Full build pipeline: takes a PRD, breaks it into tasks, implements them in parallel, and reviews the result. Orchestrates prd-task-planner → parallel-task-orchestrator → code-reviewer.
Cybernetics-based multi-agent orchestration for complex tasks. Coordinates a Planner → Generator → Evaluator → Retro pipeline with clean-context sub-agents, per-checkpoint drift prevention, and persistent retro learning.
Create and manage Claude Code sessions via the Cogpit (agent-window) HTTP API running on localhost:19384. Use when an agent needs to spawn a new Claude Code session in a project directory, send messages to existing sessions, stop sessions, list projects, or query active sessions. Triggers on requests like "start a session", "run claude in project X", "send a message to session Y", "list cogpit projects", or any programmatic interaction with the agent-window server.
Personal AI tutor — generates learning paths, sends daily tasks via Telegram, evaluates progress, and adapts to the learner.
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.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Use when writing, reviewing, or validating Claude Code plugin artifacts — check frontmatter schemas, hook event names, naming conventions, prompt structure, or reference syntax. Loaded by the NLPM scorer and checker agents for schema validation.
Design system component workflow. Spec, document, implement, review, spec-review, and audit DS components with Figma as primary input. 6 actions: spec, doc, dev, review, spec-review, audit.
Save a URL with an auto-generated summary to the knowledge base
Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.
Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.
Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)
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:
