Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail. — from majiayu000/claude-skill-registry
Evoluciona una definición de agente existente refinando su persona en el lugar o creando una variante avanzada.
Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via EVOLVE_REQUIRE_INTENT=1.
Evoluciona una habilidad existente refinando su contenido en el lugar o creando una variante avanzada.
Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success…
Expert at performing task X automatically. Auto-invokes when the user wants to do Y, needs help with Z, or encounters situation W. — from bg-szy/TOP-SKILLS
Expert at performing task X automatically. Auto-invokes when the user wants to do Y, needs help with Z, or encounters situation W. — from bg-szy/TOP-SKILLS
An example skill demonstrating the basic structure. Use when user asks about examples or templates.
Read, write, edit, and format Excel files (.xlsx). Create spreadsheets, manipulate data, apply formatting, manage sheets, merge cells, find/replace, and export to CSV/JSO — from…
Run a retrospective audit or lookback on historical shipments/transactions (CSV or CRM export). Re-screen parties against current lists, re-check ECCNs and license determ — from…
Classify export items for ECCN (BIS/ITAR) using regulatory data and in-skill classification. Free to use.
Generate a CARFAX-style Export Compliance Report Card that an exporter can send to their customer. Aggregates classification, screening, license determination, country ri — from…
For a given country, produce a one-page summary of embargo/sanctions, Entity List/MEU density, typical license expectations, and high-level red flags for deal or territor — from…
Search the U.S. Consolidated Screening List (CSL) via the Trade.gov API. Use when the user wants to screen a party or entity against export screening lists, search the CS — from…
Convert ExChek markdown reports to client-ready Word (.docx) and provide prompt-style document output guidelines for agents in any environment (Claude, Perplexity, ChatGPT, etc.)…
Generate tailored Export Compliance Program (ECP) docs, SOPs, and training outlines from company footprint, product mix, and risk profile.
Draft export documentation (commercial invoice export block, packing list annotations, SLI, AES/EEI data elements) from shipment, classification, and screening results.
Determine whether an item is ITAR or EAR via a guided questionnaire (USML, specially designed, etc.) and produce a short jurisdiction memo with recommended next steps (DD — from…
Determine EAR license requirements and exceptions (Part 738 Country Chart, Part 740) for a given item, ECCN, destination, and end use.
Generate a compliance requirements pack for distributors/partners: screening expectations, re-export assurances, recordkeeping, and optional flow-down language.
Produce a retention schedule or checklist under 15 CFR 762 (and ITAR 22 CFR Part 122 where applicable) tailored to company activities (classification, licenses, screening — from…
Run BIS "Know Your Customer" red-flag checklist (Supp. 3 to Part 732) for a party/transaction. Produces an auditable red-flag assessment note (no/yes/conditional; escalat — from…
Score export/transaction risk (low/medium/high) from classification, CSL screening, destination, and end use.
Use when executing an approved implementation plan task-by-task. Dispatches one fresh subagent per task using an RTCO brief, receives the return through the report filter, runs…
Execute pending SDD tasks in dependency order with wave-based concurrent execution via subagent dispatch and structured verification.
Execute a significant implementation unit (phase or major slice) using a gated subagent loop (blueprint -> gate -> execute -> digest) without creating new persistent artifacts.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task, reviews once per phase, loads phases just — from…
Use once an analysis brief or pre-analysis plan is APPROVED and it's time to actually run the analysis — build the dataset, estimate the primary specification, run the robustness…
Use when orchestrating parallel phases in plan execution - creates isolated worktrees for concurrent task execution, installs dependencies, spawns parallel subagents, verifies…
Använd när du som expert på Expertbyrån ska skapa, förfina eller utöka din EGEN expertis — din EXPERT.md, dina principer, din arbetsmetod eller filerna under din egen…
Pattern for efficiently exploring codebases using parallel subagents. Use when you need to understand code structure, find patterns, or gather context.
Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional).
Turn external skill, rule, plugin, MCP, task-memory, and multi-agent workspace patterns into safe fixture coverage rather than live dependencies.
