发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
neo4j
Neo4j graph database reference. Covers Cypher query language, node/relationship CRUD, path traversal, shortest path, graph algorithms (PageRank, Louvain, similarity), indexes, constraints, full-text search, and Python driver usage.
sandwich
Analyze sandwich operations. Use when you need to understand sandwich mechanisms, evaluate protocol security, or reference on-chain concepts.
symptom-checker
Symptom self-check tool: symptom analysis, guidance on when to see a doctor, prevention measures, lifestyle improvement tips, symptom tracking, and emergency recognition. ⚠️ Not a medical diagnostic tool. Use when you need symptom-checker capabilities. Triggers on: symptom checker.
dignified-python-313
This skill should be used when editing Python code in the erk codebase. Use when writing, reviewing, or refactoring Python to ensure adherence to LBYL exception handling patterns, Python 3.13+ type syntax (list[str], str | None), pathlib operations, ABC-based interfaces, absolute imports, and explicit error boundaries at CLI level. Also provides production-tested code smell patterns from Dagster Labs for API design, parameter complexity, and code organization. Essential for maintaining erk's dignified Python standards.
ARB Translation Updater
Batch update ARB translation files across all languages when new translation keys are added to English and Chinese files; use when adding new i18n strings to the Flutter app.
check-data-against-backup
Compare a data file against a backup or prior version. Cell-level diff with float tolerance, key-based alignment, and structured verdicts. Use when verifying that dataset changes are intentional.
Next.js 16 Launchpad
Next.js 16 with Turbopack, Cache Components, and proxy.ts. Use for bootstrapping, migrating, and building with App Router and React 19.
music
Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.
facebook-group-monitor
Monitor Facebook groups for new posts using Playwright browser automation with stealth mode and a persistent login session. Scrapes the group feed, tracks seen posts, and reports only new ones. Captures a single stitched "feed strip" screenshot (viewport scroll + Pillow stitch) for efficient LLM vision analysis — one image covers the full feed. Use when: monitoring Facebook groups, scraping FB posts, checking new group activity, Facebook automation, marketplace monitoring, book sale tracking, competitor group monitoring. Triggers: 'check Facebook group', 'scrape FB posts', 'new posts in group', 'monitor group', 'Facebook marketplace', 'group update'.
guide-integrator
Use when designing features — loads plugin methodology references, fetches online developer guides for Drupal domain knowledge, and optionally loads a user's custom guides
Auditing Security
Identify and remediate vulnerabilities through systematic code analysis. Use when performing security assessments, pre-deployment reviews, compliance validation (OWASP, PCI-DSS, GDPR), investigating known vulnerabilities, or post-incident analysis.
Writing Like User
Emulate the user's personal writing voice and style patterns. Use when the user asks to write content in their voice, draft documents, compose messages, or requests "write this like me" or "in my style."
test-rag
Test the RAG system by starting the FastAPI server and sending a query
pre-mortem
Run a project pre-mortem using multiple AI agents as diverse team members. Spawns parallel agents with different failure-finding mandates, synthesizes into ranked risks with mitigations. Use when starting a project, before a launch, before committing to an architecture, or when the user says "pre-mortem", "what could go wrong", "risk analysis", or "failure modes".
create-purchase-return
Create a Purchase Return (PRT) when returning defective goods to a supplier
nafv4-physical-resources
Create and manage NAF v4 (NATO Architecture Framework) / ADMBw Physical Resource Specification Viewpoints (P1–P8, Pr) in Sparx Enterprise Architect. Use when the user wants to create P1 (Resource Types), P2 (Resource Structure), P3 (Resource Connectivity), P4 (Resource Functions), P5 (Resource States), P6 (Resource Sequence), P7 (Data Model), P8 (Resource Constraints), or Pr (Configuration Management) diagrams, add resource elements, create associations between resources, or work with NAF physical architecture modeling. Also triggers on natural language like "system", "resource type", "function", "interface", "protocol", "state machine", etc.
orchards
Join Orchards, build agent communities, collect digital certificates, and participate in direct-purchase commissions and eligible member distributions. Use for Orchards registration, social activity, Bitcoin account operations, purchase syndication, and purchase safeguards.
quickshell
Implement, debug, and test Quickshell bar/OSD/switcher. Use when modifying QML files, debugging shape paths or rendering, testing IPC calls, or verifying visual changes after edits. Also use when adding new bar modules, popouts, dashboard tabs, or launcher features.
brainstorm-with-file
Interactive brainstorming with parallel subagent collaboration, idea expansion, and documented thought evolution. Parallel multi-perspective analysis for Codex.
team-tech-debt
Unified team skill for tech debt identification and cleanup. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team tech-debt", "tech debt cleanup", "技术债务".
decompile-f3dex
Use this skill if you need to decompile a function using F3Dex2. The presence of the Gfx type or gRegionAllocPtr are strongly indicative of an F3Dex2 function.
chad-yi-orchestrate
Use when: Orchestrating agents, managing Mission Control, making strategic decisions, or coordinating between multiple agents. Don't use when: An agent can handle the task directly, for routine execution work, or when a specific agent skill already exists. Outputs: Agent assignments, strategic decisions, escalated issue resolution.
custom-builtin-functions
Create a custom builtin function to be used in the Rego policy engine
ralph
Self-referential loop until task completion with architect verification