Skip to main content

yonatangross/orchestkit

最近记录的来源活动
SkillsMP 收录数据更新
已收集 skills
156
GitHub 星标
300
GitHub Forks
40

用 AI 助手安装

复制这段 Prompt,发给你正在使用的 AI 助手。

正在加载仓库 README…

这个仓库中的 skills

已展示 40 / 156 个已收集 Skill。

职业分类
未分类
描述

Manually dispatched classifier for every open PR with a failed check: runs ci-debug headless, posts a collapsed verdict per PR. Proposes only, never pushes. Use for all red PRs; for one run, use ci-debug.

原文语言:英语

更新
职业分类
未分类
描述

Manually dispatched classifier for every open PR with a failed check: runs ci-debug headless, posts a collapsed verdict per PR. Proposes only, never pushes. Use for all red PRs; for one run, use ci-debug.

原文语言:英语

更新
职业分类
未分类
描述

Interactive wizard for OrchestKit settings: MCP servers, hook permissions, keybindings, presets. Use when customizing plugin behavior.

原文语言:英语

更新
职业分类
未分类
描述

Diagnoses OrchestKit and project health: manifests, hooks, skills, agents, MCP servers, CC version and permissions, with severity and remedies. Use to run doctor checks, diagnose issues or check project health before a release.

原文语言:英语

更新
职业分类
未分类
描述

Diagnoses OrchestKit and project health: manifests, hooks, skills, agents, MCP servers, CC version and permissions, with severity and remedies. Use to run doctor checks, diagnose issues or check project health before a release.

原文语言:英语

更新
职业分类
未分类
描述

Diagnoses one failing CI run or PR check against an 11-pattern playbook and proposes the exact fix, never applying it unasked. Use when a GitHub Actions job failed. Not for sweeping all red PRs (use ci-sentinel) or app test failures.

原文语言:英语

更新
职业分类
未分类
描述

Diagnoses one failing CI run or PR check against an 11-pattern playbook and proposes the exact fix, never applying it unasked. Use when a GitHub Actions job failed. Not for sweeping all red PRs (use ci-sentinel) or app test failures.

原文语言:英语

更新
职业分类
未分类
描述

Default front door for goal-shaped requests: classifies a plain-English goal and routes it to the right skill. Use for do this, figure out, I want, help me, fix, build, improve. Not for browsing skills (use help).

原文语言:英语

更新
职业分类
未分类
描述

Design ideation with parallel agents: 10+ ideas, feasibility filter, devil's-advocate scoring, trade-offs. Use when brainstorming or comparing alternatives. Not for building or fixing code (use implement or fix-issue) or scoring a design (use assess).

原文语言:英语

更新
职业分类
未分类
描述

Renders planned changes as before/after architecture, risk heat maps, execution order and dependency graphs in ASCII, HTML or NotebookLM. Use when reviewing a plan. Not for an inline chart (use glyph).

原文语言:英语

更新
职业分类
未分类
描述

Default front door for goal-shaped requests: classifies a plain-English goal and routes it to the right skill. Use for do this, figure out, I want, help me, fix, build, improve. Not for browsing skills (use help).

原文语言:英语

更新
职业分类
未分类
描述

Design ideation with parallel agents: 10+ ideas, feasibility filter, devil's-advocate scoring, trade-offs. Use when brainstorming or comparing alternatives. Not for building or fixing code (use implement or fix-issue) or scoring a design (use assess).

原文语言:英语

更新
职业分类
未分类
描述

Renders planned changes as before/after architecture, risk heat maps, execution order and dependency graphs in ASCII, HTML or NotebookLM. Use when reviewing a plan. Not for an inline chart (use glyph).

原文语言:英语

更新
职业分类
未分类
描述

Renders an answer as inline ASCII art with emojis, verdict first, one render per reply. Use for status, inventories, comparisons, rankings, pipelines or show-me-visually asks. Not for definitions. For a full plan playground, use visualize-plan.

原文语言:英语

更新
职业分类
未分类
描述

Serves a static HTML page at a stable https://NAME.localhost/ URL via portless, never a port, and stops it on request. Use when an agent made a page a person should open. Not for app dev servers (use dev).

原文语言:英语

更新
职业分类
未分类
描述

Distributed systems patterns for locking, resilience, idempotency, and rate limiting. Use when implementing distributed locks, circuit breakers, retry policies, idempotency keys, token bucket rate limiters, or fault tolerance patterns.

原文语言:英语

更新
职业分类
未分类
描述

Local OrchestKit usage analytics: agent and skill frequency, hook timing, session replay, cost estimates, model delegation trends. Use when reviewing usage, performance or costs.

原文语言:英语

更新
职业分类
未分类
描述

Multi-angle codebase exploration by parallel agents: structure, data flow, architecture, health. Use to map an unfamiliar repo. NOT for task research files (use create-research).

原文语言:英语

更新
职业分类
未分类
描述

Builds a new feature with parallel backend, frontend, test and security agents in worktrees, then verifies. Use when asked to build, add or scaffold a feature, endpoint or component. Not for fixing, reviewing or testing existing code.

