Claude skills marketplaces
7,265 indexed, 106 of them broken. Repos publishing a marketplace.json.
There is no single directory to use, and the four here divide the market cleanly enough that choosing between them is easy once you know what each one is. aitmpl.com is the broad catalogue: seven artifact kinds, a basket, 1000+ items, and no published submission route. subagents.sh is the narrow one: 40 subagents, one CLI, and the only ordering in this market built on real installs rather than stars. Smithery is not a list at all but hosted infrastructure — 18,965 skills and 715 MCP servers, with auth and credentials handled, free up to 50K RPCs a month. awesome-claude-code is the only curated one, with the only published maturity bar for getting on it and the widest scope of what counts as a resource. The gap all four share is the same one: none publishes that it checks a listed item parses and loads. Smithery has a "Verified" filter without publishing what it tests; awesome-claude-code says outright that its bot "does not review the quality"; the other two publish nothing. A marketplace.json that does not parse is invisible to every one of them, and that is the measurement this index adds.
| Artifact | Score | What the check found | Category | Reach | Last commit |
|---|---|---|---|---|---|
| open-code-reviewalibaba/open-code-review | clean | Code review | 21k stars | today | |
| text-to-cadearthtojake/text-to-cad | clean | Code review | 14k stars | today | |
| Spark-To-Paper-SkillsSpark-To-Paper-Skills/paperjury | clean | Code review | 931 stars | 2 days ago | |
| kicad-happyaklofas/kicad-happy | clean | Code review | 954 stars | 11 days ago | |
| bencherbencherdev/bencher | No license | Code review | 876 stars | 2 days ago | |
| agent-reviewspbakaus/agent-reviews | clean | Code review | 220 stars | today | |
| wardengetsentry/warden | No license | Code review | 394 stars | today | |
| app-store-reviewsafaiyeh/app-store-review-skill | clean | Code review | 286 stars | 10 days ago | |
| pair-reviewin-the-loop-labs/pair-review | clean | Code review | 50 stars | yesterday | |
| u7079256u7079256/paperjury | clean | Code review | 857 stars | 1 months ago | |
| yunomi-pluginskazuph/yunomi | clean | Code review | 20 stars | yesterday | |
| xiaolaixiaolai/bureau | No license | Code review | 20 stars | today | |
| quiveryagizdo/quiver | clean | Code review | 11 stars | today | |
| polyGoldziher/poly | clean | Code review | 9 stars | 2 days ago | |
| pr-inbox-pluginsjmprieur/pr-inbox | clean | Code review | 9 stars | 7 days ago | |
| ai-reviewmrmans0n/ai-review | clean | Code review | 5 stars | today | |
| blockwatchmennanov/blockwatch | clean | Code review | 29 stars | 10 days ago | |
| skill-reviewerTerryc21/skill-reviewer | clean | Code review | 24 stars | 9 days ago | |
| code-quality-atlasbrandondees/code-quality-atlas | No license | Code review | 8 stars | today | |
| safewordArcadeAI/safeword | No license | Code review | 8 stars | today | |
| ardanlabsardanlabs/skills | clean | Code review | 4 stars | 5 days ago | |
| vosslab-skillsvosslab/vosslab-skills | clean | Code review | 2 stars | today | |
| river-review-marketplaces977043/river-review | clean | Code review | 2 stars | today | |
| p5ych0-toolsp5ych0/watch-pr-skill | clean | Code review | 2 stars | today | |
| pip-skillsppryde/pip-skills | clean | Code review | 2 stars | 7 days ago | |
| cpython-review-toolkitdevdanzin/cpython-review-toolkit | clean | Code review | 9 stars | 22 days ago | |
| andthenIT-HUSET/andthen | No license | Code review | 4 stars | today | |
| claude-pr-autopilotMarcinSufa/claude-pr-autopilot | clean | Code review | 1 stars | 7 days ago | |
| beast-modeVibesDIY/beast-mode | clean | Code review | 2 stars | 13 days ago | |
| colorpulse6-skillscolorpulse6/claude-skills | No license | Code review | 1 stars | 7 days ago | |
| dnbgdbaggott/claude-plugins | clean | Code review | no signal | today | |
| sharpenburitica/sharpen | clean | Code review | no signal | today | |
| buildjameshemson/build | clean | Code review | no signal | today | |
| manoliiManolii-org/ai-starter-pack | clean | Code review | no signal | yesterday | |
| ebertsamrith-s/ebert | clean | Code review | no signal | 2 days ago | |
| jamescostajamescosta/review-loop | clean | Code review | no signal | yesterday | |
| ffssuinaf/ffss | clean | Code review | no signal | today | |
| app-store-reviewintelli-verse-x/agent-skills | clean | Code review | no signal | 3 days ago | |
| slop-reviewdbachelder/slop-review | No license | Code review | 47 stars | 2 months ago | |
| code-review-toolkitdevdanzin/code-review-toolkit | No license | Code review | 5 stars | 12 days ago | |
