Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Assess managed Kubernetes clusters on EKS, GKE, and AKS by exploiting the seams between cloud IAM and Kubernetes RBAC -- IRSA/OIDC trust abuse, Workload Identity Federation, pod-to-IMDS escalation, aws-auth ConfigMap takeover, node pool service account abuse, and AAD integration weaknesses. Use when pentesting a managed k8s cluster, reviewing RBAC in EKS/GKE/AKS, testing pod-to-cloud escalation, or assessing network policy enforcement across namespaces
Attack and enumerate Azure AD / Entra ID tenants: initial reconnaissance with AADInternals and ROADtools, password spraying, token theft (PRT, CAE, refresh tokens), application and service principal abuse, Conditional Access bypass, cross-tenant pivoting, hybrid identity attacks (PTA agent, Azure AD Connect), and managed identity abuse. Use when penetration-testing Entra ID tenants, assessing Azure AD security posture, or exploiting cloud identity misconfigurations.
Identify and abuse Active Directory Kerberos delegation — unconstrained delegation with printer-bug coercion, constrained delegation with protocol transition (S4U2Self/S4U2Proxy), and resource-based constrained delegation via machine-account creation and msDS-AllowedToActOnBehalfOfOtherIdentity. Use when BloodHound or enumeration flags delegation, when you control an account with an SPN or GenericWrite over a computer, or when escalating within a domain
A framework for managing attention allocation. Use when you notice you spend a lot of time each day on gossip and trending topics, aimlessly scrolling short videos, and passively absorbing pushed content, and need to re-examine where your attention goes. Core logic: attention is the only productive asset you are born with and can control yourself, and where attention goes determines your output in life. Not for people who already have stable deep-work habits and clear attention allocation. Key trigger signals: "where did all my time go", "scrolled my phone all evening again", "why am I so tired yet producing nothing".
Use when managing GitCode repositories with the oh-gc CLI — including authentication, issues, PRs, reviewers, testers, labels, releases, and repository configuration. Use this skill when the user wants to commit code, create an ISSUE, create a PR, update a PR, or perform other GitCode web operations.
Write a new SecSkills skill end to end—choose the plugin bucket and skill tier, write a description that triggers correctly without stealing traffic from siblings, add the required sections, register the skill in ttp-index.json, add routing eval cases including negative traps, and run the three validators. Use when adding a skill to this repo, splitting or merging existing skills, fixing a skill that triggers on the wrong requests, or when a new skill fails validate.py, sync_attack.py, or run_evals.py.
Remove backgrounds from images using each::sense AI. Isolate subjects with clean edges, create transparent PNGs, replace backgrounds, and generate cutouts for products, portraits, and composites. Powered by eachlabs-bg-remover-v1 for precise edge detection. Use for: e-commerce product photos, portrait backgrounds, social media, photo compositing, transparent assets, marketing materials. Triggers: remove background, background removal, transparent background, cutout, bg remove, background eraser, isolate subject, transparent png, background swap, remove bg, no background
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Design backup, restore, sync, export, recovery, data durability, cloud/local storage, versioning, migration, deletion, and disaster recovery systems. Use when building or reviewing backup strategy for SaaS, mobile apps, desktop utilities, games, user-generated content, account data, or business-critical workflows.
Systematic testing methodology for exhaustive branch coverage, edge case identification, and production bug prevention. Use when PR review reveals incomplete test coverage, when tests pass but users report bugs, when code changes break existing features, when verifying all branches and edge cases before merge, when analyzing "it works on my machine" issues, when planning test strategy for new features, or when debugging flaky tests and race conditions.
Reply like a real person, direct and warm, without lists or hedging. Use whenever the user says you sound robotic, asks you to be real or talk like a person, wants mirror mode, or is going through grief, job loss or fear. Not for code or factual lookups.
Blender 5.x modifiers, bmesh API, mesh editing operators, sculpting setup — SubSurf, Boolean, Array, Mirror, Bevel, bmesh procedural mesh creation, and modeling pipelines via Python (bpy). Includes 5.1 changes (Boolean speed, Corrective Flip Normals, UV improvements).
Use BloodHound.py for Active Directory information gathering. Use when enumerating domain users, groups, computers, sessions, ACLs, and trust relationships, or analyzing in-domain attack paths. BloodHound.py is the Python collector for BloodHound; it gathers AD data over LDAP/DNS/Kerberos and outputs JSON for analysis in the BloodHound GUI. This skill should be used in any scenario involving domain penetration, AD enumeration, or attack path analysis
Integration guide for the Bloque SDK — a TypeScript SDK for programmable financial accounts, cards with spending controls, and multi-asset transfers. Use when the user asks to "integrate Bloque", "create a card", "set up spending controls", "handle card webhooks", "transfer funds", "create pockets", "set up MCC routing", "share balances between any mediums", "same balance across pockets/cards/Polygon/bank", "set up cashback", "auto-save on purchases", "round-up savings", "cashback programs", or build any fintech feature on the Bloque platform.
Book cover design with genre-specific conventions, typography rules, and AI image generation. Covers fiction and non-fiction genres, sizing, thumbnail testing, and iteration workflows. Use for: self-publishing, ebook covers, print covers, audiobook covers, cover mockups. Triggers: book cover, cover design, ebook cover, book art, novel cover, self publishing cover, kindle cover, audiobook cover, book jacket, cover illustration, fiction cover, nonfiction cover
Lift the brain's two seals (negative words and negative emotions) and restore rational thinking. Use when the brain "shuts down" and cannot think under pressure, setbacks, or conflict, and for long-term thinking-pattern optimization. Use this skill when you fall into a self-denial loop of "I can't", "I'm not able", "there's no way", or are overwhelmed by anger, anxiety, fear and similar emotions. Not for mental health issues requiring in-depth psychotherapy (such as depression or anxiety disorders, which need professional medical care), nor for purely knowledge-learning bottlenecks (those are method problems, not seal problems). Key trigger signals: "I can't / I'm not able", "I'm furious / I'm dying of anxiety", "my mind is blank", "the more I think the more annoyed I get", "I can't control myself".
Analyze a company's published content to extract their brand voice, writing style, and tone guidelines. Reads 10-20 of their best content pieces and produces a brand voice profile covering tone, vocabulary level, sentence structure, formatting patterns, CTAs, and target persona. Useful before writing outreach, content, or campaigns that should match a client's existing voice.
Bug bounty report triage, validation, and severity escalation. Use when the user provides a bug bounty report to validate, wants to check if a finding is submittable, needs to escalate severity for maximum payout, or says 'triage this', 'validate this report', 'escalate this', 'is this submittable', 'check this bounty report', 'max bounty', or 'will this get accepted'.
Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an overview of inference.sh app development. Supports both Python and Node.js. Triggers: inference.sh app, belt app, inf.yml, inference.py, inference.js, deploy app, app development, build app, create app, GPU app, VRAM, app resources, app secrets, app integrations, multi-function app
Chinese calendar query tool — retrieves comprehensive traditional calendar information for any date, including lunar calendar, Heavenly Stems and Earthly Branches (干支), solar terms (节气), festivals, auspicious/inauspicious activities (宜忌), zodiac (生肖), constellation (星座), fetal god (胎神), Peng Zu's hundred taboos (彭祖百忌), 28 mansions (星宿), Buddhist/Taoist calendar, and more. Triggered whenever the user asks about the Chinese calendar: "what's the lunar date today", "today's 宜忌", "what solar term is it", "is today auspicious", "Chinese zodiac for this year", "constellation", "今天农历几号", "今天宜做什么", "黄历", "万年历", "今天什么节气". Trigger even for casual one-line questions.
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.
Calculate, track, and report greenhouse gas emissions following GHG Protocol standards, including Scope 1, 2, and 3 emissions and science-based targets. Use when "carbon accounting, GHG emissions, scope 1, scope 2, scope 3, carbon footprint, emission factor, science-based target, SBTi, net zero, " mentioned.
Triage the last N production call logs for a Cekura agent against a set of KPIs / issues / goals, report the call IDs that hit each failure WITH the percentage of overall call logs affected, and distribute the remaining calls into a mutually-exclusive outcome taxonomy (e.g. not-answered / vetted / non-vetted caller-side / non-vetted agent-issue) with per-bucket percentages. Use when the user says "flag call log failures", "analyze the last N calls for issues", "what % of calls have <problem>", "which calls broke and how often", "find failing calls", "give me the breakdown of call outcomes", "what % of answered calls can be improved", or pastes an agent / project ID and lists the problems or KPIs to measure. Applies attribution rules so caller-side endings and recovered calls are NOT counted as agent failures. This is the upstream triage step that feeds `cekura-generate-scenarios` — it does NOT create scenarios.
Write and review changelogs, release notes, app-store update notes, launch notes, migration notes, breaking-change notices, and customer-facing product update communication for SaaS, apps, games, developer tools, desktop software, and marketplaces. Use when a release needs clear user value, risk communication, upgrade guidance, or support-aware wording.
Convert a git log, commit list, or release notes into a polished, user-facing changelog. Use when writing release notes, generating a CHANGELOG.md entry, or documenting what changed in a version. Produces a structured changelog section with version header, categorised changes, and migration notes. For an already-curated change list use changelog-writer instead.
Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
Your EYES into the user's live Chrome browser and Electron apps. This skill lets you SEE and INTERACT with the user's actual browser or Electron app — their open tabs, logged-in sessions, and live page state. You MUST use this whenever the user's request involves browser content or Electron app inspection in ANY way. TRIGGER THIS SKILL when the user: - References pages they have open: 'I have X open', 'my tabs', 'open tabs' - Asks to look at, compare, or analyze anything in their browser: 'compare these pages', 'which looks better', 'check this page' - Mentions UI/visual analysis of live pages: 'dashboard', 'UI', 'layout', 'design quality' - Asks for screenshots or page inspection: screenshot, inspect, debug, check the page - Refers to 'the page', 'the browser', 'my tab' in any context - Mentions console errors, page state, or anything requiring browser access - Mentions Electron apps or CDP connections: 'Electron', 'electron app', 'CDP', 'CDP_PORT', 'DevTools Protocol', 'desktop app', 'remote-debugging-port' CRITICAL: NEVER say you cannot see the user's browser or ask users to paste screenshots. You CAN see their browser through this skill. Use `list` to discover open tabs, then `perceive` or `shot` to see page content. Do NOT use Playwright — it launches an isolated browser without the user's login state, cookies, or open tabs.
Chrome Extensions (Manifest V3) performance optimization guidelines (formerly chrome-extensions). This skill should be used when writing, reviewing, or refactoring Chrome extension code to ensure optimal performance patterns. Triggers on tasks involving service workers, content scripts, message passing, storage APIs, or extension development.
Skill dedicated to the custom cabinet pitfall-avoidance guide. Covers the full process of countertop materials, cabinet doors and panels, hardware and accessories, wardrobes, shoe cabinets and sideboards, cabinet layout and dimensions, and whole-house customization pitfalls, integrating in reverse order the highlights of the Xi'an Renovation Classroom member-edition knowledge base to help users customize cabinets with less hassle and fewer pitfalls.
Activate when the user is considering making a decision in an unfamiliar field, or needs to judge whether they truly "understand" something. Typical trigger signals: the user says "I can learn it", "it should be about right", or "this isn't hard", but lacks deep experience in the relevant field. Not applicable to scenarios where the user already has a long track record of success in the field and is acting within their circle, nor to early exploration stages where taking risks and trial and error are needed to expand boundaries.
Build autonomous AI agents with Claude Agent SDK. Structured outputs (v0.1.45, Nov 2025) guarantee JSON schema validation, plugins system, hooks for event-driven workflows. Use when: building coding agents with validated JSON responses, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.