Plugin Claude Code
Create, edit, evaluate, and package Claude Code agent skills — full draft→test→review→improve lifecycle.
Plugin Claude Code
Create, edit, evaluate, and package Claude Code agent skills — full draft→test→review→improve lifecycle.
Skill Claude CodeCodex
Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skill, fixing a skill that never triggers or fires unreliably, running evals to test a skill, benchmarking skill performance, optimizing a skill's description, reviewing third-party skills for quality…
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Evaluate a skill artifact with atomic binary yes/no questions, one answer (1/0) per question, each preceded by a written critique grounded in evidence from the skill's own files. Aggregate to per-dimension scores in [0,1]; the orchestrator turns your answers into the overall score and the pass/fail gate.
Agent
Compare two outputs WITHOUT knowing which skill produced them, using binary yes/no questions.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.
Skill Claude CodeCodex
Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external.…
smixs/awesome-claude-output-styles
Command
Switch the active Claude Code output style from a picker.
smixs/awesome-claude-output-styles
Skill Claude CodeCodex
Interviews the user with 10 questions about how they want Claude to talk, optionally collects writing samples they like and hate, then generates a personal Claude Code output style file and activates it. Use when the user says "make my output style", "build me a custom style", "I want Claude to talk like...", "create…
Skill Claude CodeCodex
Generate an /insights-style HTML report across MANY of your agent coding sessions (Claude Code and OpenAI Codex): what you work on, how you use the agent, your wins, your friction points, and concrete fixes to become more effective — precise goal-setting, not trusting output blindly, scoping, context hygiene…
Plugin Claude Code
Plugin marketplace listing 1 plugin: autograph.
Plugin Claude Code
Schema-as-code memory engine for Obsidian vaults that AI agents write to: typed cards, entity dedup, link repair, update-in-place (supersede + History), Ebbinghaus decay, MOC generation, and a vault health score. Plain Markdown you own, Python stdlib only. Ships the autograph skill plus a /research slash command that…
Command
Bootstrap a schema for an empty or chaotic Obsidian vault via a swarm of exploration agents + interactive Q&A. Only use on vaults with no schema and no coherent structure — structured vaults should run the regular autograph bootstrap workflow.
Skill Claude CodeCodex
Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…
Plugin Claude Code
12 agent skills for AI-driven software development, stitched into one gated idea-to-ship pipeline: 7w3 design, build-ready spec, executable architecture guardrails, tracer-bullet slicing, an honest review loop, a parallel MVP worker fleet, demo-stand QA and safe server deploy. Cross-agent skills format (Claude Code…
Skill Claude CodeCodex
A prompt template that turns module boundaries into executable architecture — linter, import-graph, and filesystem checks enforced in CI.
Skill Claude CodeCodex
Use when iterating on any artifact — code, design, document, process, analysis — through repeated review-and-fix passes toward a hardened state, or when running long unsupervised improvement that continues until a human stop signal. Also when "a few more passes" gets hand-waved, when something is called done after one…
Skill Claude CodeCodex
Use when the user wants to build, deliver, or orchestrate an MVP, prototype, demo, or v1 of ANY project (software or not), wants multi-agent fan-out over a task board, mentions "delivering-mvp-fleet" or "deliver an MVP" or "orchestrate this build", or drops a vague product idea and asks to make it real. Do NOT use for…
Skill Claude CodeCodex
Use when designing a feature, system, refactor, process, protocol, or decision before implementing it; when expanding a vague spec, RFC, or ticket into an implementable design; when writing or reorganizing design docs; when the user mentions "7w3", the seven Ws, "wishes / functions / decision flows", or wants a design…
Skill Claude CodeCodex
An ordered, gated pipeline — a router of Yes/No gates over the eleven Disruptor skills that carry a project from idea to running server.
Skill Claude CodeCodex
Prompt template that builds a local demo test stand and QA-tests a converged project to production quality.
Skill Claude CodeCodex
Use when starting the flow in a repo that has no CONTEXT.md / conventions yet, when a term keeps getting used two ways, or when a hard-to-reverse decision was just made and needs recording. Triggers: "set up the repo conventions", "what's our vocabulary", "record this decision", "write an ADR", "the glossary".
Skill Claude CodeCodex
A prompt template for safely provisioning a production Ubuntu/Debian web server (Docker Compose, reverse proxy, TLS, firewall, SSH hardening) without lockouts or data loss.