ai-agents skills

tianxiao1430-jpg/zai-skills

Skill Claude Code

A senior architect-level skill that coordinates Vision, Search, and Zread to solve complex engineering problems.

theinfosecguy/razin

Skill Claude CodeCodex

Format local Markdown headings and lists consistently.

MelonS/MelonS-Agents

Skill Claude Code needs its repo

Find Korean job postings for a target role with minimal user input — pass a short --seed keyword like "Problem Solver" or "Forward Deployed Engineer" and the skill expands it to the full family of equivalent titles used at different companies (FDE / Applied AI Engineer / Generalist / Solutions Engineer / etc.)…

breethomas/bette-think

Skill Claude CodeCodex

Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checked with code. Do NOT use when the failure can be checked with regex, schema validation, or execution tests. Do NOT use…

Evaluris-Solutions/claude-active-directory

Skill Claude CodeCodex

Use when performing or planning authorized Active Directory reconnaissance—DNS and DC SRV, forest and trust mapping, LDAP/LDAPS and signing posture, gMSA discovery, SMB signing, password policy and spray approval gates, Kerberos SPN and pre-auth discovery, BloodHound collection choice, and LDAP filter cookbook. Use…

Amal-David/docingest

Skill Claude CodeCodex

Find, search, and read approved documentation snapshots through DocIngest.

tinh2/skills-hub-registry

Skill Claude CodeCodex

Analyzes infrastructure costs at 1K-100K user scales by reading the actual codebase, auto-detecting cloud providers, modeling per-action costs, and projecting total monthly spend with optimization recommendations.

iannuttall/mailroom

Skill Codex

Read, search, triage, draft, approve, and send project email through the local Mailroom CLI or MCP server. Use when checking Mailroom inboxes, finding conversations, marking spam, preparing replies, reviewing sponsorship enquiries, or sending an explicitly approved draft.

markoblogo/abvx-agent-skills

Skill Codex

Review an implemented product UI or public prose surface for hard visual defects, design-system incoherence, repeated template patterns, and AI-writing tells without treating subjective taste as universal law. Use for pre-ship screenshots, browser review, README/tool-page copy, launch notes, guide prose, or redesigns…

protostatis/unbrowser

Skill Claude CodeCodex

Cheap first-pass web discovery without launching Chrome — fetch SSR pages, run bounded JS, find routes/forms/API endpoints, extract structured data, and detect bot-wall or browser-only escalation points.

edg-l/engram-mcp

Skill Claude Code

Save a session handoff to Engram for future sessions. Captures decisions, todos, blockers, mental model, and next steps as a structured memory. Use when the user wants to preserve session context before ending work.

kununu/agent-bridge

Skill Claude CodeCodex

Delegate real coding work to a peer AI agent (such as Claude Code, Codex (ChatGPT), or Gemini (Antigravity)) that runs its own full harness, or use that peer as an independent reviewer, adversarial red-team, ideation & planning partner. Trigger when the user says "use agent bridge", "ask ", "delegate to ", "have…

yelmuratoff/agent_sync

Skill Claude CodeCodex

Create or edit AgentSync configuration — AGENTS.md, rules, skills, commands, subagents, settings, MCP servers, hooks, or per-tool configs. Use this skill when adding a rule, creating or scaffolding a skill, writing a slash command, defining a subagent persona, editing permissions, configuring an MCP server, setting up…

Komagon/hermes-production-patterns

Skill Claude CodeCodex needs its repo

A scheduled news workflow that reads RSS feeds, which are machine-readable lists of new articles, creates Chinese summaries, and checks their quality.

AEndrix03/Graft

Skill Claude CodeCodex

Batch knowledge ingestion from external sources (a folder, a codebase, a docs tree, a set of files). Plans the ingestion as a list of well-shaped nodes with reconciled keywords, shows the user the plan for approval, then executes idempotently. Triggered by /learn, "ingest this folder into memory", "porta questo codice…

jazelly/tokenless

Skill Codex

Install, upgrade, repair, and verify Tokenless API CLI, agent skills, browser/runtime dependencies, and the optional macOS menu app. Use for requested installation, upgrades, setup, browser sign-in handoff, or installation health checks.

beadhive/beadhive

Skill Claude Code

Walk a user through setting up Beadhive on this machine without them reading the docs: probe what is already installed, choose ONE install route (the managed nix path, or PyPI as the labelled fallback), install and verify bh, then configure it — bh config init, MCP wiring, the harness plugin, Factory HQ, and a first…

Caprista/KarvyLoop

Skill Claude Code

Read a receipt or invoice — pasted text, or a photo/scan — and turn it into one clean, structured expense record: merchant, date, currency, total, tax id, and itemised amounts, with those amounts checked to actually sum to the stated total. OCR text is dirty (O↔0, l↔1, misplaced decimals); this skill calibrates that…

rblalock/omakaseagent

Skill Claude Code

Omakase fallback router (plan, init, taste, handoff only). NOT for engineering/critique/archivist — use native agents @omakase-engineer @omakase-critic @omakase-archivist. Never load when user @mentions omakase- (that prefix is reserved for native agents, not this skill).

Aidan945/SafeAgentDB

Skill Claude CodeCodex

Sets up and maintains SafeAgentDB-style database safety infrastructure for AFK agentic development. Use when integrating isolated local, develop, preview, and production database workflows; configuring Supabase/Vercel/GitHub Actions previews; adding migration guardrails; packaging SafeAgentDB into a project; or…

backspace-shmackspace/claude-devkit

Skill Claude CodeCodex

Use when performing threat modeling for a project, feature, or system architecture. Applies STRIDE threat categorization with DREAD risk rating to produce structured threat models in OTM JSON and markdown formats. Covers system decomposition, trust boundary mapping, data flow analysis, per-subsystem threat…

domengabrovsek/claude

Skill Claude Code

Plans a huge chunk of work - more than one agent session can hold - as a shared map of decision tickets in a local file, and resolves them one at a time until the way to the destination is clear. Use when the user invokes /wayfinder on an effort too big for a single session.

charmonye/landkit

Skill Claude CodeCodex

Primary local starter skill for a copied landscape project folder. Use when a designer starts a new project, asks what to do next, provides photos/measurements/client wishes, or needs guided onboarding through briefing, BDD-style site scenarios, and SDD-style spatial decisions.

buildoak/fieldwork-skills

Skill Claude CodeCodex

Browser automation skill for AI coding agents. 25 Playwright-based tools for navigation, interaction, observation, and session management.