Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Use this skill for any GTM Engineering work in Deepline — prospecting, list-building, account research, contact enrichment, email/phone/LinkedIn lookup, ICP qualification, lead scoring, outreach copy, CSV-driven row work, and verifying enriched data. Triggers on phrases like 'enrich this CSV', 'find contacts at these companies', 'build a TAM list', 'waterfall emails for these leads', 'detect job changes', 'is this data accurate', 'write a sequence for', and on any request that mentions Deepline, plays, or named GTM providers (Crustdata, Hunter, Dropleads, etc.). Use this even when the user does not explicitly say 'GTM' — most CSV-with-leads tasks and most provider-driven enrichment tasks are GTM tasks. SKIP only when the request is a Clay table extraction (use clay-to-deepline) or has no Deepline / outbound / data-enrichment dimension at all.
Run a quick Deepline demo recipe to show the user how Deepline works.
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals. Before reading this file, first read deepline-gtm to understand the Deepline CLI tool and how to use it. Then read this file for guidance on the task.
Resolve LinkedIn profile URLs from name + company with strict identity validation to avoid false positives.
Find companies backed by a specific investor or accelerator, then find contacts and build personalized outbound.
Use when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search.
Use agent-browser CLI for website automation: navigate, click/fill, scrape, screenshot, test web apps, debug console/network.
Convert current chat session into a reusable skill. Use when user says "/chat-to-skill", "save this as skill", "create skill from chat", "turn this into a skill", or wants to preserve learnings from the conversation as long-term memory.
Fetch and curate AI news from X/Twitter list. Use when user asks for AI news, AI digest, what's happening in AI, or wants a summary of AI announcements, papers, and releases.
Use gh CLI to view, triage, fix, link, create, or close GitHub Issues.
X/Twitter CLI for posting tweets, reading threads, searching, and fetching news. Use when user asks to tweet, reply, read tweets, search X/Twitter, get mentions, view bookmarks, likes, followers, following, user timelines, or fetch trending news/topics.
AppleScript and JXA automation for macOS. Use when user asks to automate apps, control system, run AppleScript/osascript, or integrate with macOS applications.
Prepare concise, high-signal issues or contribution proposals for the pi repository without annoying maintainers. Use when filing issues/PR proposals for earendil-works/pi or mentioning Mario/pi tracker etiquette.
Decode garbled Russian/English wrong-keyboard-layout text (ЙЦУКЕН/QWERTY).
Prepare, publish, repair, or verify package releases and changelogs. Always use for package/version release, publish, ship, tag, changelog, release notes, registry publication, documentation publication, or GitHub Release work. Distinguish package releases from application deployments before acting.
Analyze a user's pi coding-agent session history for recurring behavior, prompting habits, workflow loops, friction, and preferences. Use when the user asks to inspect or reflect on pi sessions, common behavior patterns, agent/user interaction style, prompting habits, or personal pi workflow quality.
Find agent skills and skill repositories on GitHub.
Write or revise X/Twitter developer announcement threads in the user's preferred style. Use for technical launch threads, project announcements, release threads, and threads with code screenshots/snippets.
Use when the user wants to "vibe-merge"/"vibe-marge" a PR or branch: independently reimplement good ideas, avoid blind merging/cherry-picking, preserve quality, and credit the contributor as co-author.
Transforms technical documents into rigorous learning journeys with collegiate-level mastery requirements. Uses Bloom's taxonomy progression, 80%+ mastery thresholds, and multi-level verification before advancing. Treats learning as a high school to college graduation progression. Use when user wants deep understanding, not surface familiarity.
Certify a skulto build for Homebrew prod release. Runs three passes — unit/lint/cross-compile, clean-slate CLI walkthrough, and security audit — then produces a certification summary.
Use when executing implementation plans phase-by-phase with strict enforcement of quality gates, tests, and Definition of Done. Triggers on "build this plan", "execute plan", "implement phases", or when user provides a plan document to execute.
| Comprehensive code review for Golang CLI applications. Produces an actionable checklist covering error handling, CLI framework patterns (Cobra/urfave), testing, performance, security, and Go idioms.
Autonomous single-shot plan execution. Runs entire superplan implementation plans without stopping, using sub-agents for each phase. Phases write state to filesystem for resume capability. Sequential phases run in order, parallel phases (1a, 1b) run concurrently. User never needs to compact context.
Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codebase scan.
Autonomous single-shot plan execution. Runs entire superplan implementation plans without stopping, using sub-agents for each phase. Phases write state to filesystem for resume capability. Sequential phases run in order, parallel phases (1a, 1b) run concurrently. User never needs to compact context.
Designs integration and E2E tests with mock boundaries. Use when: writing E2E tests, integration tests, or reviewing test quality.
Validates approach and checks assumptions before/after tasks. Use when: starting work, encountering errors, or switching phases.
Prioritizes tests based on ROI and critical user journeys. Use when: deciding test coverage, selecting test types, or budgeting effort.
Detects code smells, anti-patterns, and debugging issues. Use when: fixing bugs, reviewing code quality, or refactoring.
Applies TDD process, test quality criteria, and mock guidelines. Use when: writing unit tests, using mocks, or reviewing test quality.
Selects implementation strategy (vertical/horizontal/hybrid) with risk assessment. Use when: planning features or deciding development approach.
Guides PRD, ADR, Design Doc, and Work Plan creation. Use when: planning features, writing specs, or creating technical documents.
Applies coding standards for clean, maintainable code. Use when: writing functions, handling errors, refactoring, or reviewing code style.
> Inspect, build, or extend Figma design systems — and optionally sync them to component scoring, detached instance detection, handoff docs) and build mode (creating components with variable bindings, slot-based composition, structured descriptions, validation, and optional export of tokens.css + AI rules to the user's codebase). Use when the user says 'audit my design system', 'check component quality', 'create design system', 'build DS in Figma', 'generate component library', 'add slots to my components', 'sync design tokens from code', 'find detached instances', 'check WCAG compliance', 'export tokens to code', 'generate CLAUDE.md for design system', or wants to push a design system from code to Figma or back. The skill auto-detects the mode from request, or asks if unclear. After inspect, ALWAYS pauses and waits for explicit user decision before any build action. Phase 6 (sync to code) is OFF by default — only triggers on explicit user request. Does NOT implement Figma designs as code — use figma-implement-design for that. Does NOT create individual screens — use figma-generate-design for that.
> Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external. "разведка", "due diligence", "background check", "digital footprint", "найди всё про", "собери информацию", "кто это", "профиль человека". market research, content generation, or general web scraping tasks.
Conduct structured analysis on any problem using CIA/IC analytic techniques — assess competing hypotheses, challenge assumptions, stress-test judgments, and produce defensible evidence-based assessments with full citations. Supports 18 techniques including ACH, Key Assumptions Check, What-If, Premortem, Cross-Impact Matrix, Contrasting Narratives, Devil's Advocacy, Red Hat Analysis, Alternative Futures, and Deception Detection.
Use when modifying a CLI, API, SDK, CI job, workflow, or MCP server that has embedded LLM calls, model/provider config, or a bounded reasoning checkpoint and needs T2A authoring guidance.
Complete T2A Protocol capsules when a tool returns t2a.handoff, points to task.json, needs output.json, or asks for validation.
Complexity-management design principles — deep modules, information hiding and leakage, module boundaries, dependency direction, strategic vs. tactical tradeoffs. Triggered by planner-agent, plan-reviewer, implementer-agent, implementer-expert-agent, and code-reviewer before any design, implementation, or review work.
TDD cycle and code quality guardrails — failing-test-first, evidence, dependency, error-handling, and test-quality rules. Triggered by /speq-implement, implementer-agent, implementer-expert-agent, and code-reviewer before any implementation or review work.
Semantic code navigation and editing via Serena MCP — symbol-level tools preferred over grep/find/manual edits. Triggered by /speq-mission, /speq-implement, planner-agent, implementer-agent, implementer-expert-agent, code-reviewer, and recorder-agent.
Query specs via the speq CLI — semantic search, feature listing, structure validation. Use before reading any spec file; every speq orchestrator and sub-agent invokes this first for spec discovery, search, or validation.
Audit a speq project's health — spec-library structure, feature/decision-log/plan validation, mission-to-spec sync, unrecorded plans, and gitignore hygiene — then guide fixes. Use when the user asks to audit, health-check, doctor, lint, or sanity-check the specs or repo, or after cloning or inheriting a speq project.
External documentation and research via Context7 and WebSearch — library APIs and design patterns. Triggered by /speq-mission, /speq-implement, planner-agent, implementer-agent, and implementer-expert-agent when current external sources are needed.
Code review tag taxonomy and findings output format — guardrail violations, dead code, test quality, bad comments, optimizations, YAGNI/over-engineering, error handling, and design depth. Triggered by code-reviewer.
Read-only git guardrails and the Conventional Commits reference — no history writes, verify changes before completing. Triggered by planner-agent, implementer-agent, implementer-expert-agent, and recorder-agent; git-agent alone is exempt and uses /speq-git-operations instead.
Orchestrate implementation of a reviewed plan: task breakdown, TDD sub-agents, code review, and verification report. Use when the user asks to implement, build, or execute a plan under specs/_plans/ — after /speq-plan, before /speq-record. Arg: <plan-name>.
Create or update specs/mission.md through a Socratic interview; detects brownfield vs greenfield. Use when the user asks to bootstrap or initialize a speq project, write or revise the project mission, or when /speq-audit reports mission drift and seeds this skill with its findings.
Headless, non-interactive version of /speq-plan for CI or agent-driven runs. Plans a feature without a live interview, commits the result to a feat/plan-name branch, and opens a draft PR. If a decision genuinely needs a human, it persists the partial plan and open questions and asks in a PR comment instead of blocking. Arg: plan name, feature intent text, PR number, or branch name.
Plan-authoring workflow — spec delta authoring, test mapping, plan.md/decision-log.md generation, expert-task tagging, headless escalation, and revision mode. Triggered by planner-agent.
The git/gh operation-to-command mapping and return formats for git-agent — the sole write-permitted actor in this system. Triggered by git-agent.
Headless follow-up to /speq-plan-pr. Continues on a plan's feat/plan-name branch, runs /speq-implement, bumps the version, runs the real test suites, records only if green, then pushes, opens/updates the PR, and marks it ready. Arg: plan name, PR number, or branch name.
Adversarial plan-review method and challenge taxonomy — premortem framing, multi-axis challenge taxonomy, severity discipline, and findings output format. Triggered by plan-reviewer.
Plan a feature or change through a clarifying interview, producing spec deltas, plan.md, and decision-log.md via planner-agent with adversarial review. Use when the user asks to plan, spec, design, or scope a new feature, a change or removal of existing behavior, a refactor, or a fix — before any implementation.
Delta-merge procedure — DELTA marker semantics, library-organization thresholds, and ADR-promotion field mapping. Triggered by recorder-agent.
Merge implemented spec deltas into the permanent specs library and archive the plan. Use when implementation is verified — after /speq-implement produces verification-report.md — or when the user asks to record, merge, or archive a finished plan. Arg: <plan-name>.
Prose guardrails for speq artifacts and GitHub PRs, issues, and comments — front-loaded (BLUF), terse, unambiguous writing anchored in established style and requirements standards. Triggered by /speq-mission, /speq-audit, /speq-implement, /speq-plan-pr, /speq-implement-pr, planner-agent, plan-reviewer, and recorder-agent.
>- Design and scaffold an autonomous "loop" around a coding agent for a recurring workflow. Use when the user wants to stop hand-prompting an agent and instead build a system that discovers work, delegates it to a maker, verifies the result with a separate checker, remembers progress on disk, and re-runs until a goal is met or it stops for an honest reason. Triggers on "build a loop", "loop engineering", "automate this agent workflow", "design an agentic loop", "/goal", "/loop", "Ralph loop", "maker/checker", "run this overnight", "verifier rubric", or "loop contract". Works with Claude Code, Codex, Cursor, and OpenCode.
Use picocom to interact with IoT device UART consoles for pentesting operations including device enumeration, vulnerability discovery, bootloader manipulation, and gaining root shells. Use when the user needs to interact with embedded devices, IoT hardware, or serial consoles.
Claude Skills — questions
Answers built from the skills we actually parsed.