Use when documenting architecture, understanding system structure, creating diagrams, or analyzing component relationships. Focuses on interfaces and high-level design. Triggers on: 'use architecture mode', 'architecture', 'system design', 'how is this structured', 'document the system', 'create a diagram', 'high-level overview'. Read-only mode.
Collect and confirm the minimum required initialization info before starting any AHT run: project path, environment or conda env name, reference training launch script/method, and optimization target. Always send a user-facing confirmation request first, even when the values seem inferable from context, and wait for the user to confirm or update them before continuing.
Use when a Jumbo goal has been approved by QA review and needs architectural reconciliation before closing. Captures new learnings, updates stale entities, and ensures documentation reflects the work performed.
State-machine driven iterative planning and execution for complex coding tasks.
Convene a panel of CLI-based AI agents (Codex, Gemini) to deliberate on a question. Each agent answers independently, then you synthesize the council's verdict as chairman. Use for architecture decisions, code review, debugging hypotheses, or any question where diverse perspectives add value.
Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.
This skill should be used when the user asks to generate weekly reports from git history, process document links, update markdown files with URL descriptions, or mentions "生成周报", "处理文档链接", "更新 docs.md". Automates weekly report generation by extracting URLs from git commits or source files, generating concise Chinese descriptions, and organizing them into markdown tables.
When the user wants to track follower growth, understand what drives new followers, or analyze audience development. Also use when the user mentions 'follower growth,' 'followers,' 'audience growth,' 'gaining followers,' 'losing followers,' 'who follows me,' or 'grow my audience.' Uses BlackTwist follower data when available. For post-level metrics, see performance-analyzer-sms. For content patterns, see content-pattern-analyzer-sms.
A **rig** is a project-scoped collection of _riglets_ that provide knowledge and tools for AI agents.
Generate a draft VALIDATION.md for a skill by analyzing its SKILL.md construction steps
Reads production/traces/agent-metrics.jsonl and displays a per-agent performance summary table for the current or a specified session. Highlights agents with high error rates or OPEN circuit breaker state.
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
