Manage your /.claude config — timestamped backup/restore of CLAUDE.md, settings, user commands/skills/subagents, and installed plugins. Includes a permissions-merge command and a PreToolUse hook that blocks recursive rm outside the project directory.
Build production-grade UI using real design system specifications from Google Material Design 3, Apple HIG, and IBM Carbon. Includes complete design tokens (4 themes for Carbon: White/G10/G90/G100), interaction states, page composition patterns, icon systems (Material Symbols + SF Symbols + Carbon Icons), pictograms…
★not rated 24 6mo agoA
tokens not measured
originalMIT
A collection of four thinking-practice skills: taste-audit, intent-refine, judgment-redteam, and abstraction-uplift. The descriptions are in Chinese and present the collection as a way to challenge and improve human thinking.
★not rated 24 6mo agoA
tokens not measured
originalMIT
A local-first startup advisor that guides founders through idea validation, competitors research, hypotheses generation, MVP/prototype design, getting the first users, and more.
★not rated 24 3mo agoA
tokens not measured
GPL-3.0
Pipeline PQ di proiezione del contesto: T1 compressione signal-preserving degli output dei tool (canary end-to-end con auto-degrade: dopo N violazioni updatedToolOutput nella sessione, raw pass-through; auto-heal su evidenza dal transcript: auto-ack dei failure transitori dopo M verified consecutive e un-degrade a son.
★not rated 24▲
+1 3mo agoA
tokens not measured
originalMIT
Intelligent command history tracking with automatic failure detection. Tracks all bash commands Claude runs (successful and failed) with semantic directory aliasing and command mapping.
Camada compilada de contexto para qualquer AI coding tool. Compila projetos em estrutura .first-plan/ com 15 camadas (discovery, conventions, reuse, features, quality, contracts, evolution, runtime) e gera arquivos de instrução tool-specific (AGENTS.md para Codex, .cursorrules para Cursor, .github/copilot-instructions.
★not rated 24
changed 1mo agoA
tokens not measured
originalMIT
Graph, categorize and search your installed Claude Code skill collection: what is loadable, what is disabled, what points at things that no longer exist — plus a zero-token searchable tier for dormant skills.
★not rated 24 2mo agoA
tokens not measured
originalApache-2.0
Comprehensive biological and medical research data integration server providing unified access to 13+ specialized databases including Reactome (pathways), KEGG (pathways/diseases), UniProt (proteins), ChEMBL (drug discovery), PubMed (literature), GWAS Catalog (genetic associations), ClinicalTrials.gov (clinical…
★not rated 24▲
+1 2mo agoA
tokens not measured
originalMIT
Skills for agents you leave and come back to: /whats-next and /human-context-rebuild re-orient you, /stale-check and /worktree-cleanup handle finished branches, /cold-read checks words before users see them, and the idle-return hook runs whats-next when you come back.
★not rated 24
changed 8d agoA
tokens not measured
originalMIT
Full product lifecycle orchestrator for SpecKit: research → product-spec → plan → tasks → implement → verify → test → release, across express/lite/standard/v-model modes with human-in-the-loop gates, cross-artifact sync-verify, a living/delta spec with a REQ→…→TEST→EVT traceability matrix, a feature catalog with…
★not rated 24
changed 16d agoA
tokens not measured
originalMIT
Adversarial, multi-agent review of an uncommitted diff: parallel specialist reviewers, then a refutation pass that tries to disprove every finding so only real, risk-scored issues survive.
★not rated 24 27d agoA
tokens not measured
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: