Free and open source, LibreJustice gives your agent 3.9 million French-language and European decisions and 2.1 million legal articles in force and 1.8 million historical versions, readable as they stood on any date and linked article by article. Four MCP tools over OAuth, two research skills.
★not rated 33▲
+3
changed yesterdayA
tokens not measured
originalApache-2.0
Turn screen recordings into transcript, exact frames, OCR and wall-clock evidence — then into ready-to-file bug drafts, specs, backlogs and meeting actions. Bundles the talkthrough MCP server, six workflow commands, a triage agent, and an agent skill.
Slash media skills for social cards, Xiaohongshu carousels, WeChat covers, creator packaging, scripts, hooks, topics, and content production workflows.
A build playbook for shipping real websites with coding agents, by Turki Alshuaibi. The agent interviews you, forces the decisions you would skip, locks a visual system, writes the brief, builds it or hands it over, then verifies, ships and indexes. Three modes set how many questions it asks. Four tools run on their…
★not rated 33
changed 10d agoA
tokens not measured
originalMIT
Comprehensive VC fundraising and investor relations toolkit for CEOs. Includes pitch narrative development, deck review, investor update writing, board deck preparation, fundraising process strategy, and Q&A preparation -- all grounded in first principles from Sequoia, a16z, Benchmark, YC, and leading VC thought…
★not rated 33 8mo agoA
tokens not measured
originalMIT
Automated job scanning and scoring for IT positions in Sweden. Fetches from JobTech API, scores against your profile with LLM, supports unattended daily runs via claude -p.
★not rated 33▲
+1 1mo agoA
tokens not measured
originalMIT
A running coach plugin that builds tailored training plans, uses Strava to track your progress and provides advice and plan adaptation as you pursue your goals.
★not rated 33▲
+1 5mo agoA
tokens not measured
originalMIT
Makes Claude write like a sharp, plain-spoken human. Loads 29 researched anti-AI-writing patterns at session start and checks every file it writes for tells. /copywrite audits or writes website copy against 36 researched copywriting rules.
Telegram Bot API 10.3 Rich Messages skills: send structured documents, block JSON, uploaded media, galleries, maps, streaming AI replies, polls with description and media, and rewrite agent replies for non-engineers.
Recall and reuse your past AI coding sessions as long-term memory. Searches the local sessionwiki index so the agent can find prior work, pull context, and trace which session wrote a file.
★not rated 33 4d agoA
tokens not measured
originalMIT
35 marketing skills for technical marketers and founders: CRO, copywriting, cold email, SEO, AI SEO, paid ads, ad creative, churn prevention, pricing strategy, referral programs, revenue operations, sales enablement, customer research, site architecture, and more.
★not rated 33 7mo agoA
tokens not measured
originalMIT
Spec-driven development for AI agents. Define what to build, let the agent build it right. Vibeflow separates thinking from coding with specs, guardrails, and audits — grounded in your project's real patterns.
★not rated 33
changed 13d agoA
tokens not measured
originalMIT
Query logs, metrics, events, entities, problems, security vulnerabilities and SLOs from self-hosted Dynatrace Managed clusters, across one or many environments.
★not rated 33
changed 11d agoA
tokens not measured
originalApache-2.0
DataRobot Skills for AI/ML workflows including model training, deployment, predictions, feature engineering, monitoring, data preparation, and Workload API management.
Elastic skills and documentation — Elasticsearch, Kibana, Observability, Security, Cloud, ES|QL, OpenTelemetry, and MCP docs access.
★not rated 33
changed 11d agoA
tokens not measured
originalApache-2.0
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: