Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions, plus an episodic observation log of what happened — so Claude explains your codebase without file traversal, follows your patterns, learns from corrections, and never re-asks what it already learned.
★not rated 27 26d agoA
tokens not measured
originalMIT
Tech-lead orchestration mode: the top-tier model keeps architecture and decisions, a role roster of cheaper subagents does the implementation, the routine, the digging and the review. Save tokens without losing quality.
★not rated 27
changed 10d agoA
tokens not measured
originalMIT
Analiza campañas de Meta (Facebook e Instagram Ads) con la metodología de las 3 Q's y benchmarks semáforo (🔴/🟡/🟢) sobre datos de la Meta Marketing API.
A coordinated writing assistant made up of six specialist agents for the full meta-analysis process. It supports medical researchers from planning a study through preparing the final paper.
Smart contract security analysis powered by 4,500+ real audit findings from Solodit. Quick scans, full framework assessments, and integration with audit-readiness.zealynx.io.
★not rated 27▲
+1 todayA
tokens not measured
originalMIT
Schema-first development ecosystem with dual-spec workflows (OpenAPI + DB schema) for building production-ready applications through deterministic code generation and intelligent orchestration.
★not rated 27▲
+1 1y agoA
tokens not measured
originalMIT
Skill for managing and optimizing Amazon Advertising campaigns — browse campaigns, analyze performance, get bid/budget recommendations, and discover keyword opportunities via the Marketplace Ad Pros MCP server.
★not rated 27
changed todayA
tokens not measured
originalMIT
Run Fable 5.2 (or Opus 5.5) as a coordinator: plan big, execute small. Bulk reading — codebase sweeps, log triage, document review, web research, coverage verification — fans out to parallel workers pinned to Sonnet/Haiku, and only distilled findings enter Fable's premium context. Ported to Claude Code from…
★not rated 27
changed todayA
tokens not measured
originalMIT
State-of-the-art engineering skills (2026) for building and auditing software across 42 domains and languages — security, architecture, APIs, databases, cloud, Kubernetes, web frameworks, observability, testing, LLM engineering, UX writing, copywriting, and more — with a master router and BUILD/AUDIT modes (43 skills).
★not rated 28▲
+2
changed yesterdayA
tokens not measured
CC-BY-4.0
ServiceNow MCP server for Claude Code, GitHub Copilot, Codex and any MCP client: Table API, CMDB, schema, aggregates and update sets, plus four Agent Skills. Read-only mode, OAuth client credentials for headless use, audit log.
★not rated 27
changed 11d agoA
tokens not measured
originalMIT
An adversarial job search that gets better as it goes. Search a careers board, score fit against the realistic applicant pool, build the resume and cover letter, run seven agents at the result before a human ever sees it, then write what they find back into your profile.
★not rated 27 2mo agoA
tokens not measured
originalMIT
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: