Run a task as an evolved multi-agent ORG. The compose-org skill makes the running Claude embody a proven team — one subagent per specialist talent — then grades and records the result so good teams get reused on similar future tasks. Backed by the liquid-org CLI (plan / compose / record).
Falsification-first investigation workflow: convert every assertion into a labeled falsifiable hypothesis, predict before measuring, run controlled experiments, verify findings adversarially (REFUTE-first), and persist verdicts in a hypothesis ledger so killed ideas are never re-attacked.
Persistent, graph-based memory for Claude Code backed by Neo4j. Runs against a local Podman or Docker container by default, or a remote/hosted Neo4j instance (e.g. Aura) when configured. Injects relevant memory at session start, captures new facts automatically at compaction/session end, and exposes on-demand search…
Write and audit the legal documents of a SaaS — terms, privacy policy, security policy, consumer buttons — deduced from the real schema, providers and pixels instead of a template. Audit mode compares what the published text promises against what the code actually does. Covers Argentina, EU (GDPR), US, Brazil (LGPD)…
★not rated 1 25d agoA
tokens not measured
originalMIT
Personalized Hacker News brief. Ranks today's stories against a stored interest profile, surfaces a few new topics each run, and learns from which links you click.
★not rated 1 26d agoA
tokens not measured
originalMIT
Odoo SA development skills, hooks, and conventions for PSDU customer work. Principles-first guidance for module development, code review, testing, and continuous skill refinement.
Operator skills for Forseti, the web UI and admin console for the Ory Kratos + Hydra identity stack: guided setup (with or without Docker), goal-driven reconfiguration (login providers, Linux/POSIX login, downstream OAuth clients), and a best-practice security audit of an existing deployment.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Use when writing or landing code — implementing a feature, fixing a bug, refactoring, or migrating. code:implement carries the standard for how code gets written (naming, control flow, comments, constants, purity) plus choosing a branch, verifying the change before calling it done, and splitting the work into atomic.
★not rated 1 18d agoA
tokens not measured
originalMIT
Declarative Action Architecture (DAA) — a strict three-layer separation pattern for E2E automation testing. Provides skills for generating, reviewing, and architecting DAA-compliant test code.
★not rated 1 4mo agoA
tokens not measured
originalApache-2.0
Autonomous supervisor/worker/critic iteration loop for Claude Code (the evaluator-optimizer pattern). Delegate a goal once; a supervisor agent grades each round against a checkable rubric — mechanical checks plus a SEPARATE critic sub-agent — and re-dispatches with feedback until the rubric passes or a hard cap is hit.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Verifies in compiled machine code that secret zeroization survived dead-store elimination and that constant-time logic did not regain secret-dependent branches. Ships a Ghidra headless inventory script. Use when auditing a binary, shared object, or firmware image against a source-level guarantee.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Plain-Markdown Scrum/Agile product management for Claude Code — backlog, sprints, board, velocity, releases, and GitHub traceability from slash commands.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Orquestador multi-agente que, a partir de un prompt, corre el loop plan → code → QA → review → iterar sobre un gateway local OpenAI-compatible (OmniRoute). Sirve para proyectos de software de cualquier tipo (frontend, backend, CLIs, scripts, librerías, config); el QA visual con la skill websight es OPCIONAL y lo…
★not rated 1 27d agoA
tokens not measured
originalMIT
Transforms video content (screen recordings, demos, bug reports) into structured multimodal data — keyframes synced with audio transcription — for AI analysis.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Design, compile, and deploy JasperReports artifacts to JasperReports Server over REST v2: scaffold JR7 jrxml from SQL, lint/compile/deploy reports and dashboards, manage datasources, Domains, OLAP, themes, input controls, scheduling, permissions, and STAGE/PROD promotion. Includes a doc-derived reference library…
★not rated 1 15d agoA
tokens not measured
originalApache-2.0
Generate interactive documentation websites from any codebase. Produces a React + Vite + TypeScript app with 10 cross-linked views: architecture, components, data flows, sequences, ERD, state machines, APIs, dependencies, tech stack, and ADRs.
★not rated 1 5mo 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: