ZSL agentic engineering skills — daily-driver slash commands for triage, TDD, code review, and more.
npx claudepluginhub zunosmartlabs/zsl-superpowersDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, domain doc layout, and ship style (PR vs direct push). Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, domain docs, or ship style.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Fan out the unblocked [AFK] sub-tasks of a parent (PRD) issue into parallel /tdd sub-agents in worktrees. Sub-agents commit but do NOT push; the orchestrator merges every slice branch onto the PRD branch in wave order with --no-ff, then opens a single integration PR. AFK-only — [HITL] slices are skipped. PR-style repos only.
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Do a comprehensive code review of the current branch
Create git commits with user approval and no Claude attribution
Create a git branch with a name that matches the auto-PR workflow prefix convention
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Use when querying AWS infrastructure via Steampipe. Provides correct table names, column schemas, and query patterns.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Frontend design skill for UI/UX implementation
Creative skill for generating algorithmic and generative art. Produces visual designs using mathematical patterns, fractals, and procedural generation.
Humanise text and remove AI writing patterns. Detects and fixes 24 AI tell-tales including inflated language, promotional tone, AI vocabulary, filler phrases, sycophantic tone, and formulaic structure.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents: true, providing patterns for 'use cache' directive, cacheLife(), cacheTag(), cache invalidation, and parameter permutation rendering.
Share bugs, ideas, or general feedback.
Fork of mattpocock/skills, customized for the ZSL Agentic Engineering workflow. Agent skills we use every day for real engineering — not vibe coding.
Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away control and make bugs in the process hard to resolve. The skills here are small, easy to adapt, and composable. They work with any model.
The skills compose into one end-to-end loop. Most days you only touch a few of them.
/setup-zsl-superpowers — configure the issue tracker, triage label vocabulary, domain doc layout, and ship style for this repo. Run once before anything else./grill-me or /grill-with-docs — interview yourself to surface what you're actually building. grill-with-docs also updates CONTEXT.md and ADRs inline./to-prd — synthesise that conversation into a PRD on the issue tracker./to-issues — break the PRD into vertical-slice sub-issues. Children are labeled needs-triage; the PRD parent is auto-relabeled to tracking. Slice titles use the [AFK|HITL] <wave>[<letter>] — <description> format so the dependency graph reads at a glance (same wave = runnable in parallel)./triage — triage each child to ready-for-agent (with an agent brief), ready-for-human, or needs-info. Skip triaging the PRD itself; you just wrote it./tdd-parallel <PRD> — fan out the unblocked [AFK] ready-for-agent children into parallel /tdd sub-agents in worktrees. Sub-agents commit but do not push (/tdd --no-ship). The orchestrator merges every slice branch onto the PRD branch in wave order with --no-ff, then opens one consolidated integration PR. Halts with a structured RCA on agent failure, merge conflict, or zero-progress cycles. PR-style repos only; [HITL], container, and blocked items are skipped./tdd <child> — single-issue red-green-refactor. Refuses if you point it at a container./tdd reads docs/agents/ship-style.md. PR-style opens a PR per slice; direct-push pushes the feature branch and you merge by hand./commit for clean, attribution-free commits./code-review before opening the PR.git worktree remove and git branch -d to clean up the parallel-tdd worktrees and branches (the next /tdd-parallel run also sweeps these in its pre-flight).Every issue carries one category role (bug or enhancement) and one state role: needs-triage, needs-info, ready-for-agent, ready-for-human, tracking, or wontfix. See /triage for the full state machine and transitions.
Where state is stored and how closure works depends on the backend you picked in /setup-zsl-superpowers:
GitHub project dashboard — state lives as labels on each issue and is mirrored to the project board's Status field via the mapping in docs/agents/project-board.md. /triage updates both. When a child issue's PR merges, GitHub closes the child; when the last child of a tracking PRD closes, GitHub auto-closes the parent — no manual transition needed.
Local markdown files — state lives as a Status: line near the top of each .md file under .scratch/<feature-slug>/. Closure is folder-based, and nothing is deleted:
.scratch/<feature-slug>/issues/<NN>-<slug>.md to .scratch/<feature-slug>/issues/done/<NN>-<slug>.md. The filename and final Status: line are preserved so the archive records why it closed (e.g. shipped from ready-for-agent vs wontfix)..scratch/<feature-slug>/ directory to .scratch/done/<feature-slug>/, preserving its internal layout. There's no auto-close: move the feature explicitly once all its issues sit in issues/done/ (or you've decided to abandon it).Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim