发现 AI Agent 技能

Capture useful learnings from the current Codex session and propose concise updates to AGENTS.md files. Use near the end of a session, or when the user asks to revise AGENTS.md, capture project instructions, record missing context, update Codex project memory, or save recurring commands, workflows, gotchas, testing approaches, environment quirks, or codebase conventions discovered while working.

Audit and improve AGENTS.md files in repositories. Use when user asks to check, audit, update, improve, or fix AGENTS.md files. Scans for all AGENTS.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "AGENTS.md maintenance" or "Codex project instructions".

Guides day-to-day work in Tuist-generated Xcode workspaces, including generation, build and test commands, and buildable folders. Use when working in a Tuist-generated project or when users mention `tuist generate`, `xcodebuild test`, or generated workspaces.

Debugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it is a bug, misconfiguration, or something that needs team input. Use when users report generation failures, build errors after generation, or unexpected project behavior.

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.

Scan Apple's SwiftUI documentation for deprecated APIs and update the SwiftUI skill with modern replacements. Use when asked to "update latest APIs", "refresh deprecated SwiftUI APIs", "check for new SwiftUI deprecations", "scan for API changes", or after a new iOS/Xcode release. Requires the Sosumi MCP to be available.

Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration. Use when writing new Swift tests, modernizing XCTest suites, debugging flaky tests, or improving test quality and maintainability in Apple-platform or Swift server projects.

Diagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or concurrency-related compiler and linter warnings.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when implementing any feature or bugfix, before writing implementation code

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when executing implementation plans with independent tasks in the current session

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

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 it fits into the bigger picture.

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Compact the current conversation into a handoff document for another agent to pick up.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.

Draft repository-compliant GitHub pull requests with the `gh` CLI. Use when Codex needs to inspect the current repository's PR template and lint rules, derive a PR from local changes, find related issues or precedent PRs, and create or update a PR with labels discovered from GitHub.

Draft repository-compliant GitHub issues with the `gh` CLI. Use when Codex needs to inspect the current repository's issue templates and title rules, classify a request into the repository's supported issue types, and create or update an issue with labels discovered from GitHub.