发现 Skills

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) "Cannot access 'X' before initialization" at runtime, (2) import returns undefined unexpectedly, (3) "ReferenceError: Cannot access X before initialization", (4) Type errors that disappear when you change import order, (5) Jest/Vitest tests fail with undefined imports that work in browser.

Maximizing Claude Code capabilities and efficiency. Use when helping users discover features, optimize workflows, or improve their Claude Code experience.

You MUST use this before any code edit: creating features, fixing bugs, building components, adding functionality, refactoring, or modifying behaviour. Routes the design step to standard, guided, committee, or skip mode based on a single user choice, then hands off to the chosen mode skill.

Analyzes the current session to extract patterns, preferences, and learnings. Produces a structured review capturing what worked and what to improve. Use for session retrospectives, debriefs, post-mortems, or when reflecting on insights worth remembering.

Content creation and optimization: copywriting, copy editing, social media, launch announcements, email sequences, and AI-writing cleanup. Covers the full content lifecycle from first draft to polished, on-brand output. Use when writing, editing, or publishing any marketing or product content.

Investigate host stability incidents (memory/process pressure), triage likely culprits, and drive safe recovery and hardening for multi-workspace Pi operations.

Modern Python development with uv, ruff, mypy, and pytest. Use when: - Writing or reviewing Python code - Setting up Python projects or pyproject.toml - Choosing dependency management (uv, poetry, pip) - Configuring linting, formatting, or type checking - Organizing Python packages Keywords: Python, pyproject.toml, uv, ruff, mypy, pytest, type hints, virtual environment, lockfile, package structure

WHEN: Rust project review, ownership/borrowing, error handling, unsafe code, performance WHAT: Ownership patterns + Lifetime analysis + Error handling (Result/Option) + Unsafe audit + Idiomatic Rust WHEN NOT: Rust API → rust-api-reviewer, Go → go-reviewer

Diagnose features into the right LLM component type: Skill, Agent, or Command wrapper. USE WHEN: - "should this be a skill?" - "command or agent?" - "what type should this be" - "skill vs command" - "diagnose this feature" - structure/architecture decisions for LLM components DO NOT USE WHEN: - Actually implementing (use the generated spec instead) - General coding tasks unrelated to structure design

Create, ingest into, and query a Pinecone full-text-search (FTS) index using the preview API (2026-01.alpha, public preview). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct score_by clauses (text / query_string / dense_vector / sparse_vector), or compose with text-match filters ($match_phrase / $match_all / $match_any). Ships `scripts/ingest.py` for safe bulk ingestion (batch_upsert + error inspection + readiness polling); query construction is documented inline in this skill — write `documents.search(...)` calls directly, validated against `pc.preview.indexes.describe(...)` output.

Design and execute insect population surveys covering survey design, sampling methods, field execution, specimen identification, diversity index calculation including Shannon-Wiener and Simpson indices, statistical analysis, and reporting. Covers defining survey objectives, selecting study sites, determining sampling intensity and replication, choosing sampling methods appropriate to target taxa, standardizing collection effort, recording environmental covariates, identifying specimens to the lowest practical taxonomic level, calculating species richness, Shannon-Wiener diversity (H'), Simpson diversity (1-D), evenness, rarefaction curves, multivariate ordination, and producing survey reports with species lists and conservation implications. Use when conducting baseline biodiversity assessments, monitoring insect populations over time, comparing insect communities across habitats or treatments, assessing environmental impact, or supporting conservation planning with quantitative ecological data.

Analyze prime numbers using primality tests, factorization algorithms, prime distribution analysis, and sieve methods. Covers trial division, Miller-Rabin, Sieve of Eratosthenes, and the Prime Number Theorem. Use when determining whether an integer is prime or composite, finding prime factorizations, counting or listing primes up to a bound, or investigating prime properties within a number-theoretic proof or computation.

Design and execute insect population surveys covering survey design, sampling methods, field execution, specimen identification, diversity index calculation including Shannon-Wiener and Simpson indices, statistical analysis, and reporting. Covers defining survey objectives, selecting study sites, determining sampling intensity and replication, choosing sampling methods appropriate to target taxa, standardizing collection effort, recording environmental covariates, identifying specimens to the lowest practical taxonomic level, calculating species richness, Shannon-Wiener diversity (H'), Simpson diversity (1-D), evenness, rarefaction curves, multivariate ordination, and producing survey reports with species lists and conservation implications. Use when conducting baseline biodiversity assessments, monitoring insect populations over time, comparing insect communities across habitats or treatments, assessing environmental impact, or supporting conservation planning with quantitative ecological data.

Find bugs, logic errors, race conditions, and edge cases in code. Use when investigating issues, reviewing complex logic, checking async code, or looking for potential runtime errors.

Expert guidance for Plang programming language (plang.is). Use when the user asks about Plang syntax, wants to generate Plang code, needs help debugging Plang goals, wants to understand Plang patterns, or is working on Plang projects. Plang is a natural language pseudo-code language with goal-based architecture using SQLite databases.

Embedded C code style assistant based on code conventions from 8051 microcontroller teaching projects. Defaults to snake_case naming, with optional camelCase. Used to create project structures that follow embedded development conventions, optimize code style, and provide hardware driver templates. Suitable for 8051, STM32, and other embedded C project development.

Fuzzing framework LibAFL for custom fuzzing campaigns.

Narya Hatchery

This skill should be used when the user asks to "create a sample", "add a new sample", "make a Dev Proxy sample", "start a new sample", "scaffold a sample", or needs to create a new Dev Proxy sample with proper structure, config files, metadata, and README.

Two-mode plugin: CHECKER audits designs across seven categories (purpose, typography, proportions, composition, visual hierarchy, color, SEO); APPLIER guides six-phase creation from foundation through technical implementation.

GLSL shader development: ray marching, fluid simulation, particle systems, and procedural generation. Official MiniMax skill for creating real-time visual effects in WebGL and creative coding contexts.

Build or review WinUI 3 applications with the Windows App SDK, including MVVM patterns, packaging decisions, navigation, theming, windowing, and interop boundaries with other .NET stacks. Use when building modern Windows-native desktop UI.

Code review, refactoring, and quality improvement. Use when reviewing code, eliminating code smells, reducing technical debt, refactoring methods, running self-critique loops, or improving maintainability and readability.

Comprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors, assertions, waits, fixtures, and test organization.