mgiovani

@mgiovani source repo

55 skills
0 followers
10 hours ago last updated

▌
Gh Agent Screenshot · mgiovani
Use when asked to attach a screenshot or image to a GitHub issue or PR — uploads files inline via the Git Data API, works in private repos with a token only (no browser session). Triggers on "attach a screenshot to a GitHub issue/PR", "upload an image to a GitHub comment", "embed an image inline in a private GitHub repo", or "post a screenshot to a PR/issue".

0
installs
▌
Wtf · mgiovani
Re-explain your own previous message in plain, simplified English (ASD-STE100 style), when the user did not understand it. Use when the user replies with "wtf", "what?", "I don't get it", "explain that again simpler", "ELI5", or "in plain English". Rewrites what was already said; it does not do new work, new research, or new code.

0
installs
▌
Ship · mgiovani bundle
Orchestrates the current branch from "code done" to "merged": runs the review-code skill, then any project-specific pre-merge checks it detects (visual regression like `just visual-diff`, tests, lint), then a conventional commit per git-commit, a PR per git-create-pr, and optionally watches CI and merges on green. Use when the user says "ship it", "ship this", "ship train", "get this merged", or wants the whole review-to-merge pipeline in one go. Reuses the sibling skills and stops on the first red gate (failing review, failing check, red CI). Owns "ship it" for the default case: a feature branch merging straight to its base. Not for a single step in isolation (use review-code, git-commit, or git-create-pr directly). Not for release/hotfix branch topology, versioning, or promoting dev to main, use gitflow for that, including "ship it" said in a repo that runs gitflow.

0
installs
▌
Render · mgiovani bundle
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 "render this as a page", "make this visual", "I want to review this properly", "turn this plan into something I can comment on", or to wrap another skill's output (`render /review-code`). Not for generating a Mermaid diagram into docs/ (use docs-diagram), not for designing a UI for a product being built (use product-design-spec), and not for simplifying prose the user did not understand (use wtf).

0
installs
▌
Fix Bug · mgiovani bundle
Fixes a bug through test-driven debugging, reproduces it with a failing test, locates the root cause with evidence (file:line), then applies the smallest fix that resolves it without refactoring unrelated code. Use when the user wants to fix a bug, debug an issue, resolve an error, or investigate a failing test. Not for building new functionality (use implement-feature) or restructuring working code with no bug involved (use refactor).

0
installs
▌
Gitflow · mgiovani bundle
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 branches, cutting a release, branching strategy, promoting an integration branch to production, tagging a version, or rolling back a live release. Also reaches for it when the user says "promote dev to main" or "we need to hotfix prod" without naming gitflow. Not for a single commit message (use git-commit). Not for versioned releases on a simple main-branch workflow with no release/hotfix branches (use git-release). Not for the mechanical review-to-merge pipeline on a branch with no release/hotfix topology involved (use ship). Skip for general git mechanics (merge conflicts, interactive rebase, git education) or CI-failure debugging unrelated to a release.

0
installs
▌
CI Local · mgiovani bundle
Run the checks a GitHub Actions workflow would run, locally, when Actions is unavailable or out of quota. Parses .github/workflows/*.yml, extracts the jobs/steps that gate merges (lint, typecheck, test, build), translates them to local commands respecting the workflow's pinned node/python versions and env, executes them sequentially, and reports a parity table of what passed locally vs. what can't be replicated (service containers, secrets, matrix dimensions) and why. Activates on "CI quota", "Actions is down/unavailable", "run CI locally", "verify like CI would", "run the pipeline on my machine", or a pre-push request to check a branch the way CI checks it. Not for generating a new workflow file (use ci-generate), not for debugging why a specific CI run failed on GitHub (use fix-bug or review-code), and not for the release/hotfix gating process itself (use gitflow), this skill only produces the local stand-in when the real thing isn't reachable.

0
installs
▌
Docs Adr · mgiovani bundle
Create a numbered Architecture Decision Record (ADR) documenting a technical decision with context, alternatives, and consequences. Trigger on "create an ADR", "document this architectural decision", "record why we chose X", or "write an ADR for [decision]". Not for a decision still open for discussion (use docs-rfc, RFCs propose, ADRs record) and not for bootstrapping a project's whole docs/ tree from scratch (use docs-init).

0
installs
▌
Docs Rfc · mgiovani bundle
Create a numbered RFC (Request For Comments) document proposing a change and opening it for team discussion, using minimal/standard/detailed templates. Trigger on "write an RFC", "draft a proposal for X", "document this change before we build it", or "get feedback on this design". Not for recording a decision that's already made (use docs-adr), RFCs propose and stay open for discussion, ADRs record a choice that happened.

0
installs
▌
Gh Daily · mgiovani bundle
Generate a GitHub-based standup report from assigned issues, open/merged PRs, review requests, and git commit history. Use when the user asks for a standup, daily update, or status report and works with GitHub Issues/PRs. Trigger phrases include "standup report", "daily update", "what did I do yesterday", "GitHub status report". Not for Jira-based standups (use jira-daily), gh-daily is GitHub-only and never queries Jira.

0
installs
▌
Git Sync · mgiovani bundle
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 branch promotion or cutting versioned releases, use gitflow or git-release for those.

0
installs
▌
Jira CLI · mgiovani bundle
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 bash/CI script that drives jira-cli. Manual-invocation skill, does not auto-fire on general mentions of "jira" or "ticket". Not for a ready-made standup summary correlated with git commits (use jira-daily). Not for a prioritized "what should I work on" plan (use jira-todo).

0
installs
▌
Refactor · mgiovani bundle
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, reduce duplication, improve naming, restructure modules, or pay down technical debt in code that already works. Not for adding new functionality (use implement-feature) or fixing broken behavior (use fix-bug).

0
installs
▌
Docs Init · mgiovani bundle
Bootstraps a documentation structure (architecture, onboarding, data-model, deployment, security, contributing, and a first ADR) for a project that has little or no docs/ directory, exploring the codebase and populating templates only with content evidenced in the code. Use when the user wants to set up docs, bootstrap documentation, initialize project docs, scaffold a docs/ folder, or create docs from scratch for a new or undocumented project. Not for refreshing or syncing docs that already exist (use docs-update). Not for generating a standalone architecture or ER diagram without the surrounding document (use docs-diagram).

0
installs
▌
Env Setup · mgiovani bundle
Scans a codebase for environment variable usage to generate or sync .env.example, validate .env completeness against what the code actually reads, and detect leaked secrets in .env or git history. Use for "/env-setup", "update .env.example", "sync .env.example with the codebase", "check if .env has everything it needs", "is .env in .gitignore", or "scan for leaked secrets in .env". Not a full security audit (use review-security for OWASP-level scanning) and not a generic secret-rotation or CI-secrets-injection tool.

0
installs
▌
Jira Todo · mgiovani bundle
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 backlog. Not for yesterday's standup recap (use jira-daily) or raw command reference (use jira-cli), this skill is specifically for forward-looking prioritization, not status reporting.

0
installs
▌
Vrt Check · mgiovani bundle
Runs the project's visual regression testing (VRT) workflow, detects whatever tooling the repo actually uses (justfile/Makefile/package.json targets like visual-diff or visual-update, Storybook test-runner, Playwright screenshot tests, Chromatic, Loki, Percy), executes the diff, and triages every failure as a real regression or an intended change by inspecting the diff images and the components that changed on this branch. Only updates snapshots for changes confirmed intended; never blanket-approves a diff run. Use when the user says "run the visual diff", "check for visual regressions", "VRT", "did I break the UI", "update snapshots", "storybook snapshot tests failing", or before merging a branch that touches UI components. Not for a subjective UX/design critique with no baseline (use review-design) or writing new tests from scratch (use test-suite).

0
installs
▌
DB Migrate · mgiovani bundle
Creates, checks the status of, and validates database migrations by auto-detecting the project's migration framework (Alembic, Prisma, Knex, Django, Rails/ActiveRecord, Flyway, Atlas, TypeORM, Sequelize, SQLx, golang-migrate, Liquibase) from marker files, then driving that framework's own CLI. Use when the user wants to create a new migration, check pending vs. applied migration status, or validate a migration for a missing rollback script, a missing foreign-key index, or a destructive operation like DROP TABLE / TRUNCATE / DELETE FROM. Trigger phrases include "create a migration", "check migration status", "any pending migrations", "validate this migration", "does this migration have a rollback". Not for designing the schema change itself or writing ORM model code (use implement-feature), this skill only manages migration files and framework tooling once the schema change is already decided.

0
installs
▌
Docs Check · mgiovani bundle
Read-only audit of documentation against the current codebase, flags stale docs, missing sections, broken links, and hallucinated claims (wrong file references, wrong counts, diagram entities that don't exist in code). Use for "check the docs", "audit documentation", "are the docs stale", "find hallucinations in docs", "docs health check", "does this doc still match the code", or before onboarding/release. Reports only, never edits files, for actually fixing or regenerating docs use docs-update instead.

0
installs
▌
Git Commit · mgiovani bundle
Generate a conventional commit message (conventionalcommits.org) from the staged/unstaged diff and create the commit. Use when the user wants to commit, stage changes, or needs a commit message written. Not for release commits or changelogs (use git-release) or branch-finish workflows (use gitflow).

0
installs
▌
I18N Check · mgiovani bundle
i18n completeness checker, detects the project's i18n framework (next-intl, i18next, react-intl, vue-i18n, Django gettext, Rails I18n), diffs every locale file against the default locale for missing keys, untranslated values (identical to the source string), and orphan keys, then scans changed files (or the whole codebase) for hardcoded user-facing strings that bypass the i18n layer. Reports gaps grouped by locale and can scaffold the missing keys. Use when the user mentions i18n, translations, locale files, missing translation keys, or reports a localization bug like "the pt-BR label is untranslated" or "translations are out of sync". Also reach for it proactively after a PR touches locale/translation files or adds new UI copy, to catch missing keys before they ship. Not for writing the actual translated text (this only reports what's missing/wrong, a human or translation service fills it in) and not for scaffolding a brand-new locale from zero (that's a bigger one-time setup, not a completeness check).

0
installs
▌
Jira Daily · mgiovani bundle
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 instead for forward-looking "what should I work on" planning. Not for GitHub-only standups (use gh-daily), jira-daily is Jira-only and never queries GitHub issues or PRs.

0
installs
▌
Nanobanana · mgiovani bundle
Generates and edits images by calling Google's Nano Banana / Gemini image generation API (requires a GEMINI_API_KEY), 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", "GEMINI_API_KEY", "use nanobanana to …") or wants to integrate the Nano Banana / Gemini image API into their own codebase. For any implicit or general image-generation request ("generate an image", "create a logo/hero/mascot"), the default generator is codex-imagegen, not this skill. Not a design/mockup critique tool (use review-design) and not a browser-driven screenshot flow (use agent-browser).

0
installs
▌
Oss Launch · mgiovani bundle
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, scrubs internal or AI-tooling mentions from code and docs (only after explicit confirmation of what to remove), optionally rewrites git history while the repo is still private, then flips the repo public with topics and description set. Use for "open source this", "get this repo ready to go public", "launch prep", "make this repo public", "prep this for launch", or "clean this up before I open source it". Not for PR/merge mechanics on an already-public repo (use ship) or cutting version releases (use git-release). Not for the actual image-generation call itself (use codex-imagegen or nanobanana directly) or a standalone secrets/license audit with no launch intent (use env-setup).

0
installs
▌
Test Suite · mgiovani bundle
Generates a test suite by analyzing coverage gaps, prioritizing critical and untested code paths, then writing tests in parallel that match the project's existing patterns. Use when the user wants to write tests, add test coverage, generate test cases, improve testing, or analyze coverage gaps. Supports pytest, vitest, jest, and all major test frameworks. Not for debugging a specific failing test (use fix-bug).

0
installs
▌
CI Generate · mgiovani bundle
Generate a production-ready CI/CD pipeline config (GitHub Actions, GitLab CI, CircleCI, or Jenkins) by discovering the project's actual stack, test/build commands, and dependencies. Use when setting up CI for a new project, adding a missing workflow file, or asked to create/generate a pipeline, workflow, or `.gitlab-ci.yml`/`Jenkinsfile`. Not for writing a Dockerfile itself (see docker-init), this only wires CI stages around one. Not for running existing CI checks locally (use ci-local), this skill only authors the pipeline file itself.

0
installs
▌
Create Rule · mgiovani bundle
Create a new memory/instruction rule for whatever AI coding tool a project actually uses, a CLAUDE.md entry or .claude/rules/*.md file for Claude Code, an AGENTS.md entry for Codex/Cursor/Copilot/Gemini-CLI-style tools, or a .cursor/rules/*.mdc file for Cursor. Use when the user runs /create-rule or asks to add a project rule, user/personal rule, coding standard, style guide entry, or workflow instruction to memory, AGENTS.md, or CLAUDE.md. Not for creating skills or slash commands (use create-skill). Not for discovering or installing existing third-party skills (use find-skills).

0
installs
▌
Docker Init · mgiovani bundle
Generates production-ready docker-compose.yml and Dockerfile(s) for a project by scanning its manifest files (package.json, pyproject.toml, Gemfile, go.mod, Cargo.toml) and source code for service dependencies (Postgres, MySQL, Redis, MongoDB, RabbitMQ, Kafka, Elasticsearch, MinIO, Mailhog, etc.), then emitting compose services with health checks, security hardening, resource limits, and non-root Dockerfiles. Use when the user asks to dockerize or containerize a project, add docker-compose, generate a Dockerfile, or set up local dev services in containers. Not for CI/CD pipeline configs (use ci-generate), database schema migrations (use db-migrate), or scanning/syncing environment variables and secrets (use env-setup).

0
installs
▌
Docs Update · mgiovani bundle
Refresh existing docs (architecture, onboarding, data-model, deployment, security, contributing) so they match the current codebase, verifying every claim against real code instead of guessing. Use when the user says docs are stale, asks to sync docs with recent code changes, update a specific doc file, or update a whole category (core/data/infrastructure/development) after a refactor or schema change. Not for creating docs that don't exist yet (use docs-init) or scoring/auditing doc health without editing (use docs-check).

0
installs
▌
Find Skills · mgiovani bundle
Search, install, update, and remove third-party Agent Skills from skills.sh or any GitHub/GitLab repo via the `npx skills` CLI. Use when the user wants to "find a skill", "install a skill from github", "search skills.sh", or add third-party capabilities to Claude Code/Cursor/other agents. Not for authoring new skills (see create-skill).

0
installs
▌
Git Release · mgiovani bundle
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 release, tag a version, generate a changelog, bump version numbers, cut a release, or publish a GitHub release. Not for release/hotfix branch topology or promoting one branch to another (use gitflow). Not for everyday conventional commit messages (use git-commit, this skill only creates the single release commit itself).

0
installs
▌
Inject Docs · mgiovani bundle
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 Next.js or FastAPI docs to CLAUDE.md/AGENTS.md, run the Vercel agents-md codemod, inject framework best practices for AI agents, or improve AI agent performance on a Next.js or FastAPI project. This is the only framework-doc-injection skill in this toolkit, don't look for a Next.js-specific variant.

0
installs
▌
Orchestrate · mgiovani bundle
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 under strict one-owner-per-file discipline before synthesizing the result yourself. Use for "act as orchestrator", "spawn subagents for this", "delegate this with the right models", "run this in parallel", or any task large enough to fan out across multiple independent workstreams. Not for a single well-scoped feature with a known shape (use implement-feature), not for the full spec-driven agent-teams flow with cross-agent messaging (use team-implement), and not for pure task breakdown with no execution (use project-planner).

0
installs
▌
Product Prd · mgiovani bundle
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, mandatory non-goals at medium and up, ID'd testable traceable requirements, and ends in a hand-off plus a self-grade. Use for "write a PRD", "draft product requirements", or "spec out this product". Writes no code. Not for the design spec (use product-design-spec), the visual token system (use product-design-tokens), or a single decision record (use docs-adr or docs-rfc).

0
installs
▌
Review Code · mgiovani bundle
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 thorough code review, asks to review a PR or diff, or wants over-engineered code flagged for simplification. Analysis only, identifying issues without modifying code, committing, or running tests. Not for a security-focused audit (use review-security), a visual/UX design critique (use review-design), a deep performance-only investigation with profiling and query-level analysis (use review-perf), or a heavier multi-agent PR review team with adversarial/security passes (use team-review).

0
installs
▌
Review Deps · mgiovani bundle
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 vulnerable packages, audit licenses, plan dependency upgrades, assess supply chain risk, or asks "are our dependencies safe/up to date/license-compliant". Analysis only, no code or lock-file changes. Not for app-code vulnerability scanning (use review-security) or auto-applying upgrades (this skill only recommends, never runs installs).

