В каталоге 183 730 навыков в 14 категориях.
Use for large features spanning multiple platforms or autonomous end-to-end implementation. Runs the full plan-implement...
Recommend the right /ha: command for planning, review, debug, submit, or test tasks. Use when "which command", "what sho...
Learns from your work patterns across sessions. Detects repeated corrections, preferences, and workflows, then automatic...
Drafts U.S. HACCP plans for food production under FDA or USDA regimes. Triggers on requests involving HACCP plans, food...
User-invoked side-route for a judged, time-boxed hackathon day: turns the event brief into a scored project choice, an o...
Intent Pre-cognition Engine — builds a probability-ranked map of the 5 most likely underlying intents, surfacing hidden...
Create original short videos using the 手势边界换媒｜局部窗口、多形态验真与回归 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the us...
Manage human-in-the-loop approval workflow for sensitive actions like payments, email sending, social media posts, and f...
Strategies for reading, chunking, and processing files that exceed practical token limits. Covers streaming reads, selec...
Generate a self-contained handoff prompt that lets the user continue work in a fresh coding agent session with empty con...
Deprecated name. Use session-handoff; load this notice only when handoff is explicitly requested.
Compacts the current conversation into a single self-contained handoff document under docs/handoffs/ so a fresh agent —...
Compact the current conversation into a handoff document for another agent to pick up, referencing existing artifacts (P...
Compact the current conversation into a portable handoff document, with an optional live clarification path for compatib...
Capture current work context for handoff to another agent/developer. Gathers git state, todos, and modified files into a...
Create a concise, redacted handoff brief for continuing work in a future session or another agent. Adapted from handoff;...
Generates a structured Markdown handoff file to move an active conversation into a new chat, preserving full context, de...
Maintain a concise, executable `.notebook/HANDOFF.md` representing only the last verified operational state. Use when th...
Use when passing work, tasks, or deliverables between agents. This skill provides a standardized protocol for agent-to-a...
Hand off a bounded task to a chosen coding agent in a right-hand Herdr pane using a conversation snapshot.
How to draw hands in drawn-by-code, in any style. Use it before drawing, redrawing or reviewing any hand, and whenever a...
Contract for hands-off mode — the ultrapack workflow variant that minimizes user prompts after Design, takes the safest...
Audit the `bd remember` store and recommend which entries to prune, so each one earns its per-session `bd prime` injecti...
Configures a harness. A meta-skill that defines specialized agents and creates the skills those agents will use. Use whe...
Design lens: which layer a harness mechanism belongs in, and whether it outlives the next model or runtime.
CDO design lead. Owns brand system, UI/UX direction, references, mockups, and design-review hiring.
Keep agent configuration — instructions, skills, commands, agents, MCP registrations, hooks, permissions, and reusable p...
COO planning lead. Hires planners, researchers, hypothesis developers, documentation workers, technical writers, visual...
CQO quality and operational governance lead. Owns gates, regression strategy, memory hygiene, port/service policy, and a...
CTO development lead. Hires engineering workers, designs platform/API/account wiring, supervises implementation, and rep...
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, schedu...
Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same...
Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-...
HR hiring. Searches .harness/shared/HR-Resource candidates, installs selected worker skills into .claude and .codex, and...
Resource manager. Maintains hired-worker wording, aliases, keyword mapping, and hire recommendations.
Operate google-research/harness2 (Harness²), the Apache-2.0 framework for recursive agent harnessing: refine the prompts...
Promote .agents knowledge.
Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches...
Generic health check and data freshness monitoring patterns for marketing intelligence systems. Use when validating conn...
医疗行业企业融资监控系统。实时监控医疗健康企业的工商变更，识别融资信号，自动推送告警。支持天眼查/企查查数据采集、AI融资判断、多渠道推送。
Writes nursing, allied-health, clinical support and healthcare administration resumes. Keeps licenses, placements, clini...
Step-by-step guidance for healthcheck.
Creates and manages scheduled background tasks using macOS launchd.
Master-Heir synchronization, contamination prevention, and promotion workflows
Show available GSD commands and usage guide
Context-aware guide that tells you where you are in the workflow and what to do next. Use anytime you're unsure.
Explains what the studio can do, lists skills and agents by category, and suggests what to do next based on project stag...
Use when the user runs /henneth. Boots (or reuses) one standing background web server, shared across all sessions, that...
Shift the assistant by rewriting SOUL.md with a warm AI persona, elegant tone, emotional attunement, and fluid conversat...
Guide the main agent in routing workflow-shaped tasks, managing context, explaining project status, and integrating work...
Start and arrange managed orchestrators or dispatch registered local project tasks through Computer and Project Orchestr...
Automate Here tasks via Rube MCP (Composio). Always search tools first for current schemas.
Publish sites to {slug}.here.now and store files in Drives.
Review condition and treatment evidence, plan preventive care and site conservation, record historic fabric, and organiz...
Configure, troubleshoot, update, or extend Hermes Agent itself. Use this before answering questions about Hermes CLI com...
hermes-context-optimization — Optimize Hermes startup/context payloads, compression, tool-schema loading, memory/skill i...
Use when Hermes acts as the vault coordinator for canonical promotion, duplicate-topic consolidation, merge decisions, a...
Diagnose Hermes cron jobs that ran successfully at scheduler level but produced empty, missing, or non-actionable user o...
Create lightweight Hermes cron jobs that offload work into a local pre-run script, avoid chat-context overhead, and send...
Continuous self-improvement system for Hermes Agent. Analyzes your past sessions to find recurring failures and skill ga...
Use when Hermes messaging gateway failures must be diagnosed across process state, adapters, credential posture, logs, d...
Load when Claude, Codex, Antigravity, or another external agent needs to call Hermes GPT as a worker, ask it to use Herm...
Use when an existing conversation, plan, specification, or objective must become a Hermes-native Kanban board with verif...
hermes-nightly-self-check-decisions — Record decisions from nightly self-check findings so behavior is consistent.
Use for unattended Hermes continuity and watchdogs.
Use when a Hermes profile must be audited for role clarity, authority boundaries, configuration fit, skills, memory post...
Use when a Hermes session, profile, machine, or agent must hand ongoing work to a fresh continuation context without los...
Use when installed Hermes skills must be audited for overlap, staleness, broken references, usage-integrity problems, an...
Use when a top-level, read-only Hermes health audit is needed across installation, updates, gateways, cron, profiles, sk...
Use when Hermes token usage, cost attribution, runaway sessions, cron consumption, or billing discrepancies must be inve...
Use when stuck, contradictory, blocked, or incomplete Hermes updates must be diagnosed across Git state, remotes, runnin...
Manage Heroku config vars safely across environments. Use when the agent needs to inspect, compare, set, remove, or audi...
Manage Heroku pipelines and review apps with stage-aware guardrails. Use when the agent needs to inspect or configure He...
Use when the user asks to build a heterostructure, interface, van der Waals stack, substrate-film system, or lattice-mat...
Route and classify Hetzner Cloud tasks to the narrowest qualified specialist — cost optimization, infrastructure review,...
Standardized workflow for creating and publishing Hexo blog posts with local preview and deployment.
hf-model-card-research — Pull structured benchmark metadata, download stats, and quality claims from HuggingFace model c...
Use when after running the ENCODE Hi-C uniform processing pipeline or Juicer on FASTQ input data and generating a .hic o...
| Skill | Path | Description |
Get a progressive hint for the current problem. Use when user is stuck and asks for help.
Fillable private persona-review profile template for workstyle preferences and weakness guardrails. Copy into a private...
Help find and book a service provider for a task — cleaning, handyman, moving, assembly, yard work, errands, etc. Search...
Job descriptions, interview scorecards, take-home assignments, and evaluation rubrics.
WSI processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pipelines fo...
Convert human-only blockers into visible GitHub issues. Use when work is blocked by missing credentials, secrets, DNS, b...
Classifies an AI process against a four-level Human-in-the-Loop maturity model (Smoke-and-Mirrors, Reactive HOTL, Intent...
Use when coordinate multi-agent consensus using TiDB-backed shared memory. Use when agents need to agree on decisions or...
Required before any hive-browser CLI command. The browser is driven from the terminal by running `hive-browser <command>...
Manage tasks and projects on a self-hosted Vikunja instance (PERSONAL/WORK). Use when the user wants to create, view, co...
Create, track and update team goals + KPIs via the Deeplake virtual filesystem at memory/goal/ and memory/kpi/. Use when...
Traces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/breadcrumb_a...
Iteratively improve any output by running a structured observe-hypothesize-change-rerun loop. Uses an organized scratch...
Use when you need to characterize score distributions of a profile HMM on random sequences, such as calibration checks,...
Hofstadter-io hof: CUE-powered code generation with flow engine and VS Code agent
Process invoice emails: download PDF attachments, extract vendor + date, generate normalized filename, and send to Holde...
Drive a hard mathematical conjecture toward resolution across competing proof routes while staying epistemically honest:...
Use when the user asks for honesty, a hard audit, a skill audit, best work, no half-finished output, when a deliverable...
Creates and registers hooks for the Claude Code framework. Handles pre/post tool execution, validation, memory, and sess...
Use when automating agent behavior with lifecycle hooks. Covers hook events, deterministic enforcement of rules the mode...