Debugging
Find and fix bugs, error analysis
docs-writing-protocol
by z-soulx
文档写入协议（去躁点版）。控制 AI 何时写入文档、写入什么内容。当用户说"沉淀到文件"、"记录下来"、"update: xxx.md" 时使用。
prd-maintenance
by z-soulx
PRD 渐进式维护协议。多供应商并行开发 + 敏捷迭代场景下维护 PRD 文档。当用户说"prd: path"、"维护 PRD"、"更新需求文档"时使用。依赖 docs-writing-protocol 的去躁点判定。
gc-review-security
by dougkeefe
"Use when reviewing code changes for Protected B security compliance. Triggers: security review, ITSG-33 compliance, GoC security, Protected B data handling, access control review, PII protection check, or requests to audit security-sensitive code."
notebook-debugger
by dangeles
Use when encountering Jupyter notebook errors including kernel crashes, environment conflicts, import errors, memory issues, or data pipeline failures in notebooks
visual-feedback-loop
by vladmdgolam
"AI agent visual feedback loop for any web app. Use when iterating on visual code (UI, canvas, 3D, SVG, charts, animations) and you need to SEE the rendered result to evaluate quality. Covers: dev-screenshot API pattern (GET trigger → SSE → client capture → POST back → file saved), parameterized rendering, metadata sidecars, visual regression with pixel diff, WebMCP tool registration, and console fallbacks. Activate on: 'take a screenshot', 'show me the render', 'visual QA', 'compare before/after', 'pixel diff', or any iterative visual work where the agent needs to inspect rendered output."
cfd-mathematician
by dangeles
Use when invoked by cfd-bioreactor orchestrator to provide rigorous mathematical analysis of FEM variational formulations, function space selection, stability conditions (inf-sup, Lax-Milgram), convergence rate estimation, and dimensionless number analysis for bioreactor CFD simulations. Produces mathematical specifications that the orchestrator translates into FEniCSx code.
literature-gap-finder
by Data-Wise
Method×Setting matrices and systematic gap identification
cfd-bioreactor
by dangeles
Use when user needs to simulate fluid flow through bioprocess cartridges, bioreactor geometries, or membrane devices using FEniCSx. Covers Navier-Stokes flow, O2 species transport with Michaelis-Menten kinetics, membrane permeation, mesh generation from CAD geometry, and interactive 3D visualization.
support-systems
by JK-0001
Build and scale customer support for a solopreneur business. Use when setting up support channels, writing help docs, reducing support volume, improving response times, or automating common questions. Covers support channel selection, help center setup, SLA targets, automation strategies, and self-service systems. Trigger on "customer support", "help desk", "support system", "reduce support tickets", "support automation", "help documentation", "customer service".
proof-architect
by Data-Wise
Structured methodology for constructing and verifying mathematical proofs in statistical research
cfd-reviewer
by dangeles
Use when invoked by cfd-bioreactor orchestrator to provide adversarial engineering review of CFD simulation plans and generated code. Challenges mesh quality, boundary conditions, solver parameters, stabilization choices, and physical plausibility. Produces severity-rated review with approval status.
qt-compatibility-build
by re2zero
Use when maintaining Debian packages that need Qt5/Qt6 dual support, CMakeLists.txt has hard-coded Qt5/Qt6 or DTK5/DTK6 versions, or projects need dynamic library linking based on detected Qt version for deepin V25/V20 compatibility
sre-expert
by personamanagmentlayer
Expert-level site reliability engineering, SLOs, incident management, and operational excellence
software-developer
by dangeles
Use when implementing production-quality bioinformatics software with proper error handling, logging, testing, and documentation, following software engineering best practices.
qt-translation-assistant
by re2zero
Use when user requests translating Qt project localization files (TS files), automating translation workflows, or setting up multilingual support for Qt applications. This skill uses parallel processing with ThreadPoolExecutor to translate TS (Translation Source) files efficiently.
systematic-troubleshooter
by dangeles
Use when encountering errors, bugs, unexpected behavior, or any problem requiring systematic debugging with extended thinking for complex multi-layer issues
git-commit-workflow
by re2zero
Expertise in structured Git commit workflow with Chinese team conventions. Use
project-memory
by SpillwaveSolutions
Set up and maintain a structured project memory system in docs/project_notes/ that tracks bugs with solutions, architectural decisions, key project facts, and work history. Use this skill when asked to "set up project memory", "track our decisions", "log a bug fix", "update project memory", or "initialize memory system". Configures both CLAUDE.md and AGENTS.md to maintain memory awareness across different AI coding tools.
ui-design
by JayZeeDesign
Use this to design a nice UI in single html as inspiration & UI exploration.
arkts-syntax-assistant
by SummerKaze
ArkTS syntax, migration, and optimization guide for HarmonyOS/OpenHarmony development. Triggers on: .ets files, ArkTS keywords, HarmonyOS/OpenHarmony context, @ohos packages. Help with syntax reference, TypeScript migration, performance optimization, compile errors, state management, component development, and language-specific questions.
tdd-strict
by Svenja-dev
Erzwingt striktes Test-Driven Development mit Red-Green-Refactor Zyklus. Blockiert Code-Generierung ohne vorherige Tests. Dokumentiert 13 ungueltige Rationalisierungen. Aktivieren bei neuen Features, Bug Fixes, Refactoring.
Behavior Testing Skill
by Svenja-dev
Siehe: Website/Relaunch 2026 01/components/tests/MultilingualChat.behavior.test.tsx (API-Contract + State-Persistence Muster)
strict-typescript-mode
by Svenja-dev
Enforces TypeScript best practices when writing code. Automatically enables strict typing for TypeScript projects, prevents any usage, and recommends generic constraints. Activate on TS/TSX files, new features, code reviews.
multi-llm-advisor
by Svenja-dev
Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.