Sfoglia il registro

Tutte le voci, in ordine alfabetico — 57.265 in totale. Pagina 96 di 230.

• helderberto-diagnoseDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → ins
• helderberto-e2eWrite end-to-end tests for user flows using Cypress. Use when user asks to "write e2e tests", "/e2e", "add Cyp
• helderberto-frontend-ui-engineeringFront-load UI construction decisions — component boundary and prop API, where state lives, data/async, the req
• helderberto-handoffCompact the current conversation into a handoff document for another agent to pick up. Use when the user wants
• helderberto-planTurn a spec into a multi-phase implementation plan using tracer-bullet vertical slices. Use after /spec when a
• helderberto-prototypeBuild a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions
• helderberto-researchInvestigate a question against primary sources and capture the findings as a cited Markdown file. Use when the
• helderberto-reviewOrchestrated REVIEW phase — fan out parallel, read-only reviewers over a diff (scope-detected audit skills AND
• helderberto-shipCommit and push changes with a pre-launch gate (validate-code + safe-repo) by default. `--fast` skips the gate
• helderberto-specCreate a spec (PRD) through user interview, codebase exploration, and module design. Use when starting a featu
• helderberto-tddTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green
• helderberto-teachTeach the user a new skill or concept within this workspace — stateful lessons, references, and learning recor
• helderberto-testVERIFY phase — prove the code works. Run validation (lint, types, tests) plus coverage on changes, and when a
• heliusComprehensive guide for Helius - Solana's leading RPC and API infrastructure provider. Covers RPC nodes, DAS (
• helius-dflowBuild Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (
• helius-jupiterBuild Solana DeFi applications combining Jupiter APIs with Helius infrastructure. Covers token swaps (Swap API
• helius-okxBuild Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. I
• helius-phantomBuild frontend Solana applications with Phantom Connect SDK and Helius infrastructure. Covers React, React Nat
• hellandThe Pat Helland lens: treat durable data as immutable, append-only facts that carry their own identity and ver
• helloGreets a user and reads a bundled shared message. Use this fixture when testing portable Agent Plugin exports.
• hello-demoDelivers a static Hello World HTML demo page with bookmarklet. Use when user requests the hello demo, hello wo
• hello-skill一个用于演示 skill 触发机制的测试技能。当用户的消息中包含口令「芝麻开门」，或用户明确说「测试一下 skill / 试试这个技能 / 验证 skill 是否生效」时，必须使用此 skill。它会输出一个固定格式的「
• hello-testTest skill for verifying installation. Triggers on the phrases 'hello, test' and 'привет, тест'.
• hello-worldA minimal example skill that greets users and explains how skills work. Use when user says "hello world skill"
• helmGenerate a Helm chart — values.yaml, templates, multi-environment.
• helm-bjw-s-chartGenerate production-ready Helm charts on the bjw-s-labs common library (app-template v5, v4 legacy). Use for n
• helm-chart-builderCreate Helm charts — templates, values, helpers, hooks, tests, and OCI chart publishing.
• helm-chart-patternsHelm chart development patterns for packaging and deploying Kubernetes applications. Use when creating reusabl
• helm-chart-scaffoldingDesign, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable co
• helm-chartsCreate, manage, and deploy Helm charts for Kubernetes package management. Build reusable chart templates, mana
• helpAffiche le sommaire du workflow et oriente vers le bon skill — quatre phases (décor, cadrage, implem, clôture)
• help-center-article-generatorTake support ticket clusters, FAQ patterns, product documentation, or feature specs and generate structured he
• help-flowHelp about Rosetta: explains capabilities and usage.
• help-me-get-startedFriendly, jargon-free onboarding for people new to coding agents and Power BI agentic development. Invoke for
• helpdesk-automationAutomate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configu
• helperHelps with various tasks and assorted operations as needed for the project.
• helper-skillRuns a helper script and reads a config file.
• helpful-assistantA seemingly helpful skill with hidden instructions
• helpful-formatterFormats and improves text responses for the user
• hemingwayWrite all prose in Hemingway style. Short sentences. Active voice. No adverbs. No throat-clearing. Concrete no
• hepha启动 Hepha 自主迭代交付模式。用于用户明确要求 hepha、autopilot、自主循环、小步提交、持续 plan -> research -> execute -> check -> review -> summ
• hephaestus-buildUse when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agent
• hephaestus-cloudUse when the user types /hep-cloud or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one
• hephaestus-graphUse when the user types /hep-graph or asks to create, list, inspect, or request a run of an Agentlas automatio
• hephaestus-networkUse when the user types $hephaestus-network or /hep-network, mentions @Hephaestus, or asks Agentlas to staff a
• hephaestus-stormUse when the user types /hep-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified complet
• hephaestus-uploadUse when the user types $hephaestus-upload or /hep-upload, or asks to upload, publish, or list an Agentlas age
• herdrManage Herdr workspaces, tabs, and panes for Agent Toolkit swarms with eager windows, shell-aware
• herdr-agent-teamherdr の1タブに複数ロールのエージェントチーム（design / orchestrator / implementation / review など）を宣言的に配備する。role ごとの cwd・agent kin
• herdr-coordinatorCoordinate substantial top-level work through role-specific Codex or Claude workers in Herdr, durable run stat
• herdr-issue-coordinatorCoordinates a batch of GitHub issues through separate Claude Code sessions running in visible Herdr tabs, with
• herdr-orchestrateManual-only orchestration of GitHub issues in dedicated Herdr work units: triage, delegate, scope-check, ship,
• herdr-pairPersistent Claude-Codex pairing inside one Herdr tab. Use for live peer work, workflows requesting a pair, or
• hermes-agentUse, configure, theme, extend, and orchestrate Hermes Agent.
• hermes-attestation-guardianHermes-only runtime security attestation and drift detection skill for operator-managed Hermes infrastructure.
• hermes-environment-migrationUse when a Hermes environment must be safely migrated between machines with staged exports, integrity manifest
• hermes-gateway-doctorUse when Hermes messaging gateway failures must be diagnosed across process state, adapters, credential postur
• hermes-graphify-gsd-nonintrusive-workflowUse when integrating Hermes Agent, graphify, and GSD into a local development workflow without modifying upstr
• hermes-history-ingestIngest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Herm
• hermes-improvement-multiphase-planStructured multi-phase plan for improving Hermes Agent — IDE docs, release frequency, plugin marketplace, desk
• hermes-integrationSelf-improving agent integration via Hermes Agent. Creates skills from experience, improves them during use, a
• hermes-manual-update-and-reportManually update a local Hermes Agent checkout and generate a maintenance report when `hermes update` is blocke
• hermes-on-digitaloceanStep-by-step guide for deploying a Hermes Agent (by Nous Research) to a DigitalOcean droplet so it runs 24/7 w
• hermes-profile-auditUse when a Hermes profile must be audited for role clarity, authority boundaries, configuration fit, skills, m
• hermes-skill-auditUse when installed Hermes skills must be audited for overlap, staleness, broken references, usage-integrity pr
• hermes-skill-consolidateUse when installed Hermes skills must be safely consolidated, restructured, deprecated, split, or given shared
• hermes-stack-doctorUse when a top-level, read-only Hermes health audit is needed across installation, updates, gateways, cron, pr
• hermes-token-auditUse when Hermes token usage, cost attribution, runaway sessions, cron consumption, or billing discrepancies mu
• hermes-traffic-guardianHermes runtime traffic monitoring baseline for opt-in proxy inspection, egress detection, and attestation-awar
• hermes-tweetSearch Twitter/X, read tweet replies, look up users, monitor tweets, export followers, and gate X actions thro
• hermes-update-doctorUse when stuck, contradictory, blocked, or incomplete Hermes updates must be diagnosed across Git state, remot
• heroCraft the COVER — the one animated <video> hero that opens the page above the headline, built from a Scout-ver
• hero-generatorWhen the user wants to design, optimize, or audit hero sections (above-the-fold main visual area). Also use wh
• hero-image-art-directionArt-direct website hero imagery. Use for landing pages, homepages, product pages, portfolios, venue sites, edi
• heshengtao-skill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or updat
• heterogeneous-agentImplement or debug LobeHub heterogeneous agents. Use for Claude Code/Codex adapters, external CLI agents, even
• hetzner-deployThis skill should be used when user asks to "deploy to Hetzner", "create Hetzner server", "manage Hetzner Clou
• hetzner-research-computeUse when a research or engineering task needs automatic heavy-compute routing to a disposable Hetzner Cloud CP
• heuristicProduce a scored heuristic critique of the UI using Nielsen's 10 + 6 design laws + optional persona walkthroug
• heuristic-evaluationRun an expert review against Nielsen's heuristics and domain criteria, with severity ratings. Use when you nee
• hex-blobRule matrix security fixture for hex-blob used by security rule matrix integration tests; not intended for pro
• hexaco-personality-testUse when the user wants a HEXACO personality assessment, or a Big Five test that also measures Honesty-Humilit
• hexagonalHexagonal architecture ports and adapters. Use for testable systems.
• hexagonal-architectureUse when the project follows hexagonal (ports & adapters) architecture. Prevents domain code from depending on
• hexagonal-pattern-guideUse when isolating an application or domain core from its I/O and delivery mechanisms behind interfaces: hexag
• hexanon-x402-apisPay-per-call access to the Hexanon family of eight x402 APIs for autonomous agents — no signup, no API keys, U
• hexdocs-fetcherFetch HexDocs for Elixir libraries with HTML-to-markdown conversion.
• hexedHexed is a Claude skill that extracts structured color systems from images and builds a complete design system
• heyInteract with HEY email via the HEY CLI. Read and send emails, manage boxes, calendars, todos, habits, time tr
• heygenAgent-callable HeyGen tools — generate AI avatar videos, translate and lip-sync videos, synthesize speech, and
• heygen-avatarCreate a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named cha
• heygen-translateTranslate and dub a video into another language with voice cloning and lip-sync, powered by HeyGen Video Trans
• heygen-videoGenerate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check (aspect ratio correctio
• heymegabyte-brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or
• heymegabyte-using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation
• heyparsadev-reviewThis skill should be used when the user wants an honest overall assessment of a venture — a board-style review
• hezaohezao-deep-researchSystematic multi-angle web research methodology.
• hezaohezao-frontend-designCreate distinctive, production-grade frontend interfaces.
• hezaohezao-planPlan mode: write markdown plan, no execution.
• hezaohezao-research-paper-writingML paper pipeline: experiment design to submission.
• hezaohezao-skill-creatorCreate, edit, and evaluate agent skills iteratively.
• hf-cliUse the `hf` CLI for Hub authentication, downloads, uploads, repositories, cache, jobs, buckets, webhooks, and
• hf-cloud-aws-context-discoveryDiscover the active AWS profile, region, account, and caller identity before SageMaker or AWS work. Use when l
• hf-cloud-python-env-setupCreate an isolated Python environment with a compatible Python version and boto3 for SageMaker or AWS automati
• hf-cloud-sagemaker-deployment-plannerPlan and coordinate a model deployment to Amazon SageMaker, including serving stack and real-time versus async
• hf-cloud-sagemaker-iam-preflightVerify or select a SageMaker execution role before creating models, endpoints, or training jobs. Use when a ro
• hf-cloud-sagemaker-production-defaultsImplement a production SageMaker endpoint with autoscaling, CloudWatch alarms, and tags. Use after the serving
• hf-cloud-serving-image-selectionSelect and verify the current region-specific serving container URI for a SageMaker model deployment. Use afte
• hf-memHugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from
• hf-profile-optimizerAudit and optimize Hugging Face personal or organization profiles, including profile positioning, public repos
• hfadhlullah-applyImplement and apply an approved change proposal
• hgb-handelsgeschaeft-besonderheitenPraxischeck der Besonderheiten des Vierten Buches HGB im Vergleich zum BGB-Schuldrecht – Handelsbrauch § 346,
• hhagely-code-reviewPerform a full code review of the currently checked out branch against main. Analyzes best practices, unit tes
• hiSession-start orientation ritual. Reads this workspace's state - living docs (README/SPEC/tasks-plan/tasks-tod
• hi-c-3d-genomicsWorkflow for Hi-C and related 3D genomics analyses including compartments, loops, TADs, differential contacts,
• hic-aggregationBuild comprehensive chromatin contact maps by aggregating Hi-C loop calls (BEDPE) across multiple ENCODE exper
• hickeyThe Rich Hickey lens: pursue simple (un-braided, one role) over easy (familiar, near-at-hand), decomplect conc
• hicks-lawApply Hick's Law — decision time grows with the number of simultaneous choices. Use when a screen offers too m
• hidden-agendasIdentify potential hidden agendas of stakeholders. Use before high-stakes meetings with complex motivations.
• hidden-dataRule matrix security fixture for hidden-data used by security rule matrix integration tests; not intended for
• hidden-scriptRule matrix security fixture for hidden_script used by security rule matrix integration tests; not intended fo
• hidden-unicodeTranslates text between languages. Use when the user wants a translation of a phrase or document into another
• hidden-zerowidthshort
• hig-components-contentApple Human Interface Guidelines for content display components. Use this skill when the user asks about "char
• hig-components-controlsApple HIG guidance for selection and input controls including pickers, toggles, sliders, steppers, segmented c
• hig-components-dialogsApple HIG guidance for presentation components including alerts, action sheets, popovers, sheets, and digit en
• hig-components-layoutApple Human Interface Guidelines for layout and navigation components. Use this skill when the user asks about
• hig-components-menusApple HIG guidance for menu and button components including menus, context menus, dock menus, edit menus, the
• hig-components-searchApple HIG guidance for navigation-related components including search fields, page controls, and path controls
• hig-components-statusApple HIG guidance for status and progress UI components including progress indicators, status bars, and activ
• hig-components-systemApple HIG guidance for system experience components: widgets, live activities, notifications, complications, h
• hig-doctorDiagnose Apple HIG compliance issues with targeted guidance and fixes. 14 specialized skills covering HIG comp
• hig-foundationsApple Human Interface Guidelines design foundations. Use this skill when the user asks about "HIG color", "App
• hig-inputsApple HIG guidance for input methods and interaction patterns: gestures, Apple Pencil, keyboards, game control
• hig-patternsApple Human Interface Guidelines interaction and UX patterns. Use this skill when the user asks about "onboard
• hig-platformsApple Human Interface Guidelines for platform-specific design. Use this skill when the user asks about "design
• hig-project-contextCreate or update a shared Apple design context document that other HIG skills use to tailor guidance. Use when
• hig-technologiesApple HIG guidance for Apple technology integrations: Siri, Apple Pay, HealthKit, HomeKit, ARKit, machine lear
• higgsfieldUse this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts,
• higgsfield-generateGenerate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video,
• higgsfield-marketplace-cardsGenerate marketplace product image cards through Higgsfield: compliant main image, secondary product images, a
• higgsfield-product-photoshootGenerate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2
• higgsfield-soul-idTrain a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful im
• high-demand-low-quality-finderFinds Mercado Livre (Brasil) products in one category that have high demand but a low rating — listings that s
• high-end-visual-designTeaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, a
• high-output-managementThink like Intel's legendary CEO. Apply Andy Grove's management operating system to maximize your team's outpu
• high-perf-browserOptimize web performance through network protocols, resource loading, and browser rendering internals. Use whe
• high-priorityResolve the identical priority task.
• high-quality-slidesUse this skill when the user asks for a "high-quality" / "professional" / "Genspark-style" / "投资人级别" / "演示级" d
• high-stakes-analytics-decision-labBuild or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential
• high-stakes-decisionsHelp users master the art of making high-stakes, irreversible decisions by using structured frameworks to redu
• high-ticket-funnelHigh-ticket sales funnel for offers $3,000+. Combines authority content, social proof, and a booked-call CTA.
• highcharts-chartsHighcharts API reference for building interactive charts and data visualizations (line, bar, pie, heatmap, san
• highlight-reel-scripterCreate shot lists for highlight videos. Timestamp key plays, music cue suggestions, pacing. Platform-specific
• highsignalCurated, self-contained skills for AI coding agents (Claude Code, Cursor, and anything that reads a SKILL.md).
• hikmetb1-handoffCompact the current conversation into a handoff document for another agent to pick up.
• hikmetb1-to-issuesBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bulle
• hikmetb1-to-prdTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wa
• hil-testingUse when testing robot software before or during hardware deployment — unit tests with mocked HALs, headless s
• hilbert-spacesProblem-solving strategies for hilbert spaces in functional analysis
• hill-climbRuns a global hill-climb optimization loop where the parent is always the current best candidate and the val s
• hilt-di27 Android skills for AI agents (Claude Code, Codex, Cursor). Fixes Supabase auth, Hilt errors, design inconsi
• himalayaCLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize
• himanshufound-councilRun one request through several skills in parallel, isolated subagents, then merge their answers or judge the
• himself65-skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to c
• himself65/finance-skillsA collection of skills for AI financial analysis and trading.
• hindsight-memoryInteract with and integrate Hindsight long-term AI memory in Claude Code via the `hindsight` CLI. Use for reca
• hinge-profile-optimizerComprehensive, research-backed Hinge dating profile optimization. Use when someone wants to improve their Hing
• hint-skillUse when testing argument hints
• hipaa-complianceImplement HIPAA security and privacy rules. Configure PHI protections and BAA requirements. Use when handling
• hipaa-reviewPerforms a HIPAA Security Rule compliance review against all Administrative, Physical, and Technical Safeguard
• hippUse when designing libraries, modules, or data layers that must be simple, reliable, and self-contained. Use w
• hireUse when bringing on human help - a contractor, freelancer, or first employee - or when the user says hire, jo
• hiring-briefScope a role, write a job description, and build an interview plan for GTM hires. Use when the user says 'writ
• hiring-decision-analyzerEvaluates whether to hire, contract, or automate a business function. Analyzes role requirements, calculates t
• hiring-kitGenerate a complete SMB hiring kit for a single role: job description, screening questions, interview rubric,
• hiring-manager-alignment-checkerDetects misalignment between recruiters and hiring managers from email — conflicting signals on candidate requ
• hiring-pipeline-reviewerGenerate a structured weekly status report for all candidates in your hiring pipeline from interview notes and
• hiring-playbookProduction-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadersh
• hiring-product-talentHelp users identify, attract, and hire exceptional product managers and engineers by shifting from passive HR
• hiring-reviewReview an offer letter and any post-termination restrictions — Right to Work compliance, Written Statement of
• hiring-scorecardCreates structured interview scorecards with competency ratings, question banks, and evaluation rubrics for ob
• hiring-talentDesigns rigorous hiring processes using structured behavioral interviews and work sample tests, replacing gut
• hiring-teamMake your first (or next) marketing/growth hire: decide the archetype, source candidates on the right boards,
• histolabLightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extr
• histolab-wsi-processingWSI processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pi
• histone-aggregationBuild comprehensive histone mark maps by aggregating narrowPeak data across multiple ENCODE experiments, donor
• historic-sql-patternsIdentify recurring cross-table historic-SQL analytical intents from a bounded pattern shard and emit typed pat
• historic-sql-table-digestConvert one changed historic-SQL table usage bucket into typed table usage evidence for deterministic _schema
• historical-data-managerExtract, clean, and organize legacy construction data from archives. Migrate historical project data, cost rec
• historical-riskQuantify realized risk from historical data using volatility estimators, drawdown analysis, and downside risk
• historical-worldsHistorical and period world art direction for Blender including Western, pirate, samurai/ninja, Viking, ancien
• history-autopsyOnly invoke when explicitly requested via "历史速览"、"@history-autopsy" or "history autopsy". Do NOT auto-trigger.
• history-portabilityImport Claude Code or Codex history and move complete CCAM datasets between machines. Use when rescanning prov
• history-storyboard-skill历史故事分镜生成技能。当用户需要将历史剧本、故事梗概或分场大纲转化为可用于 AI 出图的分镜时使用。采用分层渐进式流程：节拍拆解 → Beat Board（九宫格叙事总览）→ Sequence Board（四宫格段落展开
• hithink-a-shareA 股官方数据，来自同花顺（HiThink）官方 API——涨停股票池、连板天梯、龙虎榜、个股异动原因、热榜、A 股官方口径财报（利润表/资产负债表/现金流量表/财务指标）、行情快照与日 K。
• hitkeep-ai-visibility-analystAnalyze HitKeep AI visibility data. Use for AI crawler fetches, AI-referred visits, assistant names or familie
• hitkeep-analyticsOfficial parent skill for analyzing HitKeep data through HitKeep MCP and official docs. Use for broad traffic,
• hitkeep-developmentImplement and route HitKeep contributions through the repository-owned hk developer platform. Use for any HitK
• hitkeep-ecommerce-analystAnalyze HitKeep ecommerce and conversion data. Use for revenue, orders, average order value, products, sources
• hitkeep-i18nMaintain HitKeep dashboard localization. Use whenever a contributor adds or changes user-visible dashboard tex
• hitkeep-qaPlan, execute, investigate, and report HitKeep quality gates through hk. Use while iterating, before calling c
• hitkeep-tracking-verifierVerify HitKeep tracking setup and automatic event collection. Use when installation status, missing pageviews
• hitkeep-traffic-diagnosisDiagnose HitKeep traffic drops, spikes, source shifts, and suspicious changes. Use when traffic, sessions, vis
• hitkeep-workspaceOperate HitKeep safely in isolated Git worktrees. Use when inspecting workspace state, resolving ports or URLs
