A set of guidelines for designing agent skills—small instruction packages that teach coding agents how to handle tasks. It focuses on making their behavior predictable and allowing skills to work together.
★not rated 7 2mo agoA
tokens not measured
originalMIT
Multi-provider AI image generation cookbook: gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for OpenAI, Google Imagen, Flux, and other image providers. Built for Claude Code, Codex, OpenClaw, and other skill-capable agent runtimes.
★not rated 7 4mo agoA
tokens not measured
originalMIT
Quality checks and fixes for a game that already runs, on any engine or platform. It covers the parts of a game that are not features: how the controls feel, whether the numbers are balanced, whether the same input always gives the same result, whether the UI fits every screen and input device, whether the sound plays.
An adapt-first playbook that helps Opus (or any Claude model) pick up the work habits that made Fable effective — render-level verification, hypothesis-driven debugging, delegation guards, input fidelity, confirm-before-irreversible, and execution rhythm. It does NOT auto-inject rules or fake model capability. Its…
★not rated 7 3mo agoA
tokens not measured
originalMIT
Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) over a grounded argument graph, with a live transcript UI, appeal review, and 10 reasoning traditions.
★not rated 7
changed 13d agoA
tokens not measured
originalMIT
Turn any data file (CSV, Excel, SQLite, JSON/JSONL, Markdown, logs) into a single-file interactive HTML experience or a static infographic PNG. Ships a five-style report design bank, a level-keyed infographic bank (eli5/junior/pro), an infographic-director agent that writes data-story briefs, and a design-adapter…
Take a GitHub issue (bare, or tracked on a Project board) from triage to a merge-ready PR through a gated, worktree-isolated pipeline that scales its depth to the task and asks at most one batched question. The gates hold every run: design hardening, tests green, code review clean. Once you approve the PR in-session…
★not rated 7
changed todayA
tokens not measured
originalMIT
A weekly sweep for open product roles that match you — and remembers what it already showed you. Standalone: no pipeline, no tracker, no setup beyond a CV or three questions.
★not rated 7 21d agoA
tokens not measured
originalMIT
Structured non-code project management for Claude Code: planning, execution, knowledge persistence, and autonomous work loops for research, strategy, and content projects. 9 skills, 5 agents, 7 commands.
★not rated 7 29d 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: