Design intelligence engine for AI coding. v3 ships THE BRAIN: a deterministic 7-axis synthesizer (warmth, contrast, density, geometry, formality, motion, typepersonality) that compiles a novel design language per brief: no LLM calls, fully offline, closed-loop learning via a local decisions ledger. 1,243 structured en.
The full collection: design tokens (export/import/setup), variable and library management, component-set analysis and docs, WCAG and design-system linting, accessibility audits, version history, changelog, blame, comments, annotations, FigJam, and Slides.
★not rated 95 2mo agoA
tokens not measured
originalMIT
Initialize research project structure with standardized directories and metadata files. Creates project.yaml (configuration) and progress.yaml (state tracking) that other skills use for canonical paths and workflow coordination. Supports qualitative, quantitative, and mixed methods projects. Use when starting a new…
★not rated 95▲
+2 23d agoA
tokens not measured
originalMIT
Skills for evaluating an AI product: write the eval rubric, build test inputs, turn trace notes into codes, write judges and check them against your labels. You annotate traces and label for calibration. The skills do the rest.
★not rated 95▲
+1
changed todayA
tokens not measured
originalMIT
Self-enforcing engineering methodology extracted from Claude Fable 5 for less advanced models: prime directives + integrity rules injected each session, 26 on-demand skills, 4 contracted subagents (builder, qa-verifier, code-reviewer, research-scout), and 6 lifecycle hooks that gate destructive commands and unverified.
A collection of practical agent skills from DevBrothers, including workflows for interviews, agent instruction files, automatic fixes, strategy advice, and designing work outputs.
★not rated 94 15d agoA
tokens not measured
originalMIT
Claude Code travel companion for the trvl MCP server, with trip planning, price watches, and destination research. 1 smart MCP tool plus 66 legacy-compatible capabilities, including 36 travel hack detectors. Default search needs no API key.
★not rated 94▲
+2
changed 28d agoA
tokens not measured
Monte Carlo Agent Toolkit — data observability for AI coding agents. Surfaces blast radius, active alerts, and monitor coverage gaps before you edit dbt SQL. Includes skills for incident response, proactive monitoring, storage cost analysis, and push ingestion. Hooks enforce data-safety checks automatically as you…
★not rated 93
changed todayA
tokens not measured
originalApache-2.0
Search, preview, install, and author MagicPath UI components (designs) from Claude Code via the magicpath-ai CLI. Create new MagicPath projects, edit canvas components directly from local code, apply design-system themes, and work across personal and team workspaces.
Humanise text and remove AI writing patterns. Detects and fixes 34 AI tell-tales including inflated language, promotional tone, AI vocabulary, vague expressions of connection, filler phrases, sycophantic tone, placeholder text, formulaic structure, and thematic breaks.
★not rated 93
changed 1mo agoA
tokens not measured
★not rated 93
changed 4d 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: