Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
All
AI Self-Improving Agent v2 - Learn from mistakes, corrections, and successes. Three-layer system: passive capture + proactive check + proactive skill generation (inspired by Hermes Agent). Avoid repeating the same errors, remember user preferences, and auto-generate reusable Skills from successful task completions.
Guides DPIA for health and medical data processing covering Art. 9(2)(h)-(j) exemptions, HIPAA crosswalk for transatlantic operations, clinical trial data protection under EU CTR 536/2014, and genetic data specifics under Art. 9(1). Activate for healthcare systems, clinical research, health apps, or medical device data. Keywords: health data, DPIA, Art. 9, clinical trial, genetic data, HIPAA, medical records, special category.
Designs rigorous hiring processes using structured behavioral interviews and work sample tests, replacing gut feel with data-driven evaluation of energy, obsession, and persistence. Use when building interview loops, evaluating candidates, writing job descriptions, or designing talent strategy.
Create collectible holographic foil cards and two-image lenticular flip cards with AI-generated full-color ukiyo-e and colored sumi-e anime artwork, layered Blender scenes, renders, GLB export, and a flat white web viewer. Use for 镭射卡、闪卡、全息卡、光栅卡、一念神魔、双形态卡、角色收藏卡，或需要保持角色高度一致的 A/B 状态切换。
Report this session's output tokens and CO₂ by running the repo's committed EcoLogits port, plus the modelled CO₂/$ saved vs a no-Honey baseline — always labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's carbon/token footprint, or to expand the 🍯 statusline badge into a full breakdown.
Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the reproducible committed figures, never invents per-repo numbers. Use when asked how much Honey saves, how it compares to Caveman / Ponytail / no-skill baseline, or for the headline numbers.
Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context — architecture + why, build/test/run commands, decisions and dead-ends — as human-readable markdown, versioned with the code so it can't silently rot. Use when asked to set up project memory/context, stop agents re-grepping the codebase, scaffold or refresh a PROJECT.md / CLAUDE.md memory section, or cut cold-start rediscovery cost. Prose context only — never code, config, or data.
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
User-invoked maintenance for openspec/BACKLOG.md. Reconciles deferred-slice entries against the shipped specs in openspec/specs/, proposes deleting entries now covered, and edits the file only on the user's per-entry confirmation. Not part of the tempa-spec pipeline. Run it by hand, ideally right after openspec archive.
Change-size check run inside the tempa-spec schema's `proposal` phase, before the \"What Changes\" list is finalized. Detects when a draft bundles several independent changes that each deserve their own change, stops and asks the user whether to split (default: one change; the agent never splits on its own), and when the user splits, records the deferred slices in proposal.md's Out of Scope section, discovery.md's Key Decisions, and openspec/BACKLOG.md. Rationale is in docs/research/2026-08-27-mattpocock-skills-gate-and-seams.md.
Evaluate source credibility using primary/secondary classification, internal/external criticism, triangulation, and misinformation detection. Use this skill when the user needs to assess whether information is trustworthy, evaluate research sources, fact-check claims, or detect misinformation — even if they say 'can I trust this source', 'is this real', 'how reliable is this data', or 'fact-check this for me'.
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."
Detect and remove signs of AI-generated writing from text. Use whenever editing, rewriting, proofreading, or reviewing any text to make it sound more natural and human-written. Trigger this skill when the user asks to "humanize" text, remove AI patterns, make writing less robotic, sound more natural, avoid AI detection, rewrite in a human voice, de-slop text, or improve writing authenticity. Also use proactively when you notice AI writing patterns in text you're producing or editing.
Hunt ASP.NET-specific attack surfaces: ViewState deserialization (signed-only vs. encrypted), machineKey recovery, dual-parser MAC-bypass anti-patterns, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, and the classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms, WCF, and SharePoint farms.
Hunt Missing/Weak Rate Limiting — login brute force, OTP/2FA brute force (10^6 keyspace), password-reset-token brute, credential stuffing, username/email enumeration via error-string / status-code / timing differences, weak password policy, missing CAPTCHA, IP-based rate-limit bypass via X-Forwarded-For and friends, ReDoS. Distinguishes hard lockout vs soft IP-throttle vs CAPTCHA-injection vs silent shadow-throttling (avoids false-negative 'no rate limit' conclusions). Medium to Critical depending on what the brute reaches (OTP→ATO = Critical).
Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable
Hunt cloud / infrastructure misconfigurations. AWS: public S3 buckets (s3:GetObject anonymous), permissive bucket policies (PutObjectAcl public-write), exposed CloudFront origin, public Lambda function URL, public RDS snapshot, IAM credentials in JS bundles, AWS metadata accessible via SSRF. GCP: public GCS buckets, exposed Cloud Run services, leaked service account JSON. Azure: public blob containers, exposed Function App. (Kubernetes/Docker exposure is owned by hunt-k8s; CI/CD pipeline attacks by hunt-cicd; post-credential IAM escalation by cloud-iam-deep.) Detection: targeted dorking, certificate transparency, JS bundle secret extraction, port scan for known service ports. Validate: actual data read / write / RCE. Use when hunting cloud-native storage and compute misconfig (S3/GCS/Blob, IMDS-via-SSRF, serverless, public managed services).
