Packages finished enablement material (meeting summaries, workshop notes, training guides) into one self-contained HTML file where the reader toggles format: bullets, prose, visual diagram, comic, or cheat sheet. Theme-aware diagrams and an AI-ism voice gate. A handoff target, not a drafting tool.
★not rated 10
changed 19d agoA
tokens not measured
originalMIT
Keep one canonical agent ecosystem usable on both Claude Code and OpenCode: generate OpenCode agents/commands/MCP from Claude sources, validate both runtimes' rules, detect drift, and ingest marketplaces or repos for OpenCode.
★not rated 10
changed 19d agoA
tokens not measured
originalMIT
Toolkit for authoring and validating Claude Code skills and agents via a real script-backed check (description cap, PII, em-dash, Task completeness, vague ask-user prose), not a self-scored rubric. Auto-invoke on 'create skill', 'validate skill', 'validate agent'.
★not rated 10 todayA
tokens not measured
originalMIT
Type-driven README updater. Detects repo family, confirms it with the user, asks for style, audience, and depth, then generates from the matching template workflow. Auto-invoke on 'update readme' and 'refresh readme'.
★not rated 10 todayA
tokens not measured
originalMIT
Deterministic offline auditor for skills, agents, and prompts. Runs static checks against a directory of SKILL.md, AGENTS.md, or CLAUDE.md files and prints findings, critical then major then minor.
★not rated 10 todayA
tokens not measured
originalMIT
Plan and run DIY builds with energy-aware work blocks, enforced breaks, and an inline child-safety veto gate. Project state lives in the build repo. Self-contained: all reference files ship inside the skill folder, with no cross-plugin dependencies.
★not rated 10
changed 1mo 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: