startup-goal
265Skill Claude CodeCodex
Use when moving an approved startup goal through evidence-backed, reviewable feature milestones.
not rated 152 12d ago A 20 tokens
SmartSunruiyang/Agent-development-specification
Skill Claude CodeCodex
Bootstraps the Day-0 agent-governance + documentation scaffold for ANY project on ANY stack. Generates the agent rule system (CLAUDE.md, AGENTS.md, SELFCONSTRAINTS.md, VIBECODINGGUIDE.md) plus upstream docs (PRD, ARCHITECTURE with module cards + dependency DAG, ROADMAP, CONVENTIONS), initializes version control with a…
not rated 151 3mo ago A 242 tokens
original MIT
bulletproof
267Skill Claude Code
Use when building a feature, refactoring, fixing a complex bug, changing architecture, or starting any non-trivial coding task. 12-stage verified dev workflow from research to deploy.
not rated 150 5mo ago C 40 tokens
original MIT
frozenpepper/deepseek-and-destroy
Skill Claude CodeCodex
Premium judgment; cheap repository specialists; deterministic helpers for objective integrity.
not rated 147
+1 19d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Persuasive GPT image deck-planning skill. Uses extracted DESIGN.md, user files, and the user's goal to decide slide ordering, page count, evidence placement, and narrative flow in JSON.
not rated 146 3mo ago A 44 tokens
original Apache-2.0
ceos-annual
270Skill Claude CodeCodex
Use when conducting, reviewing, or planning the annual planning session.
not rated 146
+1 1mo ago A SkillSpector: warn 17 tokens
original MIT
Skill Claude CodeCodex
Advanced om-auto-continue-pr for PRs started by om-auto-create-pr-loop — claims the PR, resumes from the first non-done PLAN.md Tasks row in an isolated worktree, keeps the per-step commit and checkpoint discipline (integration tests + screenshots for UI), runs the full gate at completion, keeps spec-only design PRs…
not rated 146
+5
changed yesterday A Socket: passSnyk: warnSkillSpector: pass 110 tokens
original MIT
skillhone-prd
272Skill Claude CodeCodex ✓ vendor
Interactively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should -skill do", or before running skillhone new / skillhone optim on a skill whose…
not rated 146
+5 1mo ago A 199 tokens
bonsai-board
273Skill Claude CodeCodex
Write to (or read) the user's BonsAI board — the spatial idea canvas in the BonsAI macOS app. Use when the user asks to put / drop / add / send something to their BonsAI board, capture an idea or note on the board, sketch a diagram or architecture onto the canvas, evolve an idea already on the board, or read what's…
not rated 144 9d ago A 0 tokens
Skill Claude Code
Automatically generate a comprehensive travel plan based on user's travel needs (destination, date, budget, etc.), including transportation, accommodation, attractions, food, and itinerary. Use when a user asks for a travel plan, itinerary, travel tips, or mentions a specific destination.
not rated 143 yesterday A 57 tokens
real-work
275Skill Claude CodeCodex
Use when planning a multi-step task or working in plan mode and you need to capture the plan as a durable, resumable artifact — breaking work into phases with per-item checkboxes, completion tracking, autonomous verification, and a handoff summary so a future agent can pick up where you left off. Use when user wants…
not rated 143
+2 3mo ago A 79 tokens
original MIT
system-architect
276Skill Claude CodeCodex
A workflow step for turning a product brief and technical decisions into a system architecture overview. It identifies separate systems, their boundaries, dependencies, and the source-code directories they map to.
not rated 142 3mo ago A 91 tokens
original MIT
cs-ralph-runner
277Skill Codex needs its repo
Use when the user wants Codex to turn a Markdown requirements document into a Ralph PRD and run a safe Ralph/Codex build workflow against a local Git repository. Triggers include "cs-ralph-runner", "run Ralph", "generate Ralph PRD", or requests to run a Markdown PRD against a repo.
not rated 142
+3 7d ago A SkillSpector: warn 74 tokens
original MIT
Skill Claude Code
Continuously execute a complex multi-phase implementation plan through configurable worker-agent loops until the plan is complete or a genuinely human-level blocker is reached. Uses fresh implementation and review contexts, reviewer-led repair, fresh re-review, durable multi-orchestrator state, and main-orchestrator…
not rated 142
+93 yesterday A 75 tokens
original MIT
pawel-cell/micky-podcast-agentic-engineering
Skill Claude CodeCodex
Use when building software with AI agents and you need a serious end-to-end workflow instead of vibe coding. Covers harness choice, context discipline, cleanup, review loops, launch pressure, and security basics.
not rated 141 3mo ago A 47 tokens
智能体员工助手
280Skill Claude Code
A Chinese-language assistant for creating or changing AI employee configurations through conversation. It clarifies the employee’s role, matches suitable skills, prepares a configuration draft, and waits for confirmation before saving changes.
not rated 141
+1 3mo ago A 38 tokens
original Apache-2.0
Skill Claude Code
A collaboration system for planning and writing a long Chinese novel across many volumes and chapters. It uses reference files for the world, characters, events, writing style, and story rules.
not rated 140
+1 3mo ago A 139 tokens
loop-engineering
282Mark393295827/third-brain-v7-skills
Skill Codex
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
not rated 138
+1 20d ago A SkillSpector: pass 35 tokens
original MIT
Skill Claude CodeCodex
Use when asked about harness9 architecture, module design, or how components interact — explains the system design.
not rated 138
+1 yesterday A SkillSpector: pass 24 tokens
original MIT
stakeholder-map
284sruthir28/enterprise-ai-skills
Skill Claude CodeCodex
Map the people who can make or break a decision onto a Power/Interest grid, with each named stakeholder's stance (champion / skeptic / blocker / unknown), what they care about, and the single influence move you'll make for them. Use before any cross-functional decision, big launch, reorg, or executive ask — anywhere…
not rated 138
+2 9d ago A SkillSpector: pass 81 tokens
original MIT
workflows
285Skill Claude CodeCodex
Orchestrates multi-agent work with OpenPI's inline JavaScript Workflow DSL. Use when a task needs multi-phase fan-out, pipelines, barriers, structured handoffs, or resumable background orchestration.
not rated 138
+15
changed 5d ago A SkillSpector: pass 44 tokens
original MIT
Skill Codex
Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract issues. Use when Codex is asked to turn bugs, missing protections, design gaps, API/UI mismatches, or desired behavior…
not rated 137 3mo ago A 92 tokens
original MIT
Skill Claude CodeCodex
AI agent orchestrator with Neo4j knowledge graph, Meilisearch search, and Tree-sitter parsing. Use for coordinating multiple coding agents on complex projects with shared context and plans.
not rated 136
+1 17d ago A 42 tokens
tracking-schema
288jtrackingai/analytics-tracking-automation
Skill Codex
Use when the user wants schema preparation, event design, selector validation, schema review, or event-spec generation.
not rated 136
+1 4mo ago A 25 tokens
original Apache-2.0
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: