Skip to content
SkillsGitHubChangelog

AI Skills for
Curated Agents

A practical skill system for engineers and founders who use AI coding agents without lowering their standards. Browse 73 curated skills across seven disciplines, install what you need, or route tasks with /which-skill.

How I engineer with these

Every skill in dhanji4U/skills comes directly from real pull requests, code reviews, and everyday pair programming. I keep the instruction files open-source so your agent holds predictable, human engineering standards.

The /which-skill router/antislop protocolReport issue

Install the skills

Install individual skills globally or deploy full categories into your agent directory.

$ npx skills add dhanji4U/skills --skill which-skill --global
$ ./install.sh --agent antigravity --all
Supports Antigravity · Codex · Claude · CursorGitHub
Slash CommandType in chat

Run directly in your coding agent once installed:

/which-skill Which skill fits this complex refactor and failing CI check?

Works with any agent

Antigravity · Claude Code · Cursor · Codex · Copilot · 73 skills · MIT

ARCHITECTURE

What is an Agent Skill?

Skills are executable markdown protocols you provide to your coding agent. They turn general language models into predictable pair engineers that respect design tokens, cite evidence, and eliminate AI prose tells.

01. The Problem

Default generic behavior

Left unguided, coding agents guess implementation choices, invent redundant helper abstractions, and produce verbose prose packed with canned conversational scaffolding.

02. The Fix

Executable protocols

A skill encodes one concrete senior engineering habit into a structured contract. The agent follows explicit steps, verification gates, and negative constraint lists every run.

03. The Compounding Effect

Chainable workflows

Skills compose without state lock-in. The verified output of an architecture review feeds directly as input to implementation, test generation, and pull request auditing.

Skills

Grouped by lifecycle and discipline across 73 curated skills.

01Meta & Routing802Principles2403Workflows2104Quality805Thinking806Architecture307Writing & Voice1
01

Meta & Routing

(8)

Universal skill router, advisor mode, CLI design, and agent evolution.

Start with /which-skill
/which-skill

The /which-skill Universal Router

Find and recommend the right agent skill for any task, problem, or question across the curated skills library. Use when the user asks "which skill should I use", "what skill fits this", "how do I do X", or when the user has a problem but doesn't know what skill exists to solve it. Also auto-triggers when work is ambiguous or needs routing.

/advisor

Advisor

Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use when the user types /advisor, asks to turn the advisor on or off, picks an advisor model, or explicitly asks for a second opinion from a stronger or different model. Never enable it on your own.

/cli-for-agents

CLI for agents

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

/continual-learning

Continual Learning

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

/create-learning-path

Create a learning path

Build a personalized learning roadmap with milestones and practice checkpoints

/run-learning-retrospective

Run a learning retrospective

Evaluate learning progress, identify blockers, and adjust the learning plan

/setup-pstack

Setup pstack

Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.

/teach

Teach

Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

02

Principles

(24)

Core engineering disciplines: root causes, subtractive design, domain modeling, and context management.

Start with /the-algorithm
/the-algorithm

The Algorithm

Apply to any non-trivial change before designing it. Make the requirement less dumb, delete, optimize, accelerate, automate, in that order, then run it again on the result. The reply names the requirement you questioned and what you deleted.

/fix-root-causes

Fix Root Causes

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

/attack-the-premise

Attack the Premise

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

/boundary-discipline

Boundary Discipline

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

/build-the-lever

Build the Lever

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

/encode-lessons-in-structure

Encode Lessons in Structure

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

/exhaust-the-design-space

Exhaust the Design Space

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

/experience-first

Experience First

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

/foundational-thinking

Foundational Thinking

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

/guard-the-context-window

Guard the Context Window

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

/laziness-protocol

Laziness Protocol

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

/make-operations-idempotent

Make Operations Idempotent

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

/migrate-callers-then-delete-legacy

Migrate Callers Then Delete Legacy APIs

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

/minimize-reader-load

Minimize Reader Load

Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

/model-the-domain

Model the Domain

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

/never-block-on-the-human

Never Block on the Human

Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.

/outcome-oriented-execution

Outcome-Oriented Execution

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

/prove-it-works

Prove It Works

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.

/redesign-from-first-principles

Redesign From First Principles

Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.

/separate-before-serializing

Separate Before Serializing Shared State

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

/sequence-verifiable-units

Sequence work into verifiable units

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

/subtract-before-you-add

Subtract Before You Add

Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

/test-behavior-not-implementation

Test Behavior, Not Implementation

Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.

/type-system-discipline

Type System Discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

03

Workflows

(21)

Autonomous and verifiable execution flows: TDD, Poteto Mode, swarm orchestration, CI remediation, and PR readiness.

Start with /poteto-mode
/poteto-mode

Poteto Mode

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

/tdd

Test-Driven Development (TDD)

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

/automate-me

Automate me

Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts.

/check-compiler-errors

Check compiler errors

Run compile and type-check commands and report failures

/create-verification-skill

Create a verification skill

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

/fix-ci

Fix CI

Find failing PR checks, inspect logs or external check links, and apply focused fixes

/fix-merge-conflicts

Fix merge conflicts

Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution

/get-pr-comments

Get PR comments

Fetch and summarize review comments from the active pull request

/loop-on-ci

Loop on CI

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

/maintain-verification-skill

Maintain a verification skill

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \"audit the verify skill\".

/make-pr-easy-to-review

Make PR Easy to Review

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

/new-branch-and-pr

New branch and PR

Create a fresh branch, complete work, and open a pull request

/ready-pr

Dyl ready PR

Get a PR merge-ready for Dylan: deep /dyl-review till 🟢, mark it ready, resolve conflicts, then babysit CI and comments. Use for /dyl-ready-pr, get PR green", "make the PR mergeable", "/dyl-review till green then ready", or ready-to-merge asks under /dyl-mode.

/review-and-ship

Review and ship

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

/run-smoke-tests

Run smoke tests

Run Playwright smoke tests, debug failures, and verify fixes

/show-me-your-work

Show me your work

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

/swarm

Swarm

Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.

/verify-this

Verify This

Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

/weekly-review

Weekly review

Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work

/what-did-i-get-done

What did I get done

Summarize authored commits over a user-specified time period into a concise update

/workflow-from-chats

Workflow From Chats

Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

04

Quality

(8)

Code review standards, TypeScript patterns, and anti-slop filters for code quality.

Start with /dyl-review
/dyl-review

Dyl Review

Review one or more PRs in Dylan's style: up to 7 copy-pasteable asks and one 🟢/🟡/🔴 call. Quick by default; "deep" adds thermos and Bugbot. Use for /dyl-review, "review this PR like me", or terse design/correctness comments. Never posts to the PR.

/deslop

Remove AI code slop

Remove AI-generated code slop and clean up code style

/no-comments

No comments

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

/technical-writing

Technical writing

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

/thermo-nuclear-code-quality-review

Thermo-Nuclear Code Quality Review

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

/thermo-nuclear-review

Thermo Nuclear Review

Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.

/typescript-best-practices

TypeScript best practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

/unslop

Unslop

Cut AI tells from any writing. Must always apply.

05

Thinking

(8)

Diagnostic playbooks, forensic investigations, and root-cause analysis.

Start with /why
/arena

Arena

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.

/bro

Bro

Restate the last message in plain human language, with no jargon.

/figure-it-out

Figure it out

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

/how

How

Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

/interrogate

Interrogate

Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles.

/recall

Recall

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.

/reflect

Reflect

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

/why

Why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Install the skills and get to work

Install the skills you want into the agents you use. Everything is MIT licensed and lives in one repo.

dhanji4U/skills
View on GitHub

Install the skills

Install individual skills via the skills.sh registry or use the universal installer script for batch setup across agents.

$ npx skills add dhanji4U/skills --skill which-skill --global
$ ./install.sh --agent antigravity --all
Target agents: antigravity, codex, claude-code, cursor, projectGitHub
Works with any agentAntigravity · Claude Code · Cursor · Codex · Copilot · 73 skills · MIT
Changelog

What changed recently

RSSFull history on GitHub
v2.0.1Oct 2, 2026

v2.0.1: Dependency Updates & Security Hardening

Bumped GitHub Actions dependencies to verified releases (actions/checkout@v7, actions/setup-python@v7, github/codeql-action@v4). Updated catalog and release changelog.

v2.0.0Oct 2, 2026

v2.0.0: Universal Agent Skills Library

Curated 73 production-grade agent skills across principles (24), workflows (21), quality (8), thinking (8), architecture (3), meta (8), and writing (1). Added universal router /which-skill, 36 companion reference playbooks, multi-agent installer install.sh, machine-readable catalog.json, automated CI validation, and repository security hardening.

v1.0.0Sep 10, 2026

v1.0.0: Initial Release (Antislop)

Initial public release of the curated agent skills collection. Features the complete antislop writing skill with 30 anti-AI writing patterns based on Wikipedia AI Cleanup, supporting Antigravity, Claude Code, Cursor, Codex, and Copilot.

OPEN REPOSITORY

Contribute to dhanji4U/skills on GitHub

All skills are licensed under MIT. Bug or safety report? Please Open an Issue. Real reports from real machines help us ensure 100% data safety. Feature idea? Open an issue first to discuss scope before opening a PR.

View GitHub RepoOpen an Issue