0
installs
▌
Review Perf · mgiovani bundle
Deep-dive performance audit of database queries, algorithmic complexity, frontend bottlenecks, and resource leaks for a PR, a commit, or the whole codebase, producing a severity-ranked report. Use when the user explicitly wants a dedicated performance review, asks to "audit performance", "find N+1 queries", "check for memory leaks", or "review query efficiency" - especially when review-code's single performance dimension isn't thorough enough. Analysis only - identifies issues without modifying, fixing, or committing code. Not for a general six-dimension review where performance is just one concern among several (use review-code), and not for a full multi-agent PR review team (use team-review).

0
installs
▌
Review Plan · mgiovani bundle
Adversarially review an implementation plan before any code is written, checking it against the actual repository rather than reading it on its own terms. Trigger on "review this plan", "poke holes in this plan", "what's wrong with this approach", or an automated pre-build gate. Assumes the plan is wrong and reports findings by severity; it never rewrites the plan and never edits files. Not for reviewing code that already exists (use review-code), not for reviewing a proposal still open for discussion (use docs-rfc), and not for producing a plan in the first place (use project-planner).

0
installs
▌
Team Review · mgiovani bundle
Multi-agent review team: architecture, security, performance, testing, style, docs/UX, plus an adversary that cross-examines the other 6, for security-sensitive, architectural, or large PRs (15+ files) where a single-agent pass risks missing cross-cutting issues. Use for auth/payments/PII changes, schema/pattern changes, compliance sign-off, or when asked to 'get the review team on this' / 'multi-agent review' / 'thorough review before merge'. For a standard PR or a quick pre-merge check, use /review-code instead, it's faster and cheaper.

0
installs
▌
Create Skill · mgiovani bundle
Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent capability, or slash command, including phrasings like 'make a command for X', 'create a slash command', 'turn this into a reusable skill', or 'package this workflow as a skill'. Not for editing CLAUDE.md/AGENTS.md memory rules (use create-rule) or discovering/installing existing third-party skills (use find-skills).

0
installs
▌
Docs Diagram · mgiovani bundle
Generate a Mermaid diagram (ER, architecture, deployment, or security) by reading the actual codebase and writing it to docs/. Use for requests like "draw an ER diagram of these tables", "show me the architecture", "diagram the deployment setup", "visualize the security data flow", or "generate a system diagram". Not for scaffolding a new docs directory structure (use docs-init), syncing existing prose docs with code changes (use docs-update), or recording a design decision's rationale (use docs-adr), this skill only produces diagrams generated from code.

0
installs
▌
Agent Browser · mgiovani bundle
Headless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and @e1-style refs for ~93% less context than raw DOM tools. Use whenever a task needs to interact with a live web page: click, fill forms, log in, extract text or data, take screenshots, test a running web app, or scrape a site. Triggers on 'automate the browser', 'fill this form', 'click the button', 'take a screenshot of the page', 'log into', 'scrape this site', 'test my web app', 'headless browser'. Not for Playwright test-suite authoring or CDP/service-worker work needing the full JS API: use Playwright directly. Not for driving the user's own already-open, logged-in Chrome tab: use claude-in-chrome for that.

0
installs
▌
Git Create Pr · mgiovani bundle
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 release/hotfix branch PRs use gitflow, and for the full review-then-commit-then-PR pipeline in one go use ship.

0
installs
▌
Improve Skill · mgiovani bundle
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 the same pass, then benchmarks the rewrite against the frozen baseline with deterministic grading before calling it done. Use when the user wants to improve, audit, refresh, modernize, tighten, or benchmark a skill that already exists: "make this skill better", "this skill's description never triggers right", "audit my skills", "is the new version of X actually better", "clean up this SKILL.md". Not for creating a brand-new skill from scratch (use create-skill) or discovering/installing third-party skills (use find-skills).

0
installs
▌
Prd To Issues · mgiovani bundle
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; it never writes the PRD, never estimates, and never closes or merges anything. Not for writing the PRD itself (use product-prd), not for sequencing work inside one ticket (use project-planner), and not for filing a single ad-hoc issue you could type yourself.

