Run Codex's native code-review on the current branch, working tree, or a specific commit. Use when the user invokes /hyperclaude:hyper-code-review, or after producing code changes and you want a Codex critique. Distinct from /hyperclaude:hyper-plan-review (which critiques plans, not code).
EnglishApply systematic debugging discipline when a test fails, code throws, or behavior diverges from expectation. Use the moment something is unexpectedly broken. Skip for "I know what's wrong" one-line fixes; this skill is for when the cause is not immediately obvious.
EnglishRun Codex accuracy review on documentation. Use when the user invokes /hyperclaude:hyper-docs-review or after the documenter agent edits docs. Distinct from /hyperclaude:hyper-code-review (which critiques code diffs) and /hyperclaude:hyper-plan-review (which critiques plans). Scope is strict: accuracy, drift, completeness, broken links, cross-doc inconsistencies — NOT prose or style.
EnglishSync documentation to reflect recent code changes. Use when the user invokes /hyperclaude:hyper-docs-sync or after implementing changes that affect documented behavior (API surface, schemas, CLI flags, architecture). Reads code-to-doc mapping from CLAUDE.md/AGENTS.md, identifies affected docs, dispatches the documenter agent once per affected doc.
EnglishExecute a plan task-by-task using fresh subagents, with spec compliance + code quality reviews between tasks. Use when the user invokes /hyperclaude:hyper-implement, or when about to start a multi-task implementation from a plan in .hyperclaude/plans/. Skip for single-step trivia or fast prototyping.
EnglishGenerate an ordered, bite-sized plan via the planner agent and save it to .hyperclaude/plans/. Use when the user invokes /hyperclaude:hyper-plan, or when about to start a non-trivial implementation that needs a plan for /hyperclaude:hyper-plan-review to critique and /hyperclaude:hyper-implement to execute. Skip for one-step tasks (dispatch the implementer agent directly).
EnglishRun Codex critique on an implementation plan. Use when the user invokes /hyperclaude:hyper-plan-review, after Claude has produced a plan that should be sanity-checked before execution.
EnglishRun Codex pre-implementation research on a task. Use when the user invokes /hyperclaude:hyper-research, or when starting a non-trivial implementation and you want Codex's prior-art / pitfalls / recommendations before designing.
EnglishApply test-driven development discipline when implementing code changes. Use when about to write or modify behavior-bearing code (functions, modules, business logic). Skip for pure config changes, documentation edits, or one-shot scripts where tests would not outlive the change.
English
AGENT SKILLS ATLASIncludes Hyper Code Review, Hyper Debug, Hyper Docs Review, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Hyper Code Review
Run Codex's native code-review on the current branch, working tree, or a specific commit. Use when the user invokes /hyperclaude:hyper-code-review, or after producing code changes and you want a Codex critique. Distinct from /hyperclaude:hyper-plan-review (which critiques plans, not code).
Hyper Debug
Apply systematic debugging discipline when a test fails, code throws, or behavior diverges from expectation. Use the moment something is unexpectedly broken. Skip for "I know what's wrong" one-line fixes; this skill is for when the cause is not immediately obvious.
Hyper Docs Review
Run Codex accuracy review on documentation. Use when the user invokes /hyperclaude:hyper-docs-review or after the documenter agent edits docs. Distinct from /hyperclaude:hyper-code-review (which critiques code diffs) and /hyperclaude:hyper-plan-review (which critiques plans). Scope is strict: accuracy, drift, completeness, broken links, cross-doc inconsistencies — NOT prose or style.
Hyper Docs Sync
Sync documentation to reflect recent code changes. Use when the user invokes /hyperclaude:hyper-docs-sync or after implementing changes that affect documented behavior (API surface, schemas, CLI flags, architecture). Reads code-to-doc mapping from CLAUDE.md/AGENTS.md, identifies affected docs, dispatches the documenter agent once per affected doc.
Hyper Implement
Execute a plan task-by-task using fresh subagents, with spec compliance + code quality reviews between tasks. Use when the user invokes /hyperclaude:hyper-implement, or when about to start a multi-task implementation from a plan in .hyperclaude/plans/. Skip for single-step trivia or fast prototyping.
Hyper Plan
Generate an ordered, bite-sized plan via the planner agent and save it to .hyperclaude/plans/. Use when the user invokes /hyperclaude:hyper-plan, or when about to start a non-trivial implementation that needs a plan for /hyperclaude:hyper-plan-review to critique and /hyperclaude:hyper-implement to execute. Skip for one-step tasks (dispatch the implementer agent directly).
Hyper Plan Review
Run Codex critique on an implementation plan. Use when the user invokes /hyperclaude:hyper-plan-review, after Claude has produced a plan that should be sanity-checked before execution.
Hyper Research
Run Codex pre-implementation research on a task. Use when the user invokes /hyperclaude:hyper-research, or when starting a non-trivial implementation and you want Codex's prior-art / pitfalls / recommendations before designing.
Hyper TDD
Apply test-driven development discipline when implementing code changes. Use when about to write or modify behavior-bearing code (functions, modules, business logic). Skip for pure config changes, documentation edits, or one-shot scripts where tests would not outlive the change.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Hyper Code Review skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.