jimmypaolini
- 56 skills
- 0 followers
- 3 days ago last updated
- ▌ Improve Codebase Architecture · jimmypaolini bundleScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- ▌ Tdd · jimmypaolini bundleTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
- ▌ Triage · jimmypaolini bundleMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
- ▌ Wizard · jimmypaolini bundleGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
- ▌ To Spec · jimmypaolini bundleTurn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
- ▌ Ask Matt · jimmypaolini bundleAsk which skill or flow fits your situation. A router over the skills in this repo.
- ▌ Gh Stack · jimmypaolini bundleManages 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 checked out.
- ▌ Prototype · jimmypaolini bundleBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
- ▌ Query SQL · jimmypaoliniToolkit for interactively querying and exploring the local PostgreSQL database schema and data using the local psql client. Use when asked to write a SQL query, explore database schemas, inspect table structures, or execute local database queries. Relies on workspace default environment variables.
- ▌ Wayfinder · jimmypaolini bundlePlan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
- ▌ Impeccable · jimmypaolini bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Stay Awake · jimmypaoliniUse when running long coding-agent sessions on macOS that risk idle sleep, especially when tests, builds, debugging, or CI triage may outlast display or system sleep timers, when starting implementation from a spec or ticket set or similar long-running task, or when the user says "caffeinate yourself".
- ▌ To Tickets · jimmypaolini bundleBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
- ▌ Backup Code · jimmypaoliniCreate a safety backup before potentially destructive actions. Use when running risky git commands (reset, rebase, clean, restore, checkout with overwrite, force push), applying large sweeping edits, mass refactors, broad search-and-replace, generator rewrites, or any operation that may be hard to undo. Produces a recoverable snapshot via backup branch, stash, or both, and verifies recovery commands.
- ▌ Code Review · jimmypaolini bundleReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
- ▌ Commit Code · jimmypaoliniWrite commit messages following this codebase's Conventional Commits standard with Gitmoji support. Use this skill when creating commits or when asked about commit message formatting.
- ▌ Spell Check · jimmypaoliniRun and triage cspell in this codebase. Use when spell-check fails in lint-staged, nx affected, or nx run-many, when cspell reports Unknown word entries, or when adding domain vocabulary to the correct dictionary under configuration/.cspell. Covers full-workspace checks, project-targeted checks, and dictionary update validation.
- ▌ Write React · jimmypaoliniReact coding conventions for this codebase. Use when writing or reviewing React components, when asked about component structure, section ordering, Tailwind CSS usage, state management patterns, conditional rendering, list rendering, or React 19 conventions. Covers component section layout (🔖🧩🪝🏗💪🏁🎨), Tailwind CSS with theme tokens, TanStack Router file-based routing, lexico-components usage, and testing with Vitest + RTL.
- ▌ Restore Code · jimmypaoliniRestore code safely from backup artifacts created before risky changes. Use when undoing destructive operations, recovering from failed refactors or rebases, restoring deleted files, rolling back broad search-and-replace edits, or rehydrating work from backup branches and stashes. Supports preview-first recovery via backup branch, stash, or selective file restoration.
- ▌ Sign Commits · jimmypaoliniRe-sign unsigned commits on the current branch or pull request without changing code content by rewriting only from the first unsigned commit onward on a temporary branch. Use when asked to sign commits, add GPG signatures to an existing branch, satisfy signed-commit requirements, or make a PR show verified commits. Creates a backup branch first, runs the rebase non-interactively, verifies the rewritten final tree exactly matches the original branch tip, and stops immediately if any check, conflict, drift, or GPG step fails.
- ▌ Write Python · jimmypaoliniPython project conventions for this codebase. Use when creating a new Python project, configuring Python tools (ruff, pyright, ty, pytest, bandit, vulture), writing or reviewing pyproject.toml, setting up Nx targets for Python, or asked about Python tooling setup, uv, or the language:python tag. Covers the project.json pattern, pyproject.toml structure, targetDefaults, tool execution via uv run, and ty pre-1.0 configuration rules.
- ▌ Github Issues · jimmypaolini bundleCreate, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.
- ▌ Handle Errors · jimmypaoliniApply codebase error handling patterns: Zod validation at boundaries, typed errors, early returns, and retry/backoff. Use when implementing error handling or input validation.
