Skill Claude CodeCodex
Create a GitHub Pull Request from the current branch, following conventional commit format and pre-filling the repo's PR template. Activates on "create a PR", "open a pull request", "push this for review", or similar. Use after commits are made and pushed is not yet done; for the commits themselves use git-commit, for…
Skill Claude CodeCodex
Create semantic version releases with automated changelog generation from conventional commits, version file bumps (package.json, pyproject.toml, Cargo.toml, etc.), git tagging, and GitHub release publishing, for repos on a simple main-branch workflow (no release/hotfix branches). Use when users want to create a…
Skill Claude CodeCodex
Syncs the current feature branch with its base or upstream branch via merge (default) or rebase, with conflict detection and stash handling. Use for ad-hoc requests like "sync my branch with main", "rebase onto main", "rebase on latest dev", "pull upstream into my fork", or "update my branch". Not for release/hotfix…
Skill Claude CodeCodex
Manage a gitflow branching workflow, starting and finishing feature, release, and hotfix branches; cutting versioned releases with changelog generation; coordinating emergency hotfixes directly to production; and keeping long-lived branches in sync. Activates when users mention gitflow, feature/release/hotfix…
Skill Claude CodeCodex
Finds the three ways translations silently rot: a key added to the default locale but never copied to the others (missing), a key copied but never translated (still reads identical to the source), and a key left behind in one locale after being renamed or removed from the default (orphan). Also catches new UI copy…
Skill Claude CodeCodex
Implements a new feature end-to-end as a senior staff engineer would, discovers project conventions, researches current best practices, drafts a plan for approval, then builds it (with parallel subagents where available) reusing existing code, skipping speculative abstractions, and verifying with tests before…
Skill Claude CodeCodex
Improve one or more EXISTING agent skills to the current authoring standard, with measured before/after evidence instead of a trust-me rewrite. Snapshots the current version to an immutable baseline, rewrites description/body/references against the rubric, authors or upgrades evals/evals.json and trigger-eval.json in…
Skill Claude CodeCodex
Inject compressed framework-specific best practices and docs into CLAUDE.md or AGENTS.md so AI coding agents get passive framework knowledge without extra tool calls. Supports Next.js (via Vercel's agents-md codemod, version-aware) and FastAPI (via a bundled best-practices template). Use when a user wants to add…
Skill Claude CodeCodex
Run raw ankitpokhrel/jira-cli commands directly against Jira Cloud or on-prem, issue/epic/sprint CRUD, JQL-style filtering, and scripting/CI automation (bulk assign, auto-label, sprint add). Invoke explicitly via /jira-cli, or when the user wants literal jira CLI syntax, a filter the curated skills don't expose, or a…
Skill Claude CodeCodex
Generate a standup report from recent Jira activity and git history, completed tickets, in-progress work, blockers, and commit correlation. Use when the user wants to prepare for a daily standup, asks "what did I do yesterday", or wants a Jira/git activity summary in brief, slack, or manager format. Use jira-todo…
Skill Claude CodeCodex
Generates a prioritized daily work plan from a user's assigned Jira tickets, scoring by priority, due date, blockers, and recent activity, then recommending what to work on next. Use when the user asks "what should I work on today", wants to plan their workday, prioritize assigned tickets, or triage their Jira…
Skill Claude CodeCodex
Generates and edits images by calling Google's Nano Banana / Gemini image generation API (requires a GEMINIAPIKEY), a real, billed API call. This skill is explicit-invocation only: use it only when the user names it or the Gemini path directly ("nanobanana", "nano banana", "gemini image generation", "GEMINIAPIKEY"…
Skill Claude CodeCodex
Turn any task into a model-tiered multi-agent plan, decompose it into subtasks, classify each as research, implementation, planning, or synthesis, map every subtask to the right subagent and model (haiku for research/exploration, opus for planning, sonnet for everything else), then run independent tracks in parallel…
Skill Claude CodeCodex
Takes a private side project from "done" to a public GitHub launch, pre-flight checks (confirm the repo is still private, scan for leaked secrets, verify a license exists), applies review-code findings, generates brand art (logo/hero via codex-imagegen), rewrites the README and repo description for discoverability…
Skill Claude CodeCodex
Turn an approved PRD into tracked issues, one per requirement, with the dependencies between them recorded. Trigger on "file issues for this PRD", "turn this spec into tickets", "break this PRD into work", or an automated hand-off after a PRD is approved. Creates issues in beads or GitHub and reports what it created…
Skill Claude CodeCodex
Authors the design specification for an approved PRD (information architecture, user flows, a screen inventory, and per-screen state and interaction specs), reusing the project's existing component library first and tracing every screen back to a PRD requirement ID. Lean by default: one design-spec.md, full specs for…
Skill Claude CodeCodex
Authors a durable design-token contract: a W3C DTCG 2025.10 JSON file ($value/$type, {group.token.path} aliases) as the canonical source, adopting the project's existing design system first and enforcing WCAG 2.2 AA contrast (never meaning by colour alone). An optional Google-Labs DESIGN.md alpha layer is…
Skill Claude CodeCodex
Gate-checked, size-and-intent-tiered PRD authoring. Runs a gate-zero first (is a written doc even needed, or is a 3-line ticket or a prototype enough?), then a Brief, one-pager, or big-tier stack; the big tier branches on intent: a PR/FAQ for validation versus a numbered full PRD for execution. Enforces positive…
Skill Claude CodeCodex
Break a large or ambiguous project into a dependency-ordered task list with a Mermaid dependency diagram and critical-path analysis, using the Task tool suite (TaskCreate/TaskUpdate/TaskList). Trigger on "plan this project", "break this into tasks", "what's the dependency order", "create a task breakdown", or "map out…
Skill Claude CodeCodex
Restructures existing code without changing its behavior: maps callers and test coverage, adds characterization tests where coverage is thin, then applies the change in small steps verified against the full test suite after each one. Use when the user wants to refactor, extract a method or class, simplify logic…
Skill Claude CodeCodex
Turn a plan, PRD, review, audit, comparison, brainstorm, explanation or architecture map into an interactive HTML page the user marks up in place, then read their marks back and act on them. Every section carries an anchored comment affordance, so feedback returns bound to the exact thing it was left on. Use for…
Skill Claude CodeCodex
Runs a comprehensive multi-agent code review of a PR, commit, or the whole codebase across six dimensions (correctness, performance, code style, test coverage, error handling, and simplicity/over-engineering) and returns a severity-ranked report with file:line findings and fix suggestions. Use when the user wants a…
Skill Claude CodeCodex
Audit project dependencies for vulnerabilities, license compliance risks, and staleness by running native audit tools (npm audit, pip-audit, cargo audit, etc.), querying Dependabot alerts, and dispatching parallel agents for CVE analysis, license risk, and upgrade complexity. Use when the user wants to check for…
Skill Claude CodeCodex
Performs a comprehensive UX/UI/design quality audit of a live URL or a static codebase, mapped to authoritative standards (WCAG 2.2 AA, Material Design 3, Apple HIG, Nielsen Norman Group, Refactoring UI, Laws of UX). Use when a user wants to review design quality, audit UX/UI, or check visual hierarchy, typography…