Instructions file CodexOpenCode
Instructions for fiveonecode/agent-skills: This repository is a direct package of 51Code-owned skills. Each top-level skill directory contains a SKILL.md; the front matter is the source of truth for its name and description.
Skill Claude CodeCodex
Review pull requests, commits, or diffs for high-signal engineering issues and merge risk. Use when asked to review code, audit a patch, find bugs, or provide merge readiness feedback. Focus on defects introduced by the proposed changes (correctness, security, performance, reliability, and maintainability) and report…
Skill Claude CodeCodex
Use Google Gemini through a managed Files API wrapper for multimodal local files, configurable generation parameters, structured JSON output, optional Gemini tools, and reproducible authentication setup.
Skill Claude CodeCodex
Build and improve agent-first engineering harnesses where AI agents perform most implementation work and humans steer architecture, constraints, and review. Use when defining or upgrading AGENTS.md rules, repository conventions, task decomposition, CI guardrails, merge strategy, quality gates, or cleanup loops to…
Skill Claude CodeCodex
Fail-fast visual verification for in-app hint overlays, coach marks, and spotlight callouts. Use when screenshots must prove target highlighting, background suppression, pointer geometry, safe-area containment, readable copy, and light/dark parity; not for generic screenshot review or App Store marketing composites.
Skill Claude CodeCodex
Use for repositories that already use or explicitly evaluate XcodeGen: maintain project.yml/project.yaml as source of truth, diagnose generated projects, configure resources and test hosts, manage SwiftPM state, and verify binary packaging without replacing general Xcode build guidance.
Skill Claude CodeCodex
Audit and design lifecycle side-effect correctness for async UI, purchase, analytics, retry, cancellation, presentation, and session flows. Use when reviewing SwiftUI or other UI lifecycle code, paywalls, subscription or purchase flows, analytics emission, async tasks, retries, reloads, sheet dismissal, remount…
Skill Claude CodeCodex
Select and run the right local LLM engine (MLX with speculative decoding vs llama.cpp) with the right settings for a task, and enforce the one-engine-at-a-time memory rule. Use whenever a task runs local inference against an OpenAI-compatible endpoint — evals, summarization, code review, content generation — or when…
Skill Claude CodeCodex
Audit whether a spec, task, harness, agent workflow, safety boundary, or operational contract is actually enforced by concrete mechanisms. Use when reviewing or changing AGENTS.md, CLAUDE.md, .agents/manifests, .agents/verify, .agents/evals, spec/agents, build/test specs, task plans, risk/execution contracts…
Skill Claude CodeCodex
Transcribe long local meeting audio into a validated rough transcript with bounded chunking, repetition and output-limit detection, targeted retries, optional stronger-model rescue, and auditable token usage. Use when a user provides an audio recording or asks for reliable multilingual meeting transcription.
Skill Claude CodeCodex
Check a Git repository's current candidate for high-confidence credential, private-key, and machine-home leaks, then perform a bounded public-release review. Use before publishing source or opening a public PR; do not use it to claim complete history or workflow-execution safety.
Skill Claude CodeCodex
Set up, audit, or diagnose iOS background (silent) notifications end to end: signed entitlements, APNs registration and environment, provider headers and payload, throttling, Simulator and device testing, and Apple delivery diagnostics. Use for content-available pushes or missing background delivery; not for visible…
Skill Claude CodeCodex
Create, update, review, and improve technical specification documents so they are complete, testable, and implementation-ready. Use when defining new features/systems/APIs, updating existing specs, restructuring documents, auditing missing requirements, or converting vague plans into concrete, verifiable requirements…
Skill Claude CodeCodex
Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing, including @Test, #expect, #require, async tests, XCTest migration, traits, confirmations, exit tests, and Swift 6.2+ testing features.
Skill Claude CodeCodex
Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage. Use when cleaning up a SwiftUI view, splitting long bodies, removing inline actions or side effects, reducing computed some…
Skill Claude CodeCodex
Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS simulators, managing devices, compiling Swift code, running UI tests, or automating iOS app interactions with a native Xcode/macOS CLI baseline.
Skill Claude CodeCodex
Configure or troubleshoot Xcode Cloud workflows and lifecycle scripts using Apple's project-presence, dependency, environment, and fail-closed CI contracts. Use for Xcode Cloud setup, custom ciscripts, build/test/archive diagnosis, or a separately reviewed XcodeGen regeneration exception.