ai-agents skills

kangraemin/ai-bouncer

Skill Claude CodeCodex

A structured workflow for code changes, feature work, bug fixes, refactoring, and file edits.

floomhq/starter

Skill Claude CodeCodex needs its repo

Use when the user asks to create, run, or review skill evaluations with baseline-vs-with-skill A/B tests, Docker-isolated task runs, deterministic verifiers, receipt generation, or claims like pass-rate lift for a skill or pack.

gabriele-mastrapasqua/codex-lean-team

Skill Claude CodeCodex

Route software-engineering tasks to the smallest useful workflow. Trigger for ambiguous, multi-module, risky, performance-sensitive, AI/ML, or infrastructure work; skip for trivial edits.

Mark-Libetter/ai-conversation-hub

Skill Codex

Search, inspect, and honestly resume local AI conversations through AI Conversation Hub, and initialize or maintain repository task contracts for substantial multi-session or multi-agent projects with explicit Git delivery ownership. Use when the user asks what another agent discussed, wants to continue a local…

mracal/vibe-engineering

Skill Claude Code

Dispatches research agents to find real projects, papers, and documented failures before proposing any feature, architecture, or technology choice. Triggers on creative/design tasks, not on implementation of already-designed specs.

bdhrs/kamma

Skill Claude CodeCodex

Spec-driven work skill for projects using Kamma. Use this skill when you detect a kamma/ directory in the project, when working on tasks defined in a plan.md file, or when the user asks about threads, specs, or plans. Automatically follows the Kamma way of working.

dceoy/ai-coding-agent-skills

Skill Claude Code

Read an authenticated X Following or For You timeline through agent-browser without APIs or engagement actions.

d-wwei/codex-recall

Skill Codex

Installable Codex skill that turns Codex CLI into a long-term personal assistant with global memory, project memory, lightweight bootstrap, and safe incremental updates.

assimovt/trce-cli

Skill Claude Code

Share the current Claude Code session with trce after an explicit user request.

morimorijap/sunaba-cli

Skill Claude CodeCodex

Use after implementation, before final response.

reachjalil/harness-config

Skill Codex

Use when working in the harness-config repository and Codex needs to validate, preview, activate, or explain Harness config dogfooding with the local @harnessconfig/cli package.

browoz/agentic-sdlc-skills

Skill Codex

Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…

MiaoY0uShan/FP

Skill Claude CodeCodex

A general operating guide for software-engineering work by coding agents. It covers keeping the goal fixed, finding causes before patching, verifying results, and working concisely.

dhruv-anand-aintech/continue-later-skill

Skill Claude CodeCodex

Generate a structured continuation.md for handoffs—project context, state, tasks, gotchas, and deploy steps. Use when the user wants to save state or hand off work (not for quick raw git dumps; use continue-later-fast for that).

Tarekkharsa/agentstack

Skill Claude CodeCodex

Propose a reviewable multi-agent workflow as a blueprint — pick and name the pattern (map-reduce, pipeline, tournament, loop-until-dry, dag), emit its shape as an agentstack-blueprint JSON block, and WAIT for the user to approve / reject / edit before authoring and running it via agentstack more workflow run.

SathiaAI/graphsmith

Skill Claude CodeCodex

Build and fix reliable multi-agent AI workflows for any skill level, from first-time builders to senior engineers. ALWAYS use this skill when the user asks to "build an agent", "automate" a task or workflow, wants "AI to do X for me", describes a multi-step job, mentions agents, bots, pipelines, swarms, or…

broomva/skills

Skill Claude CodeCodex

The writer cannot be the final judge of the work.

TokenBrice/cmcs

Skill Claude CodeCodex

Use when executing implementation plans via cmcs/Codex agents with structured review checkpoints.

otakumesi/subagent-cli

Skill Claude CodeCodex

A recipe for building a model of a user's preferences from an AI agent's conversation logs. It organizes decisions and outcomes into files that can inform memory, rules, or system prompts.

ellmos-ai/build-your-users-mind

Skill Claude CodeCodex

Coordination strategies for AI agents working in parallel or hierarchically — 5 multi-agent patterns (Epstein, Hierarchy, Stigmergy, Consensus, Specialist). Bundled dependency of build-your-users-mind; its stage-2 classification uses Hierarchy + Stigmergy.

RuriLothlorien/CCSwitch-operations

Skill Codex

A set of operating instructions for safely changing and synchronising CC Switch, an app that manages prompts, skills, MCP servers, providers, and Codex model settings across several AI coding applications.

kinhluan/rules-quarkus-skills

Skill Claude CodeCodex needs its repo

Expert knowledge for building Quarkus applications with Bazel using the rulesquarkus build system. Use when user asks about Quarkus+Bazel builds, augmentation, or troubleshooting.

AKSoftCode/aicrew

Skill Codex

Run a benchmark to measure skill quality, response time, and token efficiency for aicrew skills.

techcraze00/CodeGraphX

Skill Claude CodeCodex

Use this skill to orchestrate CodeGraphX (CGX) MCP tools for deep codebase understanding without reading entire files.