer
Observability queriesdatadog, grafana-mcp, honeycomb, newrelicobservability-engineer, site-reliability-engineer
Database accessmongodb, clickhouse, neon, cockroachdb, duckdb-skillsdatabase-engineer, database-architect
Security scanningclaude-security, aikido, 42crunch-api-security-testingapplication-security-engineer, devsecops-engineer
Issue trackinglinear, atlassian, github, gitlabtechnical-project-manager, product-owner
Design handofffigma, canvaproduct-designer, frontend-engineer
LLM tracing and evalslangfuse-observability, mlflow, deepevalai-evaluation-engineer, llmops-engineer
Documentation sitesmintlifytechnical-writer
Browser automationchrome-devtools-mcp, browser-useweb-ux-quality-engineer
Feature flagsgrowthbook, confidencerelease-manager

The division of labour

A plugin supplies tools and data access. This roster supplies judgement.

User: "Why did checkout latency spike at 14:00?"

  datadog plugin        → fetches the traces and metrics       (capability)
  site-reliability-eng  → reads them, forms a hypothesis,
                          checks it against the deploy log,
                          states what is verified vs inferred  (judgement)

Neither alone is enough. The plugin without the agent returns a wall of metrics. The agent without the plugin reasons about data it cannot see — which is the failure mode you most want to avoid.

Security

Marketplace plugins are third-party code with tool access running in your repository.

  • Read the source before installing anything that touches production credentials, deploys, or customer data.
  • Prefer vendor-official plugins (datadog, mongodb) over community forks of the same thing.
  • A plugin that bundles MCP servers can make network calls you did not initiate. Check what hosts.
  • Install at the narrowest scope that works — project over user, when the plugin is project-specific.

Anti-patterns

Anti-patternWhy it fails
Copying a plugin's files into .claude/No updates, no security fixes, silent divergence
Installing a plugin because the name matchedPlugins carry tool permissions; read first
Installing 20 plugins "to be ready"Each adds context and tool surface; install on demand
Assuming a plugin replaces an agentIt supplies data, not the decision about what the data means
Recommending from memoryMarketplaces change. Check /plugin first.

Done when

  • The gap is named before a plugin is proposed.
  • The plugin's existence was verified with /plugin, not recalled.
  • The agent that will use its output is named.
  • Security implications stated for anything touching credentials or production.
  • Nothing was vendored.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.