- ▌ Learn Lessons · jimmypaoliniRetrospective skill that analyzes a coding agent session, a set of local changes, or a branch/pull request, then extracts reusable coding patterns, architectural decisions, and best practices — and writes them into skills and AGENTS.md so future agents apply the same patterns automatically. Primary use: capturing HOW code was written (naming, structure, TypeScript idioms, module patterns, error handling), not just what the agent did. Use when asked to "learn from this session", "capture patterns from this PR", "remember how we did this", "document this approach", "improve skills from this work", or "make sure future agents do it this way".
- ▌ Rename Branch · jimmypaoliniRename a git branch. Analyzes changes against the main branch, decides on a conventional name, and executes the rename.
- ▌ Seed Postgres · jimmypaoliniUse this skill to dump and restore local PostgreSQL databases, schemas, and tables (collections) using Nx targets and pg_dump/pg_restore. Use when asked to backup, dump, export, restore, import, or copy local database data.
- ▌ Testing Mocks · jimmypaoliniCreate and structure mocks for tests using createMock, vi.mock, and NestJS DI patterns. USE WHEN writing unit or integration tests with mocked dependencies, when asked about mocking services or repositories, or when setting up test environments with injected dependencies.
- ▌ Validate Code · jimmypaoliniRun the full code quality validation suite for this codebase. Use this skill when you have finished implementing code changes and want to verify they are clean before committing, when told to "validate", "check quality", or "run linting", or before invoking the submit-changes skill. Runs lint-codebase (format, lint, typecheck, knip, spell-check) using the write configuration to auto-fix what it can, then checks that nothing remains.
- ▌ Submit Changes · jimmypaoliniAutomatically submit local changes through the full branch → commit → push → pull request pipeline. Includes branch-name conformance checks and automatic branch rename when needed. Use this skill when asked to submit, ship, or push changes; when you want to move from local changes to an open PR in one step; or when orchestrating the complete git workflow automatically without manual steps.
- ▌ Write Comments · jimmypaoliniApply codebase commenting conventions for TypeScript, Python, and any language. USE WHEN writing or reviewing comments, adding section comments, organizing code into logical groups, or asked about comment style. Covers when to comment, how to write good comments, section comment format (emoji + capitalized name), emoji reference table, and anti-patterns to avoid (obvious comments, redundant JSDoc, TODO lint bypasses, dash-line dividers).
- ▌ Checkout Branch · jimmypaoliniCreate and validate Git branch names following this codebase's Conventional Commits naming convention. Use this skill when creating branches, renaming branches, or when asked about branch naming rules and validation.
- ▌ Diagnosing Bugs · jimmypaolini bundleDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
- ▌ Domain Modeling · jimmypaolini bundleBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
- ▌ Codometer Triage · jimmypaoliniAct on a codometer limit breach, a comment or documentation budget breach, a stale committed report, or a run that failed outright. Use when a codometer --check exits non-zero, when a size or count limit was breached, when a comment block ran past its word, line, or character budget, when a committed report reads stale against a fresh measurement even though nothing changed, when a limit fails to bind or a target matches no files, or before reaching for a repository's limit value to make a failing check pass.
- ▌ Explore Codebase · jimmypaoliniExplore codebase files, patterns, and structure for a given topic. USE WHEN gathering implementation context before planning or executing tasks, when asked to research the codebase, or when a planning agent needs a Sub-Agent A (Codebase Research). Returns a Codebase Research Summary with relevant files, existing patterns, affected Nx projects, reusable code, related plans, constraints, and open questions.
- ▌ Testing Strategy · jimmypaolini bundleUse codebase testing conventions: unit, integration, end-to-end test naming and Nx commands, plus the four gates a change must clear — test coverage, type coverage, compiled size, and advisory duplication. Use when adding tests, recommending test coverage, running type-coverage, or checking which quality gates a touched project has to pass.
- ▌ To Questionnaire · jimmypaolini bundleTurn a decision you can't fully answer into a questionnaire for someone else to fill in.
- ▌ Write Typescript · jimmypaolini bundleTypeScript coding conventions for this codebase. Use when writing or modifying TypeScript or TSX files, when TypeScript type errors appear, or when asked about strict mode, type imports, naming conventions, return types, the no-any rule, async functions, floating promises, exhaustive switches, readonly properties, non-null assertions, control-flow style, test typing patterns, Node fs Dirent mock typing, formatting with oxfmt, import group order, enforced alphabetical ordering, the three-parameter limit, or JSDoc on public APIs.
- ▌ Codependix Export · jimmypaoliniRun a codependix dependency graph export, choose between --check and --write, point a run at a workspace root or a configuration file, or read a Mermaid block or JSON graph it produced. Use when running codependix or npx codependix, when a run exits 0 having written nothing, when looking for a flag that selects one graph type, when wiring codependix into a CI step, or when reading an exported Nx Neighborhood, NestJS module graph, or file-level import graph. Covers the command-line host directly, without assuming any task runner.
- ▌ Codependix Triage · jimmypaoliniAct on a codependix run that failed or reported drift — a --check that reported stale exports, a project that failed its export, a missing anchor block, a NestJS container that failed to boot, a rejected command line, or a --write that produced no files at all. Use when codependix exits non-zero, when a committed Mermaid block disagrees with a fresh run, when a graph export is missing for one project but not others, or before hand-editing an exported diagram to make a check pass.
- ▌ Codometer Measure · jimmypaoliniRun a codometer measurement, decide where its report goes, or read a badge block or JSON report it produced. Use when running codometer or npx codometer, choosing --write and --check flags, wiring codometer into a CI step, splicing a badge block into a README, or reading a codometer JSON report's metrics, limits, or failures. Covers the command-line host directly, without assuming any task runner.
- ▌ Triage Deployment · jimmypaoliniDiagnose and fix failing GitHub Actions CI workflows in this codebase. Use when a CI check fails on a pull request or push, when you see red checks in GitHub Actions, when asked to fix CI, debug a workflow failure, or investigate a failing job. Accepts logs pasted directly in chat OR retrieves them automatically via the gh CLI. Triages failures for: lint-codebase (typecheck, eslint, oxlint, oxfmt, spell-check, knip, markdown-lint, yaml-lint, conformetry-validate, synchronization targets), test-coverage, validate-conventions (branch name, PR title/body, config sync), audit-issues (issue labels and metadata), scan-security (gitleaks, bandit, dependency audit, licenses, trivy), and make-projects (builds, bundle sizes, devcontainer image).
- ▌ Triage Submission · jimmypaoliniTriage and fix git submission failures for both commits and pushes. Use when a git commit or push is rejected, when lint-staged errors occur, when pre-commit or pre-push hooks fail, when a branch name is invalid on push, or when you see errors from husky, commitlint, validate-branch-name, ESLint, oxfmt, prettier, typecheck, knip, cspell, markdownlint, or yamllint during a commit or push attempt. Reads the error output, identifies the failing hook and checks, reads the relevant configuration, and applies targeted fixes.
- ▌ Callidescope Trace · jimmypaoliniRun callidescope and read what it printed — a whole-workspace trace, or the depth and breadth commands against one or more callables, each addressed as file#qualified-name. Use when running callidescope or npx callidescope, when reading a call stack, a module-spread row, a breadth row, or a possibly-misplaced row, when a depth printed as "≥ n" needs interpreting, when reading a committed markdown report, mermaid diagram, or JSON report, when a run narrowed with --directories reports a frame, a stack, or a project the run was never pointed at, when a depth moved without an edit that explains it, or when asking who calls this, what does it call, what would this rename touch, and where should this callable be split before a refactor starts.
- ▌ Callidescope Triage · jimmypaoliniAct on a callidescope run that failed — a depth gate that reported a stack over the limit, a breadth gate, a stale committed report, a module-spread or possibly-misplaced finding, a project whose tsconfig could not be read, a run that traced nothing, a rejected command line, a project's own callidescope.config.ts refused for a workspace-only field or an unresolved entry-point address, or a configuration refused before anything was traced. Use when callidescope exits non-zero, when a call stack got deeper in a change, when a committed report or diagram disagrees with a fresh run, when a depth is printed as a floor rather than a number, when a declared entryPoints.addresses entry resolves to nothing or to more than one declaration, when --check breadth is refused for want of a declared limit, or before reaching for maximumDepth to make a failing check pass.
- ▌ Codependix Navigate · jimmypaoliniRead a committed codependix dependency graph to answer a question about a codebase before changing it — what depends on this project, what a rename or a signature change would touch, which modules a NestJS container really wires together, or whether a file-level import cycle is real. Use when scoping the blast radius of a refactor, when tracing why a project pulls in something it should not, when checking whether a file is actually unused, or when reading an exported Nx Neighborhood, module graph, or import graph rather than producing one.
- ▌ Codometer Configure · jimmypaoliniWrite or edit a codometer.config.ts, declaring targets, limits, comment and documentation budgets, custom convention counters, exclusions, or output destinations. Use when a repository has no codometer configuration yet, when adding a size or count limit, when bounding how long a comment block or a JSDoc comment may run, when declaring a target for compiled or generated output, when counting a naming convention no built-in analyzer knows about, when a limit fails to bind or a target matches no files, or when deciding whether one configuration can describe every project in a workspace.
- ▌ Create Pull Request · jimmypaoliniCreate and manage pull requests following this codebase's conventions. Use this skill when creating PRs, opening PRs for review, writing PR descriptions, or asked about PR workflows and best practices.
- ▌ Update Pull Request · jimmypaoliniUpdate an existing pull request's title and description to accurately reflect the implemented changes. Use this skill when asked to update, refresh, or rewrite a PR title or description, sync a PR with the latest changes, or when the PR description no longer matches the implementation.
- ▌ Codependix Configure · jimmypaoliniWrite or edit a codependix.config.ts — which graph types run, per-project overrides, include and exclude globs, the whole-workspace graph, and where each export lands. Use when a workspace has no codependix configuration yet, when a run produced no output because everything resolved to target none, when adding a JSON or Markdown destination, when choosing between an anchor block and a standalone file, when a configuration is rejected for a missing destination, or when deciding whether one configuration can describe every project in a workspace.
- ▌ Conformetry Generate · jimmypaoliniScaffold code with a conformetry generator instead of writing it by hand. Use when adding a module, component, service, application, or package to a workspace that has a conformetry configuration; when deciding whether a generator exists for the shape you are about to create; when a generator run overwrote or misplaced files; or when a conformance run reports a file that a generator should have produced. Covers both the Nx plugin and the conformetry command-line host, whose input contracts differ.
- ▌ Conformetry Validate · jimmypaolini bundleRun a conformetry conformance check and act on what it reports. Use when a conformetry-validate target fails; when a composite lint run reports conformance differences; when a report names a missing file, a missing declaration, a missing comment, an ambiguous instance, or an unmatched instance; when deciding whether to edit an instance or regenerate it; or before claiming generated code is finished. Covers both the Nx plugin and the conformetry command-line host.
- ▌ Conformetry Configure · jimmypaolini bundleAdd or change a conformetry generator, and write the template it renders. Use when a needed generator does not exist yet; when editing a conformetry configuration file; when writing or changing files under a template directory; when choosing placeholders or naming-case variants; when a generated file came out with an empty value or an odd path segment; or when a conformetry command refuses to run because the emitted generator plugin is out of date.
- ▌ Refresh Documentation · jimmypaoliniReview and update all project documentation to keep it accurate and current. Use this skill when asked to refresh, update, or audit documentation, README files, AGENTS.md files, skill descriptions, or any markdown docs across the codebase.
- ▌ Callidescope Configure · jimmypaoliniTell callidescope what to do — the command-line flags (--check, --write, --addresses, --directories, --format, --config, --json, --markdown) and the callidescope.config.ts they read alongside, covering depth, breadth, and spread limits, declared and rule-based call-stack entry points, exclusions and ignored callees, the workspace's module layout, where a run writes its JSON, markdown, mermaid, and per-project reports, and the much smaller surface a project's own configuration file may set. Use when wiring a depth gate into CI or a commit hook, when a whole-workspace run is too slow, when choosing between --check and --write, when a repository has no callidescope configuration yet, when a project needs its own depth or breadth limit, when a package low in the graph measures nothing, when a trace judges code it should not be judging, when everything is reported as an orphan root, when reading callidescope limits, or when deciding where a committed report should live.
- ▌ Setup Matt Pocock Skills · jimmypaolini bundleConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.