原文语言:英语

更新
职业分类
未分类
描述

Onboarding wizard: scans the codebase and stack, recommends skills and MCP servers, scores readiness. Use when setting up OrchestKit in a project or rescanning after big changes.

原文语言:英语

更新
职业分类
未分类
描述

Multi-angle codebase exploration by parallel agents: structure, data flow, architecture, health. Use to map an unfamiliar repo. NOT for task research files (use create-research).

原文语言:英语

更新
职业分类
未分类
描述

Builds a new feature with parallel backend, frontend, test and security agents in worktrees, then verifies. Use when asked to build, add or scaffold a feature, endpoint or component. Not for fixing, reviewing or testing existing code.

原文语言:英语

更新
职业分类
未分类
描述

Onboarding wizard: scans the codebase and stack, recommends skills and MCP servers, scores readiness. Use when setting up OrchestKit in a project or rescanning after big changes.

原文语言:英语

更新
职业分类
未分类
描述

Seed configs for Vercel emulate: stateful GitHub, Vercel, Google, Slack, Stripe, AWS and more, not mocks. Use when setting up test environments, CI or offline development.

原文语言:英语

更新
职业分类
未分类
描述

Diff-aware browser testing: maps the git diff to affected pages, plans and runs targeted checks via agent-browser. Use when testing UI changes before merge. Not for writing tests (use cover), grading a suite (use verify) or unit tests.

原文语言:英语

更新
职业分类
未分类
描述

PR review by parallel agents (quality, security, tests, architecture, performance) with conventional comments and an approve or request-changes verdict. Use when a pull request needs a reviewer. Not for design scores (use assess).

原文语言:英语

更新
职业分类
未分类
描述

Grades work for merge: runs unit, integration and E2E suites plus security and type checks, scores 0-10 with a VERIFIED vs CLAIMED manifest. Use when deciding if work can ship. Not for adding missing tests (use cover).

原文语言:英语

更新
职业分类
未分类
描述

Diff-aware browser testing: maps the git diff to affected pages, plans and runs targeted checks via agent-browser. Use when testing UI changes before merge. Not for writing tests (use cover), grading a suite (use verify) or unit tests.

原文语言:英语

更新
职业分类
未分类
描述

PR review by parallel agents (quality, security, tests, architecture, performance) with conventional comments and an approve or request-changes verdict. Use when a pull request needs a reviewer. Not for design scores (use assess).

原文语言:英语

更新
职业分类
未分类
描述

Grades work for merge: runs unit, integration and E2E suites plus security and type checks, scores 0-10 with a VERIFIED vs CLAIMED manifest. Use when deciding if work can ship. Not for adding missing tests (use cover).

原文语言:英语

更新
职业分类
未分类
描述

Rates code, designs or approaches 0-10 across quality dimensions with pros, cons and fixes. Use when evaluating or comparing options. Not for fixing or building (use implement or fix-issue), PR review (use review-pr) or running tests (use verify).

原文语言:英语

更新
职业分类
未分类
描述

Rates code, designs or approaches 0-10 across quality dimensions with pros, cons and fixes. Use when evaluating or comparing options. Not for fixing or building (use implement or fix-issue), PR review (use review-pr) or running tests (use verify).

原文语言:英语

更新
职业分类
未分类
描述

Isolated eval and grading calls with claude -p in bare mode, free of plugin and hook interference. Use when grading skill outputs, benchmarking prompts or testing trigger accuracy.

原文语言:英语

更新
职业分类
未分类
描述

Documents how code works today for a task's questions, with file:line citations. Use before planning a change; describes, never proposes. NOT for mapping a repo (use explore).

原文语言:英语

更新
职业分类
未分类
描述

API wire contracts for REST and GraphQL: resource shape, versioning and deprecation, RFC 9457 errors, OpenAPI. Use when designing an endpoint contract. Not for runtime code (use python-backend).

原文语言:英语

更新
职业分类
未分类
描述

Nygard-format ADRs: context, decision, consequences, alternatives. Use when writing an ADR or recording an architectural decision.

原文语言:英语

更新
职业分类
未分类
描述

Clean and layered architecture patterns, project structure and test-standard validation. Use when designing system boundaries or enforcing structure. For tier sizing, use scope-appropriate-architecture.

原文语言:英语

更新
职业分类
未分类
描述

Audits sub-agent activation from telemetry: attempted, started, completed, unattributed spawns, and zero-start agents. Use when agents feel under-used or before pruning the catalog.

原文语言:英语

更新
职业分类
未分类
描述

Whole-codebase audit in one 1M-token pass: security, architecture and dependencies with severity-ranked findings. Use before a release or security review. Too big for one pass: use audit-full-mapreduce.

原文语言:英语

更新
职业分类
未分类
描述

Safety rules over the upstream agent-browser skill: scraping ethics, auth, request pacing, local URLs. Use for browser automation.

原文语言:英语

更新
已展示 40 / 156 个已收集 Skill。