julien777z

Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.

Review a GitHub pull request with parallel specialized agents and post inline review comments rated by severity. Reviews the PR's changed lines and caps minor nitpicks; does not fix anything. Use when asked to review a PR or run /code-review.

Review a GitHub pull request with parallel specialized agents and post inline review comments rated by severity. Reviews the PR's changed lines and caps minor nitpicks; does not fix anything. Use when asked to review a PR or run /code-review.

Strictly review the branch's changes for reuse, simplification, abstraction quality, and maintainability, then fix the issues. An ambitious code-quality pass that hunts for structural simplifications (code-judo moves), giant files, and spaghetti-condition growth.

Run a large-scale, whole-repository refactor — code simplification, slop and code-smell removal, de-duplication, and cross-module consistency — with behavior preserved and uncertain changes escalated to the user. Use when asked to refactor the codebase, clean up at scale, or consolidate duplicated logic.

Run a large-scale, whole-repository refactor — code simplification, slop and code-smell removal, de-duplication, and cross-module consistency — with behavior preserved and uncertain changes escalated to the user. Use when asked to refactor the codebase, clean up at scale, or consolidate duplicated logic.

Common Python anti-patterns to avoid. Use as a checklist when reviewing code, before finalizing implementations, or when debugging issues that might stem from known bad practices.

Python background job patterns including task queues, workers, and event-driven architecture. Use when implementing async task processing, job queues, long-running operations, or decoupling work from request/response cycles.

Code review a pull request or the current working changes with independent reviewer lenses, validated findings, and severity-rated results. Establishes a branch and a draft pull request when none exists yet. Accepts an effort level, an optional fix mode that applies the smallest complete correction for each confirmed finding, and an optional comment mode that posts inline review comments, each written with or without a leading double dash. Asks for whichever of effort or modes the invocation did not state. Reports in chat and never posts or fixes unless the matching mode is requested. Use when asked to review a PR, review current changes, or run /code-review.

Coordinate one authorized task across a bounded collection of local repositories while preserving unrelated work. Use when a task spans repositories to apply a scoped change, run the same review or validation, or collect and merge information into one result.

Propagate explicitly requested skills, rules, and their changes across the user's other local repositories, creating missing applicable copies while preserving repository-specific guidance. Use when the user invokes /propagate-skill or $propagate-skill alongside a skill or rule creation or update request.

Upsert `.agents` source-of-truth files for agents, skills, or rules based on user input.

Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.

Find and watch a GitHub pull request for review findings, investigate each finding, fix and push legitimate issues, and stop once checks are green and review threads are resolved. Use when asked to watch, monitor, poll, babysit, or keep checking a PR for review comments or automated review feedback.

List the pull request URLs for every relevant pull request created or updated during the entire current session. Use when the user invokes /link-prs or $link-prs, or asks for links to pull requests created or updated during the session.

List the repository web URLs for every repository changed during the entire current session. Use when the user invokes /link-repo or $link-repo, or asks for links to all repositories touched, modified, committed, pushed, or otherwise changed during the session.

Run code-simplify once across the whole selected pull-request target, then run code-review repeatedly, investigate and fix every legitimate functional finding, validate and push the fixes, and stop only after two consecutive rounds with no functional findings (or a third when the second also makes simplifications). Any functional finding resets that stabilization sequence. Use when asked to review-and-fix, keep reviewing until clean, or run a code review loop.

Review the complete pull-request diff for the current branch with high-signal review lenses and severity-rated findings. When that diff is empty, review commits this Codex session created or pushed instead. Establish or update the branch and draft PR when needed, report findings in chat by default, never post GitHub review comments directly, and never fix findings. Use when asked to review a PR, review current changes, or run /code-review.

List the pull request URLs for every pull request changed during the entire current session. Use when the user invokes /link-pr or $link-pr, or asks for links to all pull requests opened, updated, reviewed, merged, closed, or otherwise changed during the session.

List the names of rules in the canonical .agents rules folder. Use when the user asks to list available repository rules.

List the names of skills in the canonical .agents skills folder. Use when the user asks to list available repository skills.

CI-runner adaptation of the code-review skill. Applies code-review's lenses and severity rubric to a pull request inside a CI job, where the runner handles PR discovery, posting, and thread resolution and findings stream out as JSONL. Use when a CI runner drives the review.

Strictly review the branch's changes for reuse, simplification, abstraction quality, and maintainability, then fix the issues. An ambitious code-quality pass that hunts for structural simplifications (code-judo moves), giant files, and spaghetti-condition growth.