onboard
Read or update the project context summary, used for handover, taking over a project, or switching AI tools. Use retrofit to establish a keel baseline.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-17 00:07
41,448 results
Read or update the project context summary, used for handover, taking over a project, or switching AI tools. Use retrofit to establish a keel baseline.
Establish a keel baseline for an existing project, or migrate legacy keel documents. Use codebase-insight for read-only code inventory; use onboard to understand project context.
Create or update the keel technical design: architecture, interfaces, data models, and change impact. Use requirements for requirement definition; use ui-orchestrator for visual design.
Creates or repairs browser mini-games specifically using crisp-game-lib. Use only when the user explicitly asks for crisp-game-lib or the existing project…
Translates game design prose into engine-neutral implementation invariants and validation checks. Use when implementing or reviewing game mechanics where idle,…
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Complete Apple developer toolkit: documentation search, WWDC videos (2014-2025), App Store Connect management (TestFlight, builds, signing, analytics,…
38 battle-tested iOS development rules covering accessibility, navigation, architecture, dark mode, localization, App Review guidelines, and more. Targets the…
Guide for installing, configuring, and using PyTorch with Intel XPU (GPU) support. Use this skill whenever the user mentions: PyTorch with Intel GPU, XPU,…
Review the entire Ably CLI codebase against the standards and conventions defined in the ably-new-command skill. Use this skill whenever asked to audit,…
Scaffold new CLI commands with tests for the Ably CLI (oclif + TypeScript). Use this skill whenever creating a new command, adding a subcommand, migrating a…
Review the current branch's changes against the standards and conventions defined in the ably-new-command skill. Use this skill whenever asked to review…
Apply the Aboudjem/solidity-style-guide rules to Solidity code — review, rewrite, or audit for naming, layout, formatting, NatSpec, custom errors, ERC-7201…
TypeScript implementation workflow for GraphOS world projects. Use after graph-world closes the graph design loop, then bootstrap npm/TypeScript, implement…
Use this skill whenever working in a JavaScript or TypeScript project that uses Bun: bun.lock, bunfig.toml, packageManager set to bun, bun scripts, Bun APIs,…
Describes efficient usage of Bun and Bun APIs instead of Node.js (and its APIs)
Apply accepted application-subtraction findings with isolated phases and snapshot-bound build/test gates.
Coordinate complete AI development work across code, tests, project knowledge and artifacts. TRIGGER WHEN: running project-lifecycle assess, repair, change,…
Restructure tangled code into a clear equivalent, preserving behavior. TRIGGER WHEN: the user asks for "readable", "maintainable" or "clean" code, a review…
Canonical readability-only plan, transformation, candidate validation and owned recovery.
Unified review engine for code-review, team-review and pr-review, including signal-selected stack specialists.
Prepare the existing code, team or PR review inputs without writing another detection prompt.
Two-stage code review combining fast pattern detection (Semgrep) with AI-powered semantic analysis (CodeRabbit)
Use when a Codex session should recall, write, seed, inspect, or delete curated Oracle-backed memory through the oracle-codex-memory MCP sidecar.