Extract a named SKILL.md section's body verbatim into a references/.md file, replace the body with a skeleton (section label + delegation pointer, runtime definitions left…
Route Claude tiers, effort, and subagents for Fable-led work, and handle Fable-specific prompting, long-running execution, API behavior, refusals, and fallback.
Single-command autonomous delivery orchestrator. Invoke it with a goal and a numbered Definition of Done (DoD) and it runs the whole job to completion — typically unattended,…
Use when the user wants a GitHub issue created by a Fable 5 subagent. Spins up a read-only subagent running on Fable 5 that executes the new-issue procedure (duplicate check, code…
Use when the user asks to have a Fable 5 subagent draft and file a GitHub issue, then autonomously drive it all the way to a reviewed PR in one shot — "fable-new-issue-loop",…
Use when the user wants a task decomposed and driven by a Fable 5 orchestrator delegating implementation to Sonnet 5 workers.
Launch a Fable 5 Max 1M subagent to do a deep, neutral senior-developer review of the current work and report its findings back verbatim.
Use when the user wants a task planned by a Fable 5 planning subagent before building it. Spins up a Plan subagent running on Fable 5 to produce an implementation plan, relays the…
Creates, edits, updates, or modifies Claude Code custom agents (subagents). Use when user asks to create agent, edit agent, update agent, subagent.
Dispatch the same query to multiple subagents in parallel across chunks in a manifest and aggregate results with source provenance
Orchestrates the full code-to-Figma rebuild workflow for a web application. Thin dispatcher that delegates all substantial work to subagents and reads only small summary files.
Sous-agent de traitement de fichiers — lecture, parsing, transformation et génération de fichiers multiformats.
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead.
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead.
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new skills to install.
에어코리아 기반 미세먼지/초미세먼지를 지역명 또는 위치 힌트로 조회한다. 기본 경로는 k-skill-proxy의 report endpoint다.
Skill lazy loading and search pack. On-demand SKILL.md loading and keyword-based skill search. 2 loader tools.
Scaffold a new Claude Code skill at `.claude/skills//SKILL.md` with the canonical Knack body pattern (frontmatter, when-to-use, inputs, steps, output format, worked-example…
Use when pulling, comparing, de-duping, curating or syncing skills across the agent fleet (primary nodes, worker nodes, media hosts, and approved client-bot profiles), or when…
Execute an approved plan with subagents, TDD, and two-stage review. Invoke with /flow-execute to resume or when plan exists without an active spec session.
본 스킬은 Flutter 프레임워크로 앱을 개발하는 데 반드시 따라야 하는 UI/UX 디자인, 상태관리, 네트워킹, API 연동에 관한 가이드라인 제공합니다. 본 스킬은 선택적인 정보를 제공하는 것이 아니라 Flutter 앱 개발에 필수적인 지침을 제공하며 반드시 준수해야 할 사항들을 제공합니다.
본 스킬은 Flutter 프레임워크로 앱을 개발하는 데 반드시 따라야 하는 UI/UX 디자인, 상태관리, 네트워킹, API 연동에 관한 가이드라인 제공합니다. 본 스킬은 선택적인 정보를 제공하는 것이 아니라 Flutter 앱 개발에 필수적인 지침을 제공하며 반드시 준수해야 할 사항들을 제공합니다.
The flight — execute the filed flight plan step by step. Creates the topic branch, dispatches a fresh TDD subagent per step, lands each step as its own commit, and tracks progress…
Provides real-time weather forecasts using OpenWeather API. Use when users ask about current or future weather conditions, temperature, precipitation, or weather-dependent…
How to produce a demand forecast for a SKU, and when to delegate that to a subagent vs. compute it yourself.
Create a new SKILL.md from scratch and iterate with forge eval until it passes the quality gate. Don't use for editing an existing skill — use forge-skill-improver instead.
Turn one recurring workflow from supplied or available conversations into a focused, evaluated skill candidate.