Preset CLI skills for explicit shell, scripting, and CI/CD workflows driven by the sup CLI (PyPI package superset-sup). Use only for CLI workflows; do not use for MCP-only work or as a substitute for direct API calls when the user wants HTTP/SDK code.
★not rated 13
changed 1mo agoA
tokens not measured
originalApache-2.0
Turn a folder into a collaboration knowledge base for you, your AI, and your humans. Builds a SmartFolder: a tiered navigation-and-knowledge layer (root CLAUDE.md, per-folder guides, syntheses, sidecar summaries, and status surfaces) over your existing files, so knowledge lives in the folder instead of in an ephemeral.
★not rated 13
changed 6d agoA
tokens not measured
CC-BY-4.0
Planning session mode for complex tasks. Enter Fathom Mode to build shared understanding through structured dialogue before execution. Use this when you want to plan, think through, or clarify something complex before acting on it.
★not rated 13 6mo agoA
tokens not measured
originalMIT
Live in-browser feedback loop for local web pages: serve a page with a comment widget injected, then turn the comments you leave into fix-it tickets Claude Code applies and verifies in place.
★not rated 13 4mo agoA
tokens not measured
originalMIT
Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, executor-subagent chain execution, and adaptive missions — with all state mechanics executed by a tested CLI and invariants enforced by hooks. Inspired by OpenAI Codex /goal and the Ralph loop pattern.
★not rated 13
changed 2mo agoA
tokens not measured
originalMIT
Multi-agent orchestration plugin - a virtual dev crew with intelligent model routing (Opus/Sonnet/Haiku), lite mode, 3-layer codebase indexing, auto-skill selection, task history, rollback, and custom agents.
★not rated 13 7mo agoA
tokens not measured
originalMIT
Spec-driven agentic engineering as graph engineering: shape (pitch) -> decide (ADR) -> execute (delegated cycle with adversarial review) -> measure -> eval, with /graph to fan work out across a fleet of subagents (diamond / router / verifier / cycle). Dark-launch eval-gated. Distilled from a real practice.
★not rated 13 1mo agoA
tokens not measured
originalMITarchived
Environment doctor for Claude Code and Codex — checks git/Node.js/agent CLIs and login/VS Code/Docker/claude-mem health and suggests exact fix commands per OS.
★not rated 13
changed 14d agoA
tokens not measured
originalMIT
Generate, validate, and convert synthetic HL7 v2 test data — no vendor lock-in. Bundles the hl7gen MCP server and a skill covering HL7 v2 generation, validation, and FHIR conversion.
★not rated 13 2mo agoA
tokens not measured
originalMIT
From session to memory to repo docs: carries your work across Claude Code sessions and turns what you learn into docs and rules — for you, your agent, and your team. Handoffs, workstreams, curated markdown.
★not rated 13
changed 8d agoA
tokens not measured
originalMIT
Multi-perspective codebase review with severity-classified findings and holistic remediation.
★not rated 13 4mo 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: