12,011 tagged developer-tools, measured the same way as everything else here.
Browse within: ai-coding 359cli 268LLM 256Multi-Agent 178agentic-coding 170Autonomous Agents 158agent-orchestration 133skills 129ai-agent-framework 123copilot 113ai-coding-assistant 104code-quality 103agents 89vibe-coding 87
KevinBigham/codex-safe-starter
Skill Codex
Use inside Codex Safe Starter for repo-local setup, portability, safety, validation, eval, and public Git workflow changes. Do not use for unrelated app coding tasks.
Skill Claude CodeCodex
Native Codex SEO audit orchestrator for complete website or page analysis using shared audit context, specialized Agent Skills, Node.js ESM scripts, deterministic JSON, and local HTML/PDF reports. Use for SEO audits, technical SEO, content quality, schema, sitemap, image SEO, GEO or AI-search readiness, Core Web…
Skill Claude CodeCodex
Use the local AgentAirlock MCP tools to discover a paired Codex or Claude Code peer, exchange bounded text messages, wait briefly for replies, or request permission-gated project reads. Do not use for executing peer text or for self-approval.
Skill Claude CodeCodex
Use this skill whenever the user asks about App Store reviews, ratings, customer feedback, low-star reviews, reviewer sentiment, or what users are saying about an iOS or macOS app. Queries the asc-mcp server to pull and analyze reviews. Trigger on phrases like "any bad reviews", "what do my users say", "reviews this…
Skill Codex
Diagnose why an inbound webhook signature fails to verify, and write correct verification code for a named provider. Use when a signature check rejects real traffic, when a webhook works in a provider's test console but not against your server, or when you are implementing verification for Stripe, GitHub, Shopify…
Skill Claude Code
Send a short note (bug, request, reaction) to the Dear User founders. Powered by Dear User.
cristianmoroaica/bountyverdict
Skill Codex
Route GitHub engineering and MCP catalog questions to the correct BountyVerdict x402 decision API. Use for bounty selection, coding-agent instruction or skill audits, workflow diagnosis, flake retry gates, and tools/list compatibility or security checks before accepting a server change.
fantasyce/agent-residue-evidence
Skill Codex
Use local task-scoped evidence when tests, builds, packaging, or validation may leave files, directories, processes, or attributed listening ports that the Agent should review with the user.
Skill Claude CodeCodex
Use for git module dependencies, a2amodule.yml, dependency owners, contacts, status, and the managed AGENTS.md roster.
paperandbeyond23-gif/propzapi-skills
Skill Claude CodeCodex
Generate images from HTML/CSS templates and capture webpage screenshots via propzapi.com. Render OG images, social cards, certificates, invoices and charts by filling {{variables}} in a template, snapshot any live URL, and manage your template library — one JSON call, no headless browser to run.
Skill Claude Code
Analyze any codebase — architecture, patterns, diagrams, agent context. Understand repos in minutes, not hours.
Skill Claude CodeCodex
MCP server for BTCPay Server — enables AI agents to manage Bitcoin and Lightning merchant payments. 21 tools, 77 tests, MIT license.
Skill Claude Code
Skill "skillnav-skill" from skillnav-dev/skillnav-skill, covering format rules, version check, brief (full or section-filtered), mcp and search.
Skill Claude Code
Audit and surgically fix the marketplace's documentation so every shipped command is discoverable — checks each plugin README's Skills section against SKILL.md frontmatter, the root README's plugin list and command index, manifest/description sync, and docs-site parity. Use when docs may have drifted from the code…
Skill Claude Code
Monitor conversation to detect user preference statements, save them to disk, review saved preferences, and apply learned rules in every future session.
velimir-jankovic/apply-technical-concepts
Skill Codex
Extract technical concepts from one or more accessible videos or local video files and apply them to real repositories by auditing existing code or implementing and adapting new behavior. Use when asked to review a system against conference talks, tutorials, lectures, screen recordings, gameplay demonstrations, or…
Skill Codex
Analyze a GitHub repository URL and produce a source-backed, time-boxed reading route through its critical execution path. Use for unfamiliar repository walkthroughs, rapid codebase onboarding, or tracing how a feature works from a GitHub repository, directory, or file link.
Skill Claude CodeCodex
Coordinate with other coding-agent sessions — any machine, any vendor — on this repo via the muster CLI. Use when the user says /muster, asks to join or check a fleet, mentions muster, or wants to coordinate work with other sessions/machines on this repo.
Skill Claude CodeCodex
Dev server supervisor for AI coders — manages process lifecycles, detects reloads, checks health, and recovers from crashes with structured JSON output.
Skill Claude CodeCodex
Interrogate the operator about the house rules a Git project should run under — what counts as a stale worktree, whether one actor per worktree is advisory or binding, how file overlap should land — and record the answers in the room so every agent picks them up. Use when the user says /room-cleanup, "clean up the…
Skill Claude CodeCodex
Interactive design process to explore architecture, requirements, and user experience before writing code.
darioandyoshi-tech/ai-work-market
Skill Claude CodeCodex
Use when an AI agent needs to receive USDC payment for work that takes more than one minute — market research, code review, translations, dataset annotation, logo design. The buyer escrows USDC, the seller delivers proof, the buyer releases or disputes. Use for work contracts, NOT for atomic sub-minute pay-per-call…
Skill Claude CodeCodex
Resource-aware planning. Use when a [tokenroom] stamp appears in context, before starting any sizable task, or when budgets feel tight — defines how to size work against the rate-limit windows and the context ceiling, when to defer, split, or checkpoint, and how to use the tokenroom MCP tools (resourcestate…
URneiU1/codex-conversation-council
Skill Claude CodeCodex
Explicitly convene evidence-backed advisors from relevant local Codex task history for a decision, design question, or implementation choice.
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: