Menu
SkillsMP has collected 62 skills from Integralist/agent-skills. Open a skill to review its source and details.
Showing 40 of 62 collected skills.
MANDATORY for any work on Go files (*.go). Load this before editing, reviewing, or creating any *.go file. Go coding conventions and style guide covering naming, error handling, testing, HTTP handlers, caching, concurrency, and observability.
Rewrite text to be more concise, clear, and direct without losing critical information. Inventories load-bearing details first, rewrites, then audits the rewrite to verify nothing essential was dropped — for a plan, technical guide, agent instructions, or any…
Write or improve technical documentation. Applies documentation best practices: brevity, focusing on why and what rather than how, simple visualizations, modularization, and decoupling from volatile code. Use when writing new documentation from scratch, or…
Code review using specialized subagents. Analyzes behavior and tests, security, reliability, and maintainability. Use when reviewing a remote PR or local code, including unpushed/uncommitted changes. Pass --plan or --plan=<path> to check the diff against an…
Create git commits with intelligent file grouping. Use when committing changes or drafting a commit message.
Turn the plan already worked out this session into a mechanical, TDD-shaped task list a cheaper agent can execute without exploring — verbatim tests, verbatim code, and a runnable check per task. Writes to docs/tasks/.
Surface systemic patterns from an investigation as codified conventions, anti-patterns, or skill improvements.
Continue working through a project plan. Finds the next actionable slice and implements every task in it.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Rewrite prose, documentation, PR descriptions, or copy to eliminate AI-generated writing patterns, puffery, and machine cadence, restoring authentic human voice. Use when asked to remove AI tells, humanize text, or when the user invokes /unslop.
Generate Gherkin behavioural specifications (acceptance criteria) for a feature or plan. Feature/boundary scenarios become executable godog .feature files for Go; unit-level behaviour is captured as Given/When/Then prose. Returns scenarios plus scaffold tasks…
MANDATORY for any work on Markdown files (*.md). Load this before editing or creating any *.md file. Markdown formatting and linting conventions covering wrapping, code blocks, and linting tools.
MANDATORY for any work on Python files (*.py). Load this before editing, reviewing, or creating any *.py file. Python coding conventions and style guide covering modern typing, tooling (ruff, mypy, uv), project structure, error handling, and testing.
MANDATORY for any work on SQL files (*.sql). Load this before editing or creating any *.sql file. SQL migration conventions covering simple DDL, idempotency, batching ALTER statements, comments, and formatting.
Write unit and integration tests for Go services. Use when creating, editing, or updating tests, test helpers, mocks, fuzz tests, or benchmarks in Go projects.
Turn the current session's incident research/debugging into a report at docs/reports/. Use when the user has been investigating an incident or bug in a customer-facing service and wants it written up — "write an incident report", "document this incident",…
Conform work to the precedent a project already sets — naming, API shape, error handling, test style, document structure, terminology. Use when the user asks whether a change fits the codebase, when another skill needs to judge project conformance, or on…
Write an implementation plan to docs/plans/. ALWAYS use this skill — never hand-roll a plan by mimicking files in docs/. Use when the user wants to create a project/implementation plan, when a plan discussed in chat should be persisted, or says /project-plan.…
Strategic codebase-wide audit for aspirational redesign opportunities. Hunts for "code judo" moves that delete whole categories of complexity, drift from documented standards, drift from stated purpose, and gaps in test coverage that would make a redesign…
Extract a formal ADR (Architecture Decision Record) from an implementation plan or design doc — one ADR per genuine decision. Use when the user wants to record an architecture decision or says /to-adr, or when another skill needs to formalize a plan's…
Extract a focused PRD (Product Requirements Document) — the product-facing what & why — from a spec or plan. Use when the user wants a PRD, product framing, goals and success metrics, or says /to-prd, or when another skill offers to produce one.
Produce a specification document at docs/specifications/ — problem, solution, user stories, acceptance criteria, testing seams, and scope for a feature. The engineering source-of-truth a plan later implements. Use when the user wants a spec or says /to-spec,…
Rewrite drafted text in Mark's voice for Slack, PRs, docs and email.
Control Ghostty terminal (macOS) via AppleScript to manage panes, tabs, and windows. Use when splitting the terminal, opening new tabs or windows, running commands or tests out-of-band in a separate pane, spawning visible subagents or interactive tools,…
Draft a concise, direct pull request with a clear Problem and Solution. Use when the user asks to create, draft, or open a PR.
Branch, commit, and open a PR in one step. Creates a feature branch off the current base, commits the changes, then drafts and opens a pull request.
Create a git feature branch named for the current session's work. Slugifies the git username and derives a short kebab-case feature slug from the changes or task under discussion. Use when the user asks to start, create, or cut a branch.
Continue working through a project plan. Finds the next unchecked task and begins implementation.
Create, adopt, extend, submit, sync, restructure, inspect, or merge dependent pull requests with the official gh-stack extension. Use when the user requests stacked PRs, a plan or task list declares PR layers, or work crosses a stack-layer boundary.
Draft or refresh a skill's eval cases, then run them in a sandbox and grade the result against the previous run.
Analyze an existing feature and produce a reimplementation plan focused on reducing complexity and fragmentation. Asks: "If we started over, what would we do differently?"
A relentless interview to sharpen a plan, decision, or idea.
A relentless interview to sharpen a plan, decision, or idea, recording ADRs and a glossary as we go.
MANDATORY for any work on agent-facing documents. Load this before creating or editing a skill, or modifying AGENTS.md, CLAUDE.md, or GEMINI.md. Reference for the levers that make an agent-facing document predictable.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Recap the current session — what's done, in progress, and next.
Audit a codebase for MySQL index correctness. Finds composite indexes broken by leftmost-prefix violations, queries that only partially use an index (index gaps), and index killers (leading wildcards, function-wrapped columns, type mismatches). Static…
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Use when the user says "caveman mode", "talk like caveman", "use caveman", or…
Elicit and pin down the user's intent before starting work. Use when a request is too vague to act on, when another skill hits a vague request and needs to clarify it, or when the user says "help me with this", "I need something", "let's work on...", or…
Pressure-test code-review feedback before acting on it — verify each suggestion with technical rigor rather than complying reflexively. Use when receiving review feedback, before implementing suggestions, especially if feedback seems unclear or technically…