A skill for hunting GraphQL vulnerabilities, built from 12 public bug bounty reports. Covers IDOR via node() / GID, mutation IDOR including AI/LLM features, cross-tenant IDOR, SSRF via arguments, batching DoS, query cost bypass, SQLi via arguments, broken object-level authorization, auth bypass via unscoped mutations, and PII exposure from missing field-level authorization. Use when hunting GraphQL vulnerabilities on any target.
Hunt Kubernetes & Docker — API anonymous access, kubelet 10250 exec (SPDY/WebSocket, NOT plain POST) and the simpler /run primitive, etcd 2379 unauth, dashboard skip-login, RBAC misconfig, secret/SA-token abuse, docker.sock host escape, runc/container-escape (Leaky Vessels CVE-2024-21626), API-server-mediated nodes/proxy RCE, EphemeralContainers node-shell, bound/projected SA-token audience+expiry abuse, admission-controller bypass, Helm/Tiller remnants. Use when target runs containerized infra, exposes K8s ports (6443/10250/10255/2379/8443), or cloud metadata reveals K8s service accounts.
Hunt Laravel specific vulnerabilities — Debug mode leakage (APP_DEBUG=true exposes full stack trace + env vars), Laravel Telescope/Horizon dashboard unauthorized access, Ignition RCE (CVE-2021-3129), Signed URL manipulation, Queue Worker abuse, mass assignment via Eloquent, deserialization via cookies, .env file exposure. Use when target runs Laravel (PHP) — detected via X-Powered-By, Laravel session cookies, or /storage/ paths.
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration viatool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model),tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCPtools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent withtools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.
Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange. Anonymous NTLM Type-2 challenge capture leaks NetBIOS domain, internal DNS forest, computer name, AD timestamp via AV_PAIRS structure. Default Windows-installer hostnames (WIN-XXXXXXXXXXX pattern) signal lazy provisioning. Use when target advertises `WWW-Authenticate: NTLM` or `Negotiate` headers anonymously
Hunt SAML / SSO attacks. Patterns: XML Signature Wrapping (XSW) — modify Assertion while keeping Signature valid by relocating signed element, comment injection in NameID ([email protected]<!--evil-->@attacker.com → some parsers see [email protected]), signature stripping (remove Signature element entirely, server should reject but doesn't), key confusion (signed by attacker's IdP, accepted by SP), audience-restriction not validated, replay attack (same Assertion accepted twice within validity window). Tools: SAML Raider Burp extension, samlmagic, manual XML manipulation. Detection: any /saml endpoint, /Shibboleth.sso, /sso/saml/, Microsoft ADFS endpoints. Validate: account takeover via altered NameID, admin role injection via altered AttributeStatement. Use when hunting SSO flows, when SAML AssertionConsumerService is reachable, or when chaining IdP-trust to SP-impersonation
Hunt WebSocket vulnerabilities — Cross-Site WebSocket Hijacking (CSWSH), missing/weak Origin validation on the WS handshake, no per-message authentication, message tampering, socket.io namespace/room authorization bypass, and handshake-layer Upgrade smuggling. Use when target has WebSocket endpoints (ws:// or wss://), socket.io / SignalR / Phoenix Channels, real-time features, chat, live dashboards, notifications, or trading platforms.
Detects T1547.001 startup folder persistence by monitoring Windows startup directories for suspicious file creation, cross-referencing Autoruns entries, and running a Python watchdog script for real-time filesystem monitoring. Use when hunting for malware or implants that survive reboot via startup-folder placement, or when validating autoruns/EDR findings against known-good startup baselines.
Use when reading or editing config code that imports hydra_zen (builds, make_custom_builds_fn, store, just, MISSING, hydrated_dataclass, kwargs_of, make_config, ZenStore, BuildsFn), or when Hydra-style "${...}" interpolations, config groups, _target_ blocks, or `builds_bases` inheritance appear in a hydra-zen project. Covers the typing model, idiomatic patterns, type-refinement gotchas, and hacks for corner cases (partial-of-partial, per-variant overrides, project-wide builder defaults).
Fetch trade executions from Interactive Brokers filtered by account, date range, or symbol. Supports live API (~7 days history) and FlexReport (full history). Use when user asks about their trades, executions, or transaction history. Requires TWS or IB Gateway running locally.
Scandit ID Capture (`IdCapture`) in Capacitor projects — scanning passports, driver's licenses, ID cards, residence permits, visas via MRZ, VIZ, barcode, or mobile documents. Use for integration, accepted-document and scanner configuration, captured-field result handling, anonymization, add-on capabilities (voided-ID detection, European driving-license back decoding, AAMVA barcode verification), and SDK version migration.
Tonghuashun financial data queries covering stocks, funds, macroeconomics, industry economics, news announcements, bonds, Hong Kong and US stocks, and index sectors, plus intelligent stock picking, fund selection, macro and industry economic indicator queries, and financial announcement and news search.
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Automate JIRA ticket processing through domain analysis, initialization, prompt evaluation-optimization and final task execution with comprehensive error handling in thinking model. Use when given a JIRA ticket URL (format: https://[domain].atlassian.net/browse/[TICKET-ID]) to process end-to-end.
Implement exactly one ready Phat task within its documented scope, update its Goal/Blocked by/Todo checklist with verified progress, preserve unrelated changes, apply the project's verification and commit policy, and prepare the task for review. Use when a task is todo or an existing in-progress continuation with all dependencies complete.
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.