Run market research with simulated persona panels — review marketing assets, run interviews / surveys / focus groups / A-B tests / Van Westendorp / conjoint / MaxDiff / TURF / brand tracking / ethnographic / grounded theory and more. Personas live as .md files in a local .personas/ folder; build them via interview…
★not rated 2
changed yesterdayA
tokens not measured
Scan your Claude Code session logs across all projects and build a unified research/work dashboard (Markdown + visual HTML), with optional live chat and weekly auto-refresh.
★not rated 2 3mo agoA
tokens not measured
originalMIT
AI-powered test generation skills for AWS Python projects — Lambda, API Gateway, Step Functions, and Batch. Generates E2E, integration, contract, performance, and load tests by reading actual handler code.
★not rated 2 3mo agoA
tokens not measured
originalApache-2.0
Analyze FileMaker Pro DDR XML exports — index scripts, fields, layouts, relationships, and custom functions into SQLite for fast querying, code review, dependency analysis, and paste-ready implementation packages for scripts, layouts, and schema changes (FM 18+ clipboard format).
AI-powered ad creative generation for Funding Societies. Create ads from briefs, reimagine existing creatives, refine elements, resize for platforms, generate full campaign sets, and run A/B variants — with 4 style presets, brand compliance, and automated quality review built in.
A contract review assistant that reviews a contract clause-by-clause against a configurable playbook — flagging each clause GREEN, YELLOW, or RED with plain-English rationale and suggested redline language — using your firm's own playbook, or a generic clause playbook if none is attached. Never decides whether to sign.
★not rated 2 10d agoA
tokens not measured
originalApache-2.0
Extract valuable insights, decisions, patterns, and ideas from AI conversation exports (ChatGPT, Claude, Claude Code) into Obsidian-compatible notes. Includes a mirror analysis feature that builds a living psychological profile from your conversation patterns. Processes your chat history day-by-day using a Ralph…
★not rated 2 7mo agoA
tokens not measured
originalMIT
Comprehensive centralized repository of Claude Code configurations including agents, skills, commands, hooks, and MCP servers optimized for full-stack development.
★not rated 2
changed yesterdayA
tokens not measured
Observe, debug, cost-manage, and evaluate AI systems from the Progress Observability Platform: an instrumenter that retrofits observability onto an existing Python, TypeScript, or .NET agent and verifies traces arrive, a scaffolder for new instrumented .NET agents, a setup health check, then trace triage, cost/usage…
★not rated 2 10d agoA
tokens not measured
originalMIT
Multi-model fusion for Claude Code + Codex: a parallel panel (1x Claude Fable 5 via claude -p locked at --effort max + 1x GPT-5.6 Sol via codex locked at ultra; /fusion-max adds a 2nd Fable 5 panelist) answers a task independently and blind, then GPT-5.6 Sol (codex, ultra) judges and a Claude Fable 5 synthesizer (via.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Bootstrap an LLM-maintained knowledge base via a prism-driven interview: start from sample raw inputs (facts), derive the right page types, kinds, and relationships (concepts & categories) with the ontology-prism / KEOPS method, then scaffold the schema, conventions, and operating skills for the new wiki — and dogfood.
Skills that turn project documentation into a context layer AI sessions consult automatically: document-feature captures how and why a feature works for future maintainers; migrate-project-docs prepares pre-existing docs for the router; consulting-project-docs routes the relevant docs into AI sessions when the agent…
★not rated 2
changed 6d agoA
tokens not measured
originalApache-2.0
An agent-driven software factory: GitHub issues carry pipeline state, OpenSpec change folders carry spec content, ten agent roles move work between them behind four approval gates, with releases gated on GitHub milestones.
★not rated 2 12d agoA
tokens not measured
originalMIT
Skills for engineering custom Buildkite plugins and designing scalable, secure, dynamic pipelines. For plugin developers and DevOps/platform engineers.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Codebase analysis, reverse engineering, and development orchestration — 32 skills covering reconnaissance, deep investigation, TDD, debugging, planning, and code review.
★not rated 2 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: