Minimalistic, project-agnostic skills and rules for AI coding agents
Skill Claude CodeCodex
Make a project ready for AI agentic engineering by converging it toward a canonical agent-neutral structure — a lean AGENTS.md index with progressive disclosure, shared skills and gitignore hygiene. Re-runnable, and doubles as an audit.
Skill Claude CodeCodex
Check how much of a ticket is already implemented — split it into requirement blocks, judge each against the code, and save a human-readable TICKET-STATUS report in the planning dir.
Skill Claude CodeCodex
Draft, rewrite, or refine a doc for maximum token economy without losing any rule or intent. Use for docs kept in version control and regularly re-read by agents; skip throwaway docs like plans.
Skill Claude CodeCodex
Author or refine a skill for maximum token economy without losing intent. Use when creating any new skill or editing an existing SKILL.md.
Skill Claude CodeCodex
Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens.
Skill Claude CodeCodex
Turn a refined requirements document into a structured implementation PLAN.md a fresh session can execute. Planning only — decides the "how", not the "what". Invoke manually only.
Skill Claude CodeCodex
Turn a ticket or requirements document into a concise QA manual-test file a non-author can follow. Invoke manually only.
Skill Claude CodeCodex
Fetch all reviewer comments from a pull request URL (GitHub, Azure DevOps, …) and save them as a self-contained markdown PR-REVIEW file in the task's planning directory. Fetch only — no fixing or replying.
Skill Claude CodeCodex
Fetch one or more tickets/issues from their tracker (Azure DevOps, Jira, GitHub, …) and save each as a self-contained markdown ticket file. Fetch only — no analysis or planning.
Skill Claude CodeCodex
Fresh-eyes review of a changeset by a fresh-context agent — catches regressions and correctness issues the authoring context reads past.
Skill Claude CodeCodex
Use when handing finished work over to code review — writing a PR description or packaging a change for review by a human, an agent, or both.
Skill Claude CodeCodex
Review someone else's pull request as the maintainer deciding whether it merges — every prior comment walked, every claim verified, and nothing posted without your go-ahead.
Skill Claude CodeCodex
Audit the current project's agent-memory and, block by block, relocate each entry into a user-controlled home (project doc/skill/rule or user-level skill/rule) or archive it — draining memory so nothing uncontrolled accumulates in the agent's context.
Skill Claude CodeCodex
Triage a fetched PR review with the user, comment by comment, drafting each reply and producing a REQUIREMENTS file for the accepted code changes. Takes the PR-REVIEW file produced by fetch-pr-review. Invoke manually only.
Skill Claude CodeCodex
Refine a development ticket — or brainstorm a raw idea — into a validated, self-contained REQUIREMENTS document — the "what", verified against the codebase. Invoke manually only.
Skill Claude CodeCodex
Assist a human reviewing a pull request or branch locally — diff a source branch against its target (auto-detected or from a PR link) and return concise, human-voice review comments with file and line locations. Read-only, never posts.
Skill Claude CodeCodex
Triage a ticket or ticket set before work starts — compare it against the codebase and save a review covering verdict, feature walkthrough, and only the high-cost questions worth raising.
Skill Claude CodeCodex
Run nx format, lint, test, and build on affected or specified projects, then fix unambiguous failures.
Skill Claude CodeCodex
Capture durable user feedback into the governing skill/doc, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill/doc covers or should cover, and when manually…
Skill Claude CodeCodex
Self-review a changeset until merge-ready — a fresh-context reviewer checks it as a maintainer would, the author answers every finding, and a compact report for the PR proves the review happened.
Skill Claude CodeCodex
Voice rules for text published under a person's name and read as if a person typed it, such as chat replies, PR comments and descriptions, commit messages, review replies, and code comments. Defines the wording only, never the content.
Skill Claude CodeCodex
Verify the engineer is ready to implement a feature — a teach-back conversation over a .TICKET-REVIEW.md where they explain the feature in their own words and the agent probes and corrects.