Quadruple verification for Claude Code — automatically blocks placeholder code, security vulnerabilities, and ensures output quality on every operation. Built by CustomGPT.ai for production teams.
★not rated 17▲
+1 5mo agoA
tokens not measured
originalMIT
Recommend AND run open-source AI literature-review tools — a curated 70+ catalog plus a launcher that installs & runs MinerU, PaperQA2, ASReview, GPT Researcher, STORM, and arXiv/Zotero MCP servers.
★not rated 17▲
+1 yesterdayA
tokens not measured
originalCC0-1.0
Generate an interactive Markmap mindmap from a file, a URL, pasted text, or a topic. Bilingual (English /mindmap + Chinese /mindmap-zh), with optional standalone-HTML rendering.
★not rated 17▲
+1 2mo agoA
tokens not measured
originalMIT
Gives the agent a persistent, auditable evolution memory plus a bridge to the EvoMap Proxy mailbox. Recalls what worked at session start, detects improvement signals while you edit, records outcomes when a task ends, and exposes the network's genes/capsules as MCP tools — powered by the Genome Evolution Protocol (GEP).
★not rated 17 25d agoA
tokens not measured
originalMIT
Roast your repo's design system with real data: a health score, the receipts behind it (every colour, spacing value, duplicated component and inline style), and the first fixes ranked by payoff. Deterministic scanner, benchmarked against 29 public repos and 10 reputable design systems, one shareable light/dark HTML…
★not rated 17▲
+2
changed todayA
tokens not measured
originalMIT
Zero-dependency lint & format orchestrator over MCP — one pure-Rust binary wrapping ruff/oxc/taplo/rumdl and more as in-process backends, plus a tree-sitter generic tier for everything else. Exposes lint/format/cache tools with structured JSON output.
★not rated 17▲
+1
changed todayA
tokens not measured
originalMIT
Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.
★not rated 17▲
+8
changed todayA
tokens not measured
originalMIT
Pre-1.0 preview. AI-Driven Specification-Driven Development (SDD) workflow — skills, agents, and commands for the 8-layer doc flow (BRD → IPLAN). Consumes the aidoc-flow framework spec. The doc--autopilot skills opt in to running their dispatched subprocesses without permission prompts; see README "What the autopilot.
★not rated 17 4d agoA
tokens not measured
originalMIT
AI media generation: music (Suno, Producer, Fish Audio), images (Flux, Seedream, NanoBanana), video (Luma, Sora, Veo, Kling, Hailuo, Happy Horse, Seedance, Maestro).
Work with your NocoDB bases from Claude Code: the NocoDB MCP server for reading, creating, updating, and deleting records, plus an agent skill for the full NocoDB v3 REST API (workspaces, bases, tables, fields, views, records).
★not rated 17
changed 10d agoA
tokens not measured
originalMIT
AI Agent Design skills for toy designer, 3D generation, image generation, social media generator, LEGO, Minecraft, and creative to finished product MOD (Manufacturing on Demand) workflows.
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import and release, execution monitoring, and Falcon Next-Gen SIEM lookup files.
Configure HawkScan in your CI/CD pipeline. Provider-agnostic: detects GitHub Actions, GitLab CI, Jenkins, CircleCI, Azure Pipelines, Bitbucket, Buildkite, and other CI systems from repo files, edits the pipeline file in place to add a HawkScan job, and prompts for HAWKAPIKEY storage (CI-native secrets store or extern.
★not rated 16
changed 5d agoA
tokens not measured
originalMIT
Two skills for adversarial code review. parallel-adversarial-review dispatches two same-model reviewer subagents in parallel under a competitive scoring frame, aggregating findings and taking the worst severity on disagreement. multi-model-adversarial-review extends this to N installed coding-agent CLIs (claude, codex.
★not rated 16▲
+1 3mo 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: