Execution-first delivery pipeline: brainstorm, plan, decompose into proof-carrying tasks, implement, end-user test, and audit — end-user testing is the only PASS, no mocks, executed evidence over assertion. 18 skills: end-user testing, full functional audit, validation planning with cumulative proof obligations, plan…
Knowledge-Graph-Driven Development (KGDD) workflow for AI Agents. Models product requirements (PRD) and implementation plans (Plan) as structured Node/Edge/Fact graphs, with full spec traceability, automated review, multi-Agent execution, testing, visualization, and a built-in design system.
★not rated 4 5mo agoA
tokens not measured
originalMIT
Multi-model planning & review councils for Claude Code: fusion-plan runs a Claude role panel (architect/skeptic/test/maintainer) plus GPT-5.6 Sol via the local Codex CLI; fusion-review runs a bench-validated duo (one generalist Claude seat + GPT-5.6 Sol; role panel via args.roles) — each adjudicated and written up by…
An adaptive mock-interview coach: reads your resume and a job description, runs a realistic interview in the hiring company's voice, and hands you a private performance review with rewritten answers.
A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect, agentic-systems architect (ADK / Agent Runtime / MCP / A2A / AP2), plus security, SRE, and QA — wired into a design-first, security-first delivery gate. Eleven service skills (Cloud Run, GKE, IAM, BigQuery…
★not rated 4 1mo agoA
tokens not measured
originalMIT
Proactive technology mentor, security advisor, and prompt coach for Claude Code. Catches bad practices, advises on architecture decisions, and coaches better prompting.
★not rated 4 6mo agoA
tokens not measured
originalMIT
FAR and HHSAR provision and clause compliance checker for the Revolutionary FAR Overhaul (RFO). Validates a user's clause list against the acquisition.gov Smart Matrix (FAR 52.2xx) and the JUL 2026 HHSAR Deviations matrix (HHSAR 352.2xx) to produce a standalone .docx compliance report. FAR and HHSAR only; no DFARS.
★not rated 4 16d agoA
tokens not measured
originalMIT
Delegate coding tasks to OpenAI Codex CLI as a fast build agent. Supports non-interactive execution with configurable reasoning levels and parallel task dispatch.
Decision-quality layer for Claude Code that improves user-facing answers and Claude's own technical choices with high-signal tradeoff analysis, context-gap detection, and grounded recommendations.
★not rated 4 4mo agoA
tokens not measured
originalMIT
A plugin that turns plans into an auto-playing presentation narrated by the Japanese voice characters Zundamon and Shikoku Metan. It supports pausing the presentation.
Cross-platform Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion. Uses Python for cross-platform compatibility.
Capture work intent at peak context, then surface and replay it in a fresh session. A context-less session sees queued capsules on startup and offers to drain the oldest — ask-first, never auto-run.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Eisenhower Matrix-based task prioritization for any workload. Prioritize any brain dump using the Eisenhower Matrix. Use this skill whenever the user provides a workload, task list, sprint dump, or mentions phrases like 'help me prioritize', 'what should I focus on', 'I'm overwhelmed with work'. Categorizes work into…
★not rated 4 17d 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: