Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
Typst document creation and package development. Use when: (1) Working with .typ files, (2) User mentions typst, typst.toml, or typst-cli, (3) Creating or using Typst packages, (4) Developing document templates, (5) Converting Markdown/LaTeX to Typst
Deploy the opentraces.ai marketing site to Vercel production. Use when the user says "deploy site", "deploy to vercel", "push site", "ship the site", or "deploy-site". For a full coordinated release that includes a version bump and package publish alongside the site deploy, use /release-pack instead. --- # Deploy Site Deploy the Next.js marketing site (`web/site/`) to Vercel production. ## Context - **Project**: `opentraces` on Vercel (jayfareis-projects/opentraces) - **Framework**: Next.js 16 (App Router) - **Root directory**: Vercel is configured with root at `web/site/` - **Domain**: opentraces.ai - **Build**: `next build` (runs from `web/site/`) - **Version**: Auto-read from `src/opentraces/__init__.py` at build time via `next.config.ts` ## Steps ### 1. Verify build locally ```bash cd web/site && npm run build ``` If the build fails, fix issues before deploying. ### 2. Commit and push Ensure all changes are committed and pushed to `main`: ```bash git status git push origin main ``` ### 3. Deploy to Vercel Run the deploy from the **repo root** (not `web/site/`), because Vercel resolves the root directory from its project settings: ```bash cd /path/to/repo/root npx vercel --prod ``` ### 4. Verify Check the deployment URL in the Vercel output. The production URL is: ```
- Read
The universal tool adapter for AI agents. Search, install, and run packages from the anyclaw registry. Use anyclaw to access web APIs, data pipelines, CLI tools, and scripts as unified commands.
Consult Snowflake CREATE AGGREGATION POLICY parameter reference before generating any CREATE AGGREGATION POLICY DDL.
Use when interacting with Jira issues - searching, creating, updating, moving, transitioning, commenting, logging work, downloading attachments, managing sprints, boards, issue links, web links, fields, or users. Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are unavailable for Jira Server/DC.
Creates detailed reports from data when the user asks for report generation or data summaries.
从飞书文档或本地 Markdown 提炼文章主题与风格，调用 OpenRouter 的 Nano Banana / Gemini Flash Image 生成 2.35:1 的微信公众号封面图，并可选上传为微信封面素材。
Build resilient, type-safe HTTP integrations with trembita using Result-based error handling, retries, and circuit breaker patterns. --- # Trembita Skill Use this repository as a practical reference for agents implementing HTTP clients with `trembita`. ## When to Use - Build TypeScript integrations for third-party REST APIs. - Add robust error handling without exception-driven control flow. - Implement retries, circuit breakers, and timeouts with minimal dependencies. - Write testable API code by injecting `fetchImpl`. ## Core Patterns 1. Initialize once with `createTrembita()` and handle init `Result`. 2. Use `client.request()` for parsed JSON body responses. 3. Use `client.client()` when you need HTTP metadata (`statusCode`, `body`). 4. Narrow failures by checking `result.error.kind`. 5. Add resilience via `createRetryingFetch` and `circuitBreaker` config. ## Canonical References - `README.md` - quick overview and install. - `QUICK_START.md` - shortest path to first success. - `LEARNING_GUIDE.md` - concepts and progressive examples. - `EXAMPLES.md` - production-style patterns. - `ARCHITECTURE.md` - request/error flow diagrams. ## Agent Guardrails - Prefer `Result` handling over `try/catch` for request outcomes. - Keep endpoint configuration explicit and validated. - Prefer `expectedCodes` to document acceptable HTTP outcomes. - Use `client.client()` for 404/202 branching by status code. - Inject `fetchImpl` in tests; avoid global fetch patching.
Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollection, or says “用 Agently 做/用 agently 做”). Deliver runnable code plus regression tests validating schema/ensure_keys and streaming (delta/instant/streaming_parse), with optional tools (Search/Browse/MCP), TriggerFlow orchestration, KB (ChromaDB), and serviceization (SSE/WS/HTTP). Do not use for generic streaming/testing questions that are not about Agently, or for prompt-only writing without tests/structure.
Record browser & local-file actions once; replay runs without the LLM—save $ vs AI browsing, faster, no hallucinations. github.com/laziobird/openclaw-rpa
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:
