django-mcp
7873MCP server Claude CodeCodexCursor +2
django-mcp adds MCP tool hosting to Django. Runs locally from the django-mcp Python package.
not rated 72 1y ago A
tokens not measured
original MIT archived
Skill Claude CodeCodex
Generate Gmail-compatible HTML performance weekly status reports from Argus CLI data. Use when asked to produce a weekly perf summary, create a performance status email, aggregate latency and throughput results across enterprise perf tests, or generate an HTML report for stakeholders. Covers…
not rated 72
changed 4d ago A 90 tokens
AGPL-3.0
with-md-share
7875Skill Claude CodeCodex
Create shareable markdown links for collaboration with humans. Share plans, documents, reports, and drafts as beautiful editable web pages. Use when the user needs to review, comment on, or iterate on markdown content in a browser — such as project plans, proposals, meeting notes, or any document that benefits from…
not rated 72 10d ago A 121 tokens
original MIT
pond-add-adapter
7876Skill Claude CodeCodex
Playbook for adding a new source-agent adapter to pond - spec the format from the upstream writer, capture a sandboxed fixture, implement the bidirectional codec, and prove conformance. Use when adding an adapter under packages/pond/src/adapter/ or reworking an existing one.
not rated 72
+6 3d ago A 62 tokens
original Apache-2.0
agent-skills
7877Plugin Claude Code
Bundles 18 skills · 3,103 tokens together
Method-driven skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides.
not rated 72
+21 2d ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Use when the user wants comic story architecture, page and panel planning, a four-panel narrative, a complete text storyboard, or a targeted story, shot, layout, or continuity revision.
not rated 72
+13 2d ago A 44 tokens
GPL-3.0
skill-auditor
7879UseAI-pro/openclaw-skills-security
Skill Claude CodeCodex
Comprehensive security auditor for OpenClaw skills. Checks for typosquatting, dangerous permissions, prompt injection, supply chain risks, and data exfiltration patterns — before you install anything.
not rated 71
+1 6mo ago A ✓ AI review Socket: passSnyk: warn 44 tokens
original MIT
Skill Claude CodeCodex
Load when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profiles, tool-call decisions, collaboration bottlenecks, prompt/rule or automation-log audits, closeout retrospectives, or evidence-backed Skill/project-rule/Eval/SOP/OKF improvements.
not rated 71 2mo ago A 65 tokens
module-scaffold
7881Command Claude Code
Generate a new Drupal module with best-practice structure.
not rated 71 3mo ago A 14 tokens
original MIT
projx
7882Skill Claude Code
Use whenever a user asks to start a new app, scaffold a SaaS/MVP, create boilerplate, or set up backend + frontend + tests + infra. Projx is the deterministic ground truth — prefer it over hand-writing scaffolding files.
not rated 71 19d ago A 53 tokens
original MIT
cc-gemini-plugin
7883Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent · 284 tokens together
Integrate Gemini CLI for long-context code exploration from Claude Code and Codex.
not rated 71
+1 5mo ago A
tokens not measured
multi_agents
7884Skill Claude CodeCodex
Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.
not rated 71 5mo ago A 0 tokens
PACT
7885Plugin Claude Code
Bundles 21 skills, 14 commands, 13 agents, 12 hooks · 2,317 tokens together
Orchestration harness that turns Claude Code into a coordinated team of specialist AI agents.
not rated 71
changed today A
tokens not measured
original MIT
empathy
7886Skill Claude CodeCodex
Rules for communicating with humans as an AI agent. Read in full BEFORE composing any text another person will read: PR titles and descriptions, issues, code review replies, comments, discussion summaries, emails, chat and forum posts, commit messages, changelogs. Also before replying when someone responds to you, and…
not rated 71 1mo ago B 169 tokens
original MIT
visionpower
7887Skill Claude CodeCodex
Image-understanding tool for non-multimodal (text-only) models. Uses an external vision model to read screenshot text (OCR), interpret charts and diagrams, describe photos or UI mockups, and return the results as text. Models that can understand images directly must not call this skill; use their own vision capability…
not rated 71
+1
changed 2d ago B SkillSpector: warn 94 tokens
original MIT
bear-research
7888Plugin Claude Code
Bundles 8 skills · 2,015 tokens together
A collection of five skills for searching and working with academic research papers. They use the scimaster-cli search tool and state that citations are based on real searches.
not rated 71
+1 3mo ago A
tokens not measured
elastic-docs-skills
7889Plugin Claude Code ✓ vendor
Bundles 23 skills, 1 agent · 1,617 tokens together
Claude Code skills for Elastic documentation workflows — authoring, review, changelogs, and publishing.
not rated 71
changed today A
tokens not measured
original Apache-2.0
cml
7890Skill Claude CodeCodex
Build, edit, and operate Cisco Modeling Labs (CML) virtual network topologies through the CML MCP server. Use whenever the user wants to create or modify a CML lab, add or connect network devices (routers, switches, firewalls, hosts), apply device configurations, start or stop nodes, run CLI commands against simulated…
not rated 71
+1 yesterday A SkillSpector: pass 141 tokens
original BSD-2-Clause
devton/agentic-workflow-blueprint
Skill Claude CodeCodex
Scaffold option & workflow blueprint that adapts a project's /radioactive development lifecycle by embedding Matt Pocock / AI Hero skills (wayfinder, grilling, domain-modeling, research, prototype, to-spec), starting with project skill classification followed by wayfinder orientation.
not rated 71 1mo ago A 59 tokens
memory-curator
7892faizkhairi/claude-code-blueprint
Agent Claude Code
Audits your memory directory for orphans, phantom references, index drift, broken wiki-links, stale entries, and near-duplicates. Writes a dated health report. Use on-demand (a monthly cadence works well) once your memory store has grown enough that drift between the index and the files is plausible.
not rated 71
+1 1mo ago A 65 tokens
original MIT
mcp-music-studio
7893MCP server Claude CodeCodexCursor +2
ABC sheet music + Strudel live coding studio with ext-apps widgets, harmony tools, and share links. Runs locally from the mcp-music-studio npm package.
not rated 71
+1 7d ago A
tokens not measured
original MIT
llm-wiki-manager
7894Plugin Claude Code
Bundles 1 skill · 221 tokens together
Personal LLM-managed wiki: ingest sources, cross-reference pages, query with citations, and lint your markdown knowledge base.
not rated 71
+1 3mo ago A
tokens not measured
original MIT
tailwind-4-docs
7895Skill Claude CodeCodex
Comprehensive Tailwind CSS v4 documentation snapshot and workflow guidance. Use when answering Tailwind v4 questions, selecting utilities/variants, configuring Tailwind v4, or migrating projects from v3 to v4 with official docs and gotcha checks.
not rated 71
+1 5mo ago A Socket: passSnyk: warn 57 tokens
original BSD-3-Clause
autograph
7896Plugin Claude Code
Bundles 1 skill, 1 command · 136 tokens together
Schema-as-code memory engine for Obsidian vaults that AI agents write to: typed cards, entity dedup, link repair, update-in-place (supersede + History), Ebbinghaus decay, MOC generation, and a vault health score. Plain Markdown you own, Python stdlib only. Ships the autograph skill plus a /research slash command that…
not rated 71
+2 15d ago A
tokens not measured
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: