tomzx/agents

tomzx/agents

Skill Claude CodeCodex needs its repo

Summarize weekly Slack activity, colleague activity, action items, and thanks for the week.

tomzx/agents

Skill Claude CodeCodex

Summarizes the week from Slack, colleagues, action items, and thanks, then runs the end-of-week review. Use when the user says /end-week, end of week, weekly summary, or Friday wrap-up.

tomzx/agents

Skill Claude Code

Identify copy-pasted code blocks and near-duplicate logic that should be extracted into shared helpers or modules, ranked by duplication size and churn.

tomzx/agents

Skill Claude Code

Scan the codebase for functions and modules with high cyclomatic complexity, excessive length, or deep nesting, then produce prioritized refactoring suggestions.

tomzx/agents

Skill Claude Code

Identify files and modules with missing or insufficient test coverage, ranked by churn and complexity, and suggest what to test first.

tomzx/agents

Skill Claude Code

Find unused functions, classes, variables, exports, feature flags, and config keys across the codebase and produce a prioritized removal list.

tomzx/agents

Skill Claude Code

Find public APIs, modules, CLI entry points, and configuration options that lack documentation, ranked by usage and visibility, and suggest what to document first.

tomzx/agents

Skill Claude Code

Identify functions, methods, and modules missing type annotations in gradually-typed languages (Python, TypeScript, JavaScript), ranked by public visibility and churn.

tomzx/agents

Skill Claude Code

Orchestrate a bug fix from issue to PR by delegating to reproduce-issue, create-implementation, validate-implementation, and create-pr.

tomzx/agents

Skill Claude CodeCodex

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is…

tomzx/agents

Skill Claude CodeCodex

Use ghx as an extended GitHub CLI. It browses issues and pull requests with local disk caching, and performs PR/issue comment operations the standard gh CLI does not support: inline PR review comments, line-range comments, thread replies, pending reviews, local comment stashes, and edit/delete of comments. Trigger…

tomzx/agents

Skill Claude CodeCodex

Generate a git commit message based on the staged changes in the repository.

tomzx/agents

Skill Claude CodeCodex

Generate a git commit message based on the changes in the repository.

tomzx/agents

Skill Claude CodeCodex

Resolves agents commit SHA and GitHub URL for a skill's SKILL.md, and formats footers for comments or issue bodies posted via gh. Use whenever a skill posts to GitHub (PR comments, issue comments, issue create, review comments) so readers see which skill and which repo revision produced the content. Other skills…

tomzx/agents

Skill Claude Code

Reply to a comment on a GitHub issue using the codebase, issue description, and comment history as context.

tomzx/agents

Skill Claude Code

As a PR reviewer, verify that the author's new commits actually address your review comments, resolve fixed threads, reply on partial or unaddressed ones, and evaluate author rebuttals. The reviewer-side counterpart of handle-pr-reviewer-feedback.

tomzx/agents

Skill Claude Code

Diagnose failing CI checks on a GitHub pull request, fix the root cause, push, and confirm CI passes.

tomzx/agents

Skill Claude Code

Reply to a comment on a GitHub pull request, implementing changes if appropriate, using the codebase and comment history as context.

tomzx/agents

Skill Claude Code

Address reviewer comments on your own GitHub pull request, implementing valid feedback or explaining rejections, then push changes. The author-side counterpart of handle-pr-author-feedback.

tomzx/agents

Skill Claude Code

Analyze the existing software surface and surrounding signals (code, issues, recent PRs, goals, roadmap) to generate and rank new feature opportunities that would add value. The bottom-up discovery counterpart to create-roadmap and create-goals, and the inverse of create-needs-assessment (which validates a given idea…

tomzx/agents

Skill Claude CodeCodex

Identify workflows the user performs that are not yet encoded as skills in the agents repository, and prompt to create or backlog them. Drives a self-reinforcing improvement loop.

tomzx/agents

Skill Claude CodeCodex

Reflect on the current session and identify what would have been needed to run it fully autonomously end to end, producing a concrete readiness assessment and a prioritized gap list. Use when the user asks /improve-autonomy, "what would it take to run this autonomously?", or wants to assess autonomy readiness.

tomzx/agents

Skill Claude Code

Make a bounded set of safe, verified improvements to a codebase each run (remove dead code, add missing types, auto-fix lint, drop unused deps, patch dependencies). Designed to run weekly as a routine. Use when the user says /improve-codebase, "improve the codebase", "weekly cleanup", "tend the repo", or wants…

tomzx/agents

Skill Claude Code

Inspect a single skill in the library, reason about high-value low-risk improvements, and apply them directly. Used by the Skill Refresher workflow and invocable directly as /improve-skill .