发现 Skills

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria: methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing and manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

Dan Koe's HUMAN 3.0 framework - a comprehensive map for reaching your highest potential across all life domains. TRIGGERS: - When user feels stuck or plateaued in life - When user is successful in one area but failing in others - When user asks about personal development or self-actualization - When user wants a comprehensive life framework - When user asks about balancing career, health, relationships, and meaning - When user mentions feeling "off" despite external success CAPABILITIES: - Assess current developmental level across all quadrants - Identify imbalanced lifestyle archetypes - Guide through the phase system (Dissonance → Uncertainty → Discovery) - Apply the Anti-Vision protocol for clarity - Diagnose false transformation patterns - Design quadrant-specific development protocols

In-depth reference for how OpenCode works — the AI agent framework that powers this environment. Covers: agents (definition, loading, modes, model assignment), skills (discovery, loading, structure), tools (built-in + custom, permissions), commands (slash commands, frontmatter, routing), sessions (lifecycle, prompting, subagents), config (opencode.jsonc, providers, MCP servers, plugins), and the full REST/SSE API. Load this skill when you need to understand OpenCode internals, debug agent/tool/skill issues, extend the framework, create custom tools, or work with the session API.

Orchestrate lawyer agents to review code for compliance with codebase laws. Spawns counsel in parallel to produce a unified legal brief.

Analyzes CSV files and generates comprehensive summary statistics and visualizations using Python and pandas - automatically and immediately without asking what the user wants.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Cash flow analysis and treasury management workflow covering liquidity assessment, cash forecasting, working capital optimization, and treasury operations.

This skill provides guidance for Raman spectrum peak fitting tasks. It should be used when analyzing spectroscopic data, fitting Lorentzian or Gaussian peaks to Raman spectra, or working with graphene/carbon material characterization. The skill emphasizes critical data parsing verification, physical constraints from domain knowledge, and systematic debugging of curve fitting problems.

A Liu Run–style business column writing skill. Based on Liu Run’s 28 years of business writing experience and the distilled complete creation framework from “My 28 Years of Writing Principles”. Supports 3 structures (3-paragraph, 10-point, 32-item), SCQA logical momentum (ASC/CSA/QSCA), the 5-business-school SCA++ template, 8 major writing principles (empathy, sense of audience, a leader’s willingness to get hands dirty, logical momentum, the 5 business schools, 3 structure types, single-focus clarity, precision in wording with vernier-caliper accuracy), 7 special content blocks, and 12 quality checks. Use cases: create business commentary, business methodology, case breakdowns, hot-topic responses, entrepreneur interviews, visit/travel notes and other long-form/business-column pieces. Triggered when the user says “write a business commentary”, “write in Liu Run’s style”, “give me a 32-item piece”, “write a 10-point piece”, or “do an ASC”. Even if the user asks “help me write a business insight article”, “write a methodology”, or “write an entrepreneur interview”, it will trigger as long as it involves long-form business writing. Do not trigger when the user only requests short pieces such as “help me write a social post” or “explain concept XX”.

NVIDIA Omniverse platform integration and real-time 3D workflows

Path-specific CLAUDE.md rules with YAML frontmatter globs, plan mode vs direct execution decision framework, and iterative refinement patterns. Maps to CCA Domain 3.

Use when building FastAPI applications, implementing async endpoints, setting up Pydantic schemas, working with SQLAlchemy, or writing pytest tests for Python backend services.

Systematic pre-publication manuscript audit producing a structured refactoring report with section-level diagnostics, citation hygiene analysis, and submission-readiness assessment. Use this skill whenever the user uploads a manuscript, paper, thesis chapter, journal submission, or conference paper and asks for review, feedback, editing, refactoring, pre-submission check, proofreading, or quality audit. Also trigger when the user says "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "manuscript review", "refactor my paper", or asks about citation consistency, argument coherence, or formatting compliance. Covers partial requests like "check my references" or "does the abstract work" — the full diagnostic surfaces issues across all facets even when only one was asked about.

A skill that should be invoked whenever a user wants to build a Dashboard or simple app. This skill is Phase 2 of an e2e process that covers the actual build and testing. For Phase 1 (requirements, layout design, visualization selection), use the dashboard-design skill.

Generate research questions from economic phenomena

Enterprise-grade compliance architecture for SOC 2, HIPAA, GDPR, PCI-DSS. Provides compliance checklists, security controls, audit guidance, and regulatory requirements for serverless and cloud architectures. Activates for compliance, HIPAA, SOC2, SOC 2, GDPR, PCI-DSS, PCI DSS, regulatory, healthcare data, payment card, data protection, audit, security standards, regulated industry, BAA, business associate agreement, DPIA, data protection impact assessment.

Expert knowledge for Azure Container Storage development including troubleshooting, decision making, limits & quotas, security, and configuration. Use when building, debugging, or optimizing Azure Container Storage applications. Not for Azure Blob Storage (use azure-blob-storage), Azure Files (use azure-files), Azure Elastic SAN (use azure-elastic-san), Azure NetApp Files (use azure-netapp-files).

Spawn and manage multiple Codex CLI agents via tmux to work on tasks in parallel. Use whenever a task can be decomposed into independent subtasks (e.g. batch triage, parallel fixes, multi-file refactors). When codex and tmux are available, prefer this over the built-in Task tool for parallelism.

Translate and sync bilingual documentation.

Dispatch to the right problem-solving technique based on how you're stuck

Generate a deterministic, CycloneDX-aligned AI BOM from point-in-time AI asset inventory snapshots. Supports normalized multi-cloud inventory documents plus provider-shaped snapshots for AWS SageMaker and Bedrock, Google Vertex AI, and Azure Machine Learning. Use when the user mentions AI BOM, model inventory, AI asset discovery, evidence collection for AI systems, PCI / SOC 2 technical evidence, or wants a portable bill of materials for models, endpoints, datasets, vector stores, runtimes, and guardrails. Do NOT use on raw cloud audit logs or OCSF findings — this skill expects asset inventory, not events. Do NOT use as a live monitor or to claim compliance by itself — it produces a point-in-time inventory artifact and never mutates cloud state.

Performs static analysis of Windows PE (Portable Executable) malware samples using PEStudio to examine file headers, imports, strings, resources, and indicators without executing the binary. Identifies suspicious characteristics including packing, anti-analysis techniques, and malicious imports. Activates for requests involving static malware analysis, PE file inspection, Windows executable analysis, or pre-execution malware triage.

Capture learnings after tasks. Triggers on task completion, repeated mistakes, retrospective requests, or "what did I learn".