0
installs
▌
Review Design · mgiovani bundle
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, color, dark mode, shadows/elevation, buttons/icons, feedback states, motion, or accessibility contrast. Triggers on "design review", "UX audit", "accessibility audit", "check contrast", "review this against WCAG". Analysis only, cites evidence and a criterion for every finding, never modifies code. Not for correctness, security, dependency, or performance review (use review-code, review-security, review-deps, or review-perf), nor the full multi-agent PR review team (use team-review). Not for pixel-diff visual regression testing against a baseline (use vrt-check).

0
installs
▌
Codex Imagegen · mgiovani bundle
Generates images and polished raster art (logos, mascots, hero images, icons, characters, sprite sheets, illustrations, product mockups) by driving Codex CLI's $imagegen skill. This is the default image generator, use it for any request to generate or create an image or visual asset, including "generate an image", "create a hero image", "make a mascot", "design a logo", "draw an icon", "generate a sprite sheet", or "make an illustration". Requires the `codex` CLI installed and authenticated (ChatGPT or API-key auth). Not for architecture, flow, or sequence diagrams (use docs-diagram).

0
installs
▌
Team Implement · mgiovani bundle
Spec-driven team orchestration for large, multi-component features or new epics: writes a full spec/design/review artifact trail under .specs/, gates code changes behind an explicit user approval, then scales a team from 3 (lite) to roughly 9 (full) agents based on complexity. Use for sizable features spanning frontend+backend+DB, unfamiliar domains, or anything you want a reviewable spec for before code is touched. Not for small/single-component changes (use implement-feature, no spec overhead) and not for reviewing already-written code (use team-review).

0
installs
▌
Clotho Research · mgiovani bundle
Find what a change will actually touch before planning it — the existing code that must change, the prior art worth copying, and the risks that will bite. Trigger on "what would this change touch", "research this before we plan it", or an automated pre-planning step. Reports files, sources, and risks; it never proposes an implementation and never edits anything. Not for auditing dependencies (use review-deps), not for writing the plan itself (use project-planner), and not for reviewing code that already exists (use review-code).

0
installs
▌
Project Planner · mgiovani bundle
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 the milestones for X". Planning only, it does not implement code (use implement-feature for that) and it does not diagram existing code (use docs-diagram for architecture diagrams of what already exists).

0
installs
▌
Review Security · mgiovani bundle
Perform an OWASP Top 10-focused static security review of a PR, commit, or entire codebase, grep for vulnerable patterns (injection, broken access control, crypto failures, hardcoded secrets), verify each match by reading it in context, and produce a severity-ranked report with file:line evidence and fix suggestions. Use to audit code security, scan for vulnerabilities, or check OWASP compliance, "security review", "scan for vulnerabilities", "check OWASP top 10", "audit for XSS/SQLi/hardcoded secrets", "is this PR safe to ship security-wise". Analysis only, never modifies code. Not for general code quality review (use review-code), dependency CVE/license/staleness auditing (use review-deps), or a multi-agent PR review team (use team-review).

0
installs
▌
Implement Feature · mgiovani bundle
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 completion. Use when the user wants to implement, build, add, or ship new functionality (a feature, endpoint, component, module, or integration). Not for fixing an existing bug (use fix-bug), restructuring code that already works with no new behavior (use refactor), or a large multi-service build that explicitly needs a full adaptive team of 3-11 agents (use team-implement).

0
installs
▌
Product Design Spec · mgiovani bundle
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 only the 2-3 most critical screens, WCAG 2.2 AA delegated to review-design. Use for "write a design spec", "map the user flows", "screen inventory with states", or "IA and screen states for this feature". Writes no UI code. Not for a UX critique of an existing UI (use review-design), the visual token system (use product-design-tokens), or rendering mockups and hero images (use codex-imagegen).

0
installs
▌
Project Illustrator · mgiovani bundle
Create or refine a cohesive visual identity for a software project through mascots, logos, README heroes, social cards, circular thumbnails, and supporting illustrations. Use when project artwork must share one recognizable character, palette, composition language, and production-quality finish. Not for architecture or flow diagrams.

0
installs
▌
Product Design Tokens · mgiovani bundle
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 version-pinned, runtime-probed, and always paired with the DTCG JSON. Use for "define our design tokens", "create a DTCG token file", or "set up our colour palette with contrast checks". Not for the screen structure (use product-design-spec), a UX/accessibility critique (use review-design), or generating logo/hero art (use codex-imagegen). Writes no application code.

0
installs

55 published skills