5.9K skills · sorted by relevance
Review code changes or a repository for actionable bugs by tracing how components interact. Findings explain reachable triggers, incorrect behavior, consequences, and checked counterarguments. Correctness is the default focus; performance and security can also be selected.
Use past local Codex sessions to propose updates to a selected skill and project memory file. Recurring tasks are replayed, changes are checked on separate validation tasks, and proposals are staged for review before adoption.
Review Verdaccio code changes for security, package manager compatibility, performance, and maintainability. Verify concerns against surrounding code and relevant tests, then report actionable issues with their location, trigger, impact, and supporting evidence.
Reviews research ideas, papers, and experimental results through repeated critical discussion. Identifies unsupported claims, missing experiments, and weaknesses in the paper’s story, then records agreed conclusions, evidence requirements, and prioritized improvements in a review document.
Get critical feedback from Claude on research ideas, papers, and experimental results. Through multiple review rounds, identify unsupported claims, missing experiments, and narrative weaknesses, then document agreed conclusions and a prioritized improvement plan.
Review a specified code change without editing files. Checks the full diff, surrounding code, tests, and callers to identify actionable defects introduced by the change, then reports findings by severity with file and line references.
Support academic work from refining a research question to literature reviews, manuscript drafting, citation checks, and revision. Select workflows for the current stage, including study selection against eligibility criteria, peer review, and experiment planning.
Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.
Organizes a code review by giving a reviewer subagent the requirements, a change summary, and the relevant Git commits. It helps check completed work and handle findings by severity before continuing or merging.
Review assigned code changes against project conventions, architecture, and intended behavior. Verify findings with source code and tests, classify their severity, and record a merge readiness verdict, with an optional deeper process for independent reviews and resolving disagreements.
Reviews code changes for security risks using Git history, caller counts, and test coverage. Produces a Markdown report with evidence, potential attack scenarios, affected code, and clear limits on what was reviewed.
Audit Claude Code instruction rules against actual project files to find broken settings, overly broad scopes, and loading issues. Review each rule’s usefulness with the user, then apply confirmed changes or produce an audit report.
Audit a collection of agent skills for valid settings, clear activation conditions, complete workflows, and required files. Get scores for each target platform, prioritized fixes, and a separate record of whether activation was actually tested.
Review completed code through three roles: a critical reviewer, a verifier, and an adjudicator. Check evidence, look for bugs introduced by fixes, and produce an actionable repair list with regression tests and traceable review reports.
Evaluate code review feedback against the actual code, supported environments, and existing behavior. Clarify uncertain requests, respond with technical evidence, and implement valid changes one at a time with tests for each fix.
Request a focused code review after implementation or before merging. Give a separate reviewer agent the requirements, change summary, and commit range, then address findings according to their severity before continuing.
Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT Pro OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'.
The English summary is being prepared. Showing the original description.
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.
The English summary is being prepared. Showing the original description.
Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".
The English summary is being prepared. Showing the original description.
Run a comprehensive code review on local source files. Use this skill when the user asks to review, audit, inspect, evaluate, or check code, even if they never use the word "review." Does not post comments to GitHub pull requests — use post-code-review-to-pr for that. Does not analyze architectural structure or module boundaries — use architectural-analysis for that. Does not explain code or a PR to build understanding before reviewing — use code-overview for a written overview, or code-walkthrough to be paced through it one step at a time. Does not map bounded contexts or domain boundaries — use ddd-analysis for that. Does not capture feedback on Han's own skills — use han-feedback for that.
The English summary is being prepared. Showing the original description.
Produces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user), and from there what it does, how it flows, and where to start — so you can get up to speed before working on or reviewing it. Use when you want to understand, get oriented in, make sense of, explain, or get up to speed on a chunk of code, a file, a directory, a symbol, or a PR's changes. Writes the overview to a scratch file and changes no code. Does not review code quality or raise findings — use code-review for auditing changes or post-code-review-to-pr for posting them. Does not produce durable feature or system documentation — use project-documentation. Does not assess architecture or structural risk — use architectural-analysis. Does not diagnose bugs or root-cause failures — use investigate. Does not pace a person through the code one step at a time in conversation — use code-walkthrough.
The English summary is being prepared. Showing the original description.
CodeRabbit reviews pull requests with AI on GitHub, GitLab, Azure DevOps and Bitbucket, and reviews local changes from a CLI before they are pushed. Use when a user asks to set up automated PR reviews, write or validate a .coderabbit.yaml, add path-specific review instructions, control a review with @coderabbitai commands, or run coderabbit review from the terminal or a coding agent.
The English summary is being prepared. Showing the original description.
Expert in the human side of code review. Covers giving feedback that lands, receiving criticism gracefully, navigating disagreements, and building a healthy review culture. Understands that code review is as much about relationships as it is about code quality. Use when "code review, PR feedback, review comments, how to give feedback, harsh review, review culture, constructive criticism, " mentioned.
The English summary is being prepared. Showing the original description.
Run the Codex Optimized Development, Evaluation, and Remediation (CODER) Loop with an orchestration-only coordinator, non-overlapping task-family owners, fresh independent reviewers, evidence-scoped remediation, and final coordinator acceptance. Discover and compose optional MSW, Timebox, MSL, and Codex Voice Optimizer companions as the Slopware Dev Stack without making them dependencies. Use in Codex when the user invokes the CODER Loop, asks to divide a complex change into bounded implementation families with independent reviewers, requests multi-agent implementation without overlapping ownership, requires review and repair until every blocking gap is independently rechecked, asks for the CODER tutorial or Slopware Dev Stack, or wants CODER to install or use its companions. Do not trigger for an ordinary single-agent change, a review-only request, or a non-Codex host.
The English summary is being prepared. Showing the original description.