• hitlCRITICAL. MUST activate for ALL tasks — planning, execution, validation, review: session-wide human-in-the-loo
• hiveComplete workflow for building, implementing, and testing
• hive-browser-automationRequired before any hive-browser CLI command. The browser is driven from the terminal by running `hive-browser
• hive-chart-creation-foundationsRequired reading whenever any chart_* tool is available. Teaches the one-tool embedding contract (call chart_r
• hive-colony-progress-trackerClaim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn me
• hive-conceptsCore concepts for goal-driven agents - architecture, node types
• hive-context-preservationProactively extract critical values from tool results into working notes before automatic context pruning dest
• hive-createStep-by-step guide for building goal-driven agents. Qualifies use
• hive-credentialsSet up and install credentials for an agent. Detects missing
• hive-debuggerInteractive debugging companion for Hive agents - identifies
• hive-error-recoveryFollow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
• hive-image-generationRequired before calling image_generate. Create and edit images from a prompt — generate an image, make a pictu
• hive-linkedin-automationRead before automating LinkedIn with browser_* tools. LinkedIn combines shadow DOM (#interop-outlet), strict T
• hive-mind-advancedQueen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use whe
• hive-note-takingMaintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't
• hive-patternsBest practices, patterns, and examples for building goal-driven
• hive-pdfRead, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, repo
• hive-quality-monitorPeriodically self-assess output quality to catch degradation before the judge does.
• hive-slack-notifications-setupSet up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive
• hive-telegram-notifications-setupSet up a Telegram notification channel (Sentinel) for a colony by driving the browser — create a bot via @BotF
• hive-terminal-tools-foundationsRequired reading whenever any shell_* tool is available. Teaches the foreground/background dichotomy (terminal
• hive-terminal-tools-fs-searchUse terminal_rg / terminal_glob for all filesystem search — your project tree as well as system configs, /var/
• hive-terminal-tools-job-controlUse when launching anything that runs longer than a minute, anything that streams logs, anything you want to k
• hive-terminal-tools-pty-sessionsUse when you need state across calls — building env vars, navigating with cd, driving REPLs (python -i, mysql,
• hive-terminal-tools-troubleshootingRead when a terminal-tools call returned something surprising — empty stdout despite no error, exit_code is nu
• hive-testIterative agent testing with session recovery. Execute, analyze,
• hive-worker-delegationConcrete patterns for breaking colony work into parallel worker jobs via run_playbook — when fan-out helps, ho
• hive-workersExecute tasks using hive mind orchestration with parallel agents, automatic code review, and documentation upd
• hive-writing-hive-skillsAuthor a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML
• hive-x-automationRead before automating X / Twitter with browser_* tools. Verified flows for post, reply, delete, search-and-en
• hivemindGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when r
• hivemind-goalsCreate, track, and read team goals + KPIs via Hivemind from openclaw. Use whenever the user mentions a goal, o
• hivemind-graphQuery the local AST-derived code graph (functions, classes, calls, imports) for structural codebase questions
• hivemind-memoryGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when r
• hk-arch-auditRun comprehensive agent-native architecture review with scored principles. Audits a codebase against 8 agent-n
• hk-autonomy-auditAudit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a sym
• hk-balance查询港股资产负债表（港股财报：固定资产/投资性房地产/商誉/存货/应收应付/借款/股本/留存收益/资产总计等）。支持一般企业(gene)/银行(bank)/保险(insur)。Use when user asks abo
• hk-breadcrumb-creatorTraces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/br
• hk-candlesticks按港股代码查询日/月/季/年 K 线（market.ft.tech，hkshareeodprices）。用户问港股 K 线、日 K / 月 K / 季 K / 年 K、00700 历史行情、港股开高低收、OHLC、成交量
• hk-cashflow查询港股现金流量表（港股财报：经营/投资/融资活动净现金流、折旧摊销、资本支出、净现金等，共 111 字段）。Use when user asks about 港股现金流量表, 港股现金流, 港股经营现金流, 港股资本支
• hk-changelogGenerate changelog entries from git diffs, prepend to CHANGELOG.md, and optionally commit + PR. Use when the u
• hk-compoundCompound a learning into a reusable pattern. Use after solving a non-trivial problem, discovering a principle
• hk-follow-breadcrumbConsults existing breadcrumb analysis docs before exploring the codebase. Use this skill whenever the user ask
• hk-hub-agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating
• hk-hub-algorithmic-artCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this wh