发现 Skills

This skill should be used when preparing releases, writing app store updates, or maintaining a CHANGELOG.md. It parses conventional commits and outputs polished release notes.

Schematic capture and wiring. Create schematic sheets, place symbols, add wires and net labels, organize hierarchical designs.

Use AFTER requirements are validated (design document exists) and BEFORE any implementation begins. Activates when user says "plan", "write a plan", "break this down", or when transitioning from brainstorm-deep. Also use when user says /bpe:plan.

Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table management, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP server integration for AI-assisted querying. Modern TypeScript/Bun implementation replacing the Python `bq` CLI with instant startup (~10ms vs ~500ms), automatic cost awareness with confirmation prompts, and native streaming support (JSONL). Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files) from Cloud Storage.

Feishu/Lark native OpenAPI exploration: discover native OpenAPI endpoints from the official documentation repository that are not wrapped by existing lark-* skills or the lark-cli. Use this when a user's needs cannot be met by existing lark-* skills or lark-cli registered commands and you need to find and call Feishu native OpenAPI directly.

Complete end-to-end process for publishing Unity games to Google Play and the iOS App Store. Covers platform limitations, asset optimization, signing configuration, review preparation, and release strategy. Use when: preparing to publish on Google Play or the App Store; dealing with oversized builds; configuring asset distribution; setting up signing certificates; publishing to TestFlight/internal testing; handling app review; configuring privacy policy.

In Codex interactive mode, call delegate_autopilot automatically for multi-step or cross-cutting requests (including research-only), otherwise work normally.

Use the Zustand devtools middleware for time-travel debugging and state inspection.

Multi-layer validation pattern - validates data at EVERY layer it passes through to make bugs structurally impossible, not just caught.

Initial setup sub-skill - handles template selection and context initialization for the 5-stage regulatory workflow. Supports any regulatory template (pre-defined or new) via official spec intake (URL/XSD/PDF).

Isolated workspace creation - creates git worktrees with smart directory selection and safety verification for parallel feature development.

Analyze Django Silk profiling data to debug slow requests, detect N+1 queries, and optimize database performance. Use when analyzing request IDs, investigating slow endpoints, or optimizing query performance.

Guide for extracting code or pseudocode from images using OCR and implementing it correctly. This skill should be used when tasks involve reading code, pseudocode, or algorithms from images (PNG, JPG, screenshots) and executing or implementing the extracted logic.

Guide for debugging and fixing bugs in the OCaml garbage collector runtime, particularly issues in memory management code such as sweeping, pool management, and run-length compression. Use this skill when you encounter segfaults during OCaml bootstrap, when debugging crashes in runtime/shared_heap.c or similar GC code, or when investigating pointer-arithmetic bugs in memory allocator implementations.

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.

Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.

Paper workflow: read papers and generate cards in one go. Accepts one or more arXiv links, paper URLs, PDFs, or paper titles. For each paper, runs ljg-paper (produces an org-format analysis) and then ljg-card -l (produces a long reading-card PNG). Use when the user says "paper flow", "read papers and make cards", "paper cards", or supplies multiple papers and wants both analysis and cards.

Skill map viewer. Scans all installed skills and renders a visual overview — name, version, description, category at a glance. Use when the user says 'skills', 'skill map', 'what skills do I have', 'show skills', 'list skills'. Also trigger when the user asks what skills are available or installed.

Build or refresh a team culture and produce a Team Culture Operating System Pack (culture snapshot, culture code, norms, rituals, rollout + measurement plan). Use for team culture, culture code, team values, team norms, psychological safety, and coaching culture. Category: Hiring & Teams.

Travel photo and outfit suggestions. Use this when a user wants to know what photo styles suit a destination, what clothes to wear, and how to take flattering pictures.

Comprehensive Cloudflare cost trap reference with pricing, TRAP IDs, and remediation patterns. Load when reviewing code for cost safety or investigating billing anomalies.

CLI best practices for LlamaFarm. Covers Cobra, Bubbletea, and Lipgloss patterns for Go CLI development.

Act as a Socratic teacher to guide users in learning concepts or tasks step-by-step without doing the work for them. Use when user says "teach me", "I want to learn", "guide me through", "help me understand", or "don't do it for me".

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.