| opensource-review-suitepriyank766/OpenSource-SKILL | clean | Code review | 1 stars | 16 days ago | |
| pr-review-bottunderadev/pr-review-bot | No license | Code review | no signal | 6 days ago | |
| simplified-technical-englishgabrieltorresgamez/simplified-technical-english | No license | Code review | no signal | 7 days ago | |
| idea-to-productionagentic-underground/idea-to-production | No license | Code review | no signal | today | |
| erc-reviewborgr/erc-review | No license | Code review | no signal | today | |
| michaelhvisser-aimichaelhvisser/ai | No license | Code review | no signal | today | |
| joust-enginerobanderson/joust-engine | No license | Code review | 1 stars | 16 days ago | |
| dryrunsecurityDryRunSecurity/external-plugin-marketplace | No license | Code review | 1 stars | 27 days ago |
What the check on a marketplace looks for
A marketplace is a repository with a .claude-plugin/marketplace.json that Claude Code can add as a plugin source. These are the ones the nightly run found, ranked by whether the manifest parses, how many plugins it actually lists, and whether the repository is still being worked on. A marketplace that lists nothing is not a small problem — it is a source that adds nothing when you add it.
What is a Claude Code marketplace?
A repository publishing a marketplace.json manifest, which Claude Code can add directly so its plugins become installable. That mechanism is the layer underneath every directory on this page — aitmpl.com, subagents.sh, Smithery and awesome-claude-code are all ways of finding things that ultimately live in a repository. This index takes the mechanism as the unit: it finds every repository publishing a marketplace.json, counts the plugins each carries, checks whether the manifest is valid, and re-runs that every night.
Which Claude Code directory should I use?
Use aitmpl.com for breadth — it is the only one carrying all seven artifact kinds under one search, with a stack you add to. Use subagents.sh for subagents specifically, because its CLI writes straight into .claude/agents/ and its ranking is install count from real CLI telemetry. Use Smithery when the thing you want is a connection to a service rather than a file, because it runs the auth and credentials for you and its catalogue is the largest by a wide margin. Read awesome-claude-code when you are still working out what exists, because it is the only hand-picked list and the only one covering essays, field guides, alternative clients and cost tooling that no installer can install.
Do any of these check that a listed item works?
None of the four publishes a load check. Smithery offers a "Verified" filter on its skills catalogue but does not publish what verification tests, so what a reader can confirm is that a check exists, not what it does. awesome-claude-code is the most candid about it: its maturity gate is mechanical and its quality review is not — "the bot is a mechanical form-validator, it does not review the quality of the recommended resource", and "recommendations are reviewed in a best-effort way". aitmpl.com and subagents.sh publish nothing on the subject on the pages read. Where a cell in the table above says "Not published", it means exactly that: the page was read and did not carry the figure, not that the check does not exist.
How are these directories ordered?
Three different answers and one absence, and the difference matters more than it sounds. subagents.sh sorts by install count gathered from its own CLI — "we use anonymous telemetry from CLI installations to track popularity" — which is the only ordering here that measures the artifact rather than its repository. aitmpl.com offers two sorts, "Most Popular" and alphabetical. Smithery's skills catalogue prints per-item install figures but publishes no sort order and offers no sort control. awesome-claude-code groups by category with no ordering inside a category, which is the correct behaviour for a curated list and useless as a ranking.
How does SkillWorks decide what to list?
By crawling rather than by curation, and then by scoring. Every repository publishing a Claude Code marketplace.json is a candidate, every skill, subagent and plugin inside it is re-read, and each one gets a published 0–100 score for whether it actually loads. Nothing is hand-picked and nothing is paid for. That is deliberately the opposite trade-off from awesome-claude-code, which is hand-picked and says so, and it is why the two are worth reading together: a curated list tells you what a person thought was good, and an index tells you what is actually there and what state it is in.
