zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Coding & development
41,039 results
orchistrate
Orchestrate sub-agents for large tasks: plan, delegate coding to cheap/fast models, parallelize the critical path, layer reviews, and close every loop without…
new-worktree
Creates and initializes a new Git worktree as a sibling directory with automated branching and naming rules based on the latest remote default branch. Use when…
api-contract
Generate the cross-repo API/event CONTRACT (OpenAPI) by reconciling the per-stack LLDs — the backend LLD (what it exposes) and the frontend LLD (what it…
architecture-review
Review the per-stack LLDs and the cross-repo contract AFTER design, before implementation — analyze architecture gaps, security, scaling, reliability, data…
backend-design
Author the backend low-level design (LLD) for a feature — read the relevant backend code to ground the design, then design how the feature slots in —…
backend-implement
Implement an approved backend scope against the cross-repo contract, test-first, meeting the backend engineering standards (security, backward compatibility,…
backend-review
Review the backend implementation AFTER it is built — security, contract adherence, correctness, backward compatibility, rate-limiting, performance/scaling,…
backend-tasks
Split an approved backend scope + contract into a small, ordered, test-first task list with a verification step per task and risk flags. Read-only planning —…
fix-loop
Fix failing deterministic checks with a bounded loop of at most 3 autonomous attempts, root-cause first, editing only files related to the failure, then…
human-review-pack
Assemble a concise, evidence-backed PR/release review pack before approval — what changed and why, impact, the verify proof, reviewer findings (fixed and…
code-review-team
After understanding the project context, review the code from an expert perspective, and after user approval, perform parallel improvement tasks with Agent Team SPAWN. Triggers: code review, code review, code review, review it, refactoring, code inspection, PR review, review changes.
nomnoml
Writes, edits, and renders nomnoml diagrams (text-to-UML) for architecture sketches, class diagrams, sequence-like flows, and relationship graphs. Use when…
ai-sdk
Answer AI SDK-related questions and assist with building AI features. Applies to: (1) asking about APIs such as generateText, streamText, ToolLoopAgent, tools; (2) building AI agents, chatbots, or text generation; (3) about AI providers (OpenAI, Anthropic, etc.), streaming, tool…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies. Supports React 18 + TypeScript +…
python-observability
Python observability — structlog, logging, OpenTelemetry, Prometheus, tracing. MUST consult when adding logging to Python code, implementing metrics/counters,…
type-expand
Expand TS aliases to shapes
issue-triage
Triage an incoming GitHub issue on leancodepl/patrol and produce a short, evidence-based recommendation — Patrol bug / User issue / Information needed /…
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding…
upgrade-plan
Plan a library or framework upgrade from the installed version to the latest. Finds what breaks, which local patches and workarounds can go, and what to adopt,…
start-implementation
Start an implementation session from an existing plan. Discovers available plans, checks environment setup, and invokes the technical-implementation skill.
start-review
Start a review session from an existing plan and implementation. Discovers available plans, validates implementation exists, and invokes the technical-review…
technical-review
Validate completed implementation against plan tasks and acceptance criteria. Use when: (1) Implementation is complete, (2) User wants validation before…
review-file
Deep review of one named file — structure and definition order, readability, security, comment quality, alignment with the external APIs it calls, project…