AbsolutelySkilled logo

AbsolutelySkilled

A registry of production-ready skills for AI coding agents.
www.absolutelyskilled.pro

What is this?

AbsolutelySkilled is a collection of skills that teach AI agents domain-specific knowledge - from framework APIs to marketing strategy. Each skill is a self-contained folder with structured markdown that agents load on demand.

Skills work with any agent that supports the SKILL.md format: Claude Code, Gemini CLI, OpenAI Codex, Cursor, and 40+ more agents.

Flagship Skills

These skills form the backbone of AbsolutelySkilled - install them first and watch your AI agent transform from a code assistant into an autonomous development partner.

Absolute Brainstorm - Relentless Design Interview

A structured design interrogation that reads your entire codebase before asking a single question - every assumption challenged, every dependency resolved, one decision at a time.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill absolute-brainstorm

Usage:

/absolute-brainstorm "Add real-time notifications to our app"
/absolute-brainstorm "Redesign the authentication flow to support SSO"
/absolute-brainstorm "Build a platform with chat, billing, analytics, and admin dashboard"

How it works:

Reads everything - docs/, README, CLAUDE.md, recent commits, project structure
Explores the codebase - searches code before every question so it only asks what can't be inferred
Enters plan mode - all reasoning happens in plan mode with ultrathink-level depth
One question at a time - strictly linear, dependency-resolved. Decision B is never asked until Decision A is locked
Marks (Recommended) on every option set - with clear rationale, no wishy-washy "it depends"
No fake options - only proposes multiple approaches at genuine design forks. If the answer is obvious, says so
Decomposes large projects - flags multi-system requests and breaks them into sub-projects automatically
Writes a spec to docs/plans/YYYY-MM-DD-<topic>-design.md
Self-reviews via subagent - catches gaps and contradictions before you see it
You choose what's next - writing-plans, absolute-human, direct implementation, or something else

Absolute-Human - AI-Native Development Lifecycle

A complete SDLC replacement for AI agents - decomposes features into dependency-graphed tasks, executes them in parallel waves with TDD verification, and tracks everything on a persistent board.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill absolute-human

Usage:

/absolute-human "Add OAuth2 login with Google and GitHub providers"
/absolute-human "Migrate the REST API to GraphQL"
/absolute-human "Build a real-time chat feature with WebSocket support"

How it works:

Interview - extracts requirements, constraints, and success criteria
Decompose - breaks work into a dependency-graphed DAG of atomic sub-tasks
Discover - explores your codebase and docs in parallel per task
Plan - creates test-first implementation strategies per task
Execute - runs independent tasks simultaneously via sub-agents in parallel waves
Verify - validates every task with TDD, lint, typecheck, and build checks
Converge - self code review, requirements validation, and full project verification

Everything is tracked on a persistent .absolute-human/board.md that survives across sessions - resume where you left off, audit decisions, or hand off to another developer.

INTAKE --> DECOMPOSE --> DISCOVER --> PLAN --> EXECUTE --> VERIFY --> CONVERGE

Second Brain - Persistent Memory for AI Agents

A structured, hierarchical knowledge store in ~/.memory/ that gives your AI agent persistent memory across projects, sessions, and tools - automatically loading only what's relevant to the current context.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill second-brain

Usage:

# Memories are loaded automatically at conversation start
# After complex tasks, your agent proposes what to remember

"Remember that we always use Bun instead of npm"
"What do you know about our auth system?"
"Update my memory about the deployment process"

How it works:

Tag-indexed retrieval - memories are scored against your current context and only the top matches are loaded (no wasted tokens)
100-line ceiling - files stay small and split automatically, keeping context window usage efficient
Wiki-linked graph - memories cross-reference each other with [[wiki-links]] for rich knowledge traversal
Auto-propose learnings - after complex tasks, your agent suggests what to remember for next time
CRUSP lifecycle - Create, Read, Update, Split, Prune - your memory stays fresh and organized

Skill Audit - Security Analysis for AI Agent Skills

A deep, context-aware security scanner for AI agent skills - combines a Python mechanical pre-scan with AI-powered semantic analysis across 6 threat categories to catch prompt injection, data exfiltration, supply chain attacks, and behavioral risks that regex tools miss.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill skill-audit

Usage:

/skill-audit skills/suspicious-tool
/skill-audit skills/suspicious-tool --json
/skill-audit skills/                          # Batch scan entire registry

How it works:

Mechanical pre-scan - scripts/audit.py handles deterministic checks: unicode smuggling, base64 payloads, frontmatter validation, file size limits, phantom dependencies, orphaned references
Prompt injection analysis - reads every instruction as an attacker would: direct overrides, persona hijacking, instruction laundering, conditional triggers, multi-step manipulation
Permission and exfiltration audit - flags destructive commands, credential access, webhook data theft, DNS exfiltration, covert channels
Supply chain verification - maintainer provenance, dependency confusion, typosquatting, suspicious URLs, scope creep detection
Behavioral safety (AI-only) - unbounded agent loops, user consent bypass, hallucination amplification, context pollution, trust transitivity
Structured verdicts - PASS / FAIL / REVIEW REQUIRED with severity-ranked findings table and per-finding recommendations

Output as a human-readable table report (default) or JSON for CI/tooling integration.

Video Creator - End-to-End Programmatic Video Production

A 7-step orchestrator that takes you from "make me a video about X" to a finished 4K video - using Remotion, ElevenLabs TTS, royalty-free music, and SFX. No video editing knowledge required.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill video-creator

Usage:

/video-creator "Create a 60-second product demo for my SaaS dashboard"
/video-creator "Make an explainer video about how our API works"
/video-creator "Build a social clip announcing our new feature"

How it works:

Deep interview - up to 30 questions about your product, audience, tone, assets, and visual preferences
Generate script - structured YAML with scenes, timing, narration text, and audio cues
Visual verification - build minimal Remotion compositions, preview in browser, iterate on design
Build full project - complete Remotion compositions with all animations matching the approved script
Add background audio + SFX - source royalty-free music, place sound effects at trigger points
Add narration - ElevenLabs TTS with voice selection (deferred to save costs until visuals are approved)
4K render - final preview, user approval, render at 3840x2160

Companion skills: remotion-video, video-scriptwriting, video-audio-design, video-analyzer

Supaguard - Synthetic Monitoring from Your Codebase

A production monitoring skill that reads your source code, generates Playwright monitoring scripts, and deploys them as recurring checks via the supaguard CLI - all without committing any test scripts to your repository.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill supaguard

Usage:

# Point at your app and the agent does the rest
"Set up monitoring for my Next.js app"
"Monitor the login flow on production"
"Create an uptime check for our checkout page"

How it works:

Reads your source code - scans components, routes, data-testids, API endpoints, and forms
Identifies critical flows - login, checkout, page load, dashboard access
Generates Playwright scripts - written to /tmp/, never committed to your repo
Tests in the cloud - runs the script via supaguard checks test before deploying
Interactive deployment - walks you through naming, scheduling, regions, and alerting one step at a time
Multi-region monitoring - US East, EU North, India Central with configurable cron schedules

Companion skills: playwright-testing, cli-design

Codedocs - AI-Agent-Friendly Codebase Documentation

Generates a structured docs/ tree from your codebase that AI agents can navigate instantly - module docs, pattern docs, an overview map, and a file-to-doc index with 70%+ coverage enforcement.

Install:

npx skills add AbsolutelySkilled/AbsolutelySkilled --skill codedocs

Usage:

codedocs:generate                              # Generate docs for your entire repo
codedocs:generate --output documentation/      # Custom output directory
codedocs:generate packages/api                 # Specific subdirectory (monorepos)
codedocs:generate --exhaustive                 # Force exhaustive coverage
codedocs:ask "how does the auth flow work?"    # Answer from docs, not source
codedocs:status                                # Check coverage and find gaps
codedocs:update --scope src/auth/              # Update after a refactor
codedocs:update --diff HEAD~5..HEAD            # Update from recent commits

How it works:

OVERVIEW.md - architecture, tech stack, entry points, and a module map that routes any question to the right doc
Module docs - one per bounded context, covering public API, internal structure, dependencies, and implementation notes. Large modules (15+ files) are automatically split into sub-module docs
Pattern docs - cross-cutting concerns like error handling, logging, auth, and testing strategy documented once instead of scattered across every module
INDEX.md - a file-to-module lookup table so any agent can instantly answer "which doc covers this file?"
Coverage-first - runs a recursive census of your repo, verifies 70%+ file coverage (scaled by repo size), and flags gaps before writing. A huge repo generates 30-80 doc files, not 8-12

Install Skills

Skills are installed using the skills CLI via npx.

Quick Start

# Install all skills from this registry
npx skills add AbsolutelySkilled/AbsolutelySkilled

# List available skills before installing
npx skills add AbsolutelySkilled/AbsolutelySkilled --list

# Install a specific skill
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill clean-code

# Install multiple specific skills
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill clean-code --skill backend-engineering

# Install globally (available across all projects)
npx skills add AbsolutelySkilled/AbsolutelySkilled -g

# Install to a specific agent
npx skills add AbsolutelySkilled/AbsolutelySkilled -a claude-code

# Non-interactive install (CI/CD friendly)
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill clean-code -g -a claude-code -y

# Install all skills to all agents
npx skills add AbsolutelySkilled/AbsolutelySkilled --all

Install Options

Option	Description
`-g, --global`	Install to user directory instead of project
`-a, --agent <agents...>`	Target specific agents (e.g., `claude-code`, `codex`, `cursor`)
`-s, --skill <skills...>`	Install specific skills by name (use `'*'` for all)
`-l, --list`	List available skills without installing
`--copy`	Copy files instead of symlinking
`-y, --yes`	Skip all confirmation prompts
`--all`	Install all skills to all agents without prompts

Installation Scope

Scope	Flag	Location	Use Case
Project	(default)	`./<agent>/skills/`	Committed with your project, shared with team
Global	`-g`	`~/<agent>/skills/`	Available across all projects

Managing Skills

# List installed skills
npx skills list

# Search for skills
npx skills find <query>

# Check for updates
npx skills check

# Update all installed skills
npx skills update

# Remove a skill
npx skills remove <skill-name>

Supported Agents

The CLI supports 40+ agents including Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Cline, Roo Code, and many more. See the full list in the skills CLI documentation.

Structure

skills/
  <skill-name>/
    SKILL.md           # Core skill content (under 500 lines)
    evals.json         # Test suite validating the skill works
    sources.yaml       # Crawl provenance (optional for domain skills)
    references/        # Deep-dive files loaded on demand
      <topic>.md

Available Skills

Software Engineering

Skill	Description
clean-code	Clean Code principles - naming, functions, SOLID, TDD, code smells, error handling
clean-architecture	Clean Architecture principles - dependency rule, layers, boundaries, component design
backend-engineering	Backend systems design - databases, APIs, distributed systems, caching, observability
frontend-developer	Frontend engineering - components, performance, accessibility, CSS patterns, testing
absolute-brainstorm	Relentless design interview - ultrathink reasoning, codebase-first questions, dependency-resolved decision trees
absolute-human	AI-native development lifecycle - task decomposition, dependency graphs, wave-based parallel execution
system-design	Distributed systems, load balancing, CAP theorem, architecture interviews
microservices	Service decomposition, communication patterns, saga, CQRS
api-design	REST, GraphQL, gRPC, OpenAPI spec, versioning, pagination
database-engineering	Schema design, indexing, query optimization, migrations
performance-engineering	Profiling, benchmarking, memory leaks, latency optimization
absolute-simplify	Autonomous code simplification - clean code, reduce complexity, remove redundancy
refactoring-patterns	Extract method, replace conditional with polymorphism, catalog of refactors
monorepo-management	Turborepo, Nx, Bazel, workspace dependencies, build caching
code-review-mastery	Reviewing code effectively, giving actionable feedback, catching anti-patterns
address-pr-comments	Address PR review comments - read open threads, make code changes, post batch replies via gh CLI
live-dependency-resolver	Live package version lookup across npm, pip, Go, cargo, gem - never hallucinate versions
edge-computing	Edge functions, CDN logic, Cloudflare Workers, latency optimization
event-driven-architecture	Event sourcing, CQRS, message brokers, eventual consistency
localization-i18n	Translation workflows, RTL, pluralization, ICU message format

DevOps & Infrastructure

Skill	Description
docker-kubernetes	Containerization, orchestration, Helm charts, service mesh
ci-cd-pipelines	GitHub Actions, Jenkins, GitLab CI, deployment strategies
terraform-iac	Infrastructure as code, modules, state management, drift detection
cloud-aws	AWS services, well-architected framework, cost optimization
cloud-gcp	GCP services, BigQuery, Cloud Run, Pub/Sub patterns
observability	Logging, metrics, tracing, alerting, SLOs, incident response
signoz	Open-source observability - distributed tracing, logs, metrics, dashboards, OpenTelemetry
sentry	Error monitoring, performance tracing, session replay, cron monitoring, source maps
linux-admin	Shell scripting, systemd, networking, security hardening
site-reliability	SRE practices, error budgets, toil reduction, capacity planning
email-deliverability	SPF, DKIM, DMARC, warm-up, bounce handling, reputation

AI & Machine Learning

Skill	Description
a2a-protocol	Agent-to-Agent protocol - interoperability, multi-agent communication, discovery
a2ui	Agent-to-User Interface - Google's protocol for agent-driven declarative UIs
mastra	TypeScript AI framework - agents, workflows, tools, memory, RAG, MCP
prompt-engineering	LLM prompting techniques, chain-of-thought, few-shot, RAG patterns
llm-app-development	Building production LLM apps, guardrails, evaluation, fine-tuning
ml-ops	Model deployment, monitoring, A/B testing, feature stores
computer-vision	Image classification, object detection, segmentation pipelines
nlp-engineering	Text processing, embeddings, search, classification, summarization
data-science	EDA, statistical analysis, visualization, hypothesis testing
ai-agent-design	Multi-agent systems, tool use, planning, memory architectures

UI/UX & Design

Skill	Description
absolute-ui	Build polished, modern UIs - spacing, color, typography, components, accessibility, animations, design systems
accessibility-wcag	ARIA, screen readers, keyboard navigation, WCAG compliance
figma-to-code	Translating Figma designs to pixel-perfect implementations
ux-research	User interviews, usability testing, journey mapping, A/B test design

Developer Tools

Skill	Description
cmux	Terminal multiplexer CLI - panes, surfaces, workspaces, browser automation
vite-plus	Vite+ unified toolchain - scaffolding, migration, dev/build/test/lint, monorepo tasks
second-brain	Persistent second brain for AI agents - tag-indexed, hierarchical knowledge
git-advanced	Rebase strategies, bisect, worktrees, hooks, monorepo workflows
vim-neovim	Configuration, keybindings, plugins, Lua scripting
regex-mastery	Pattern writing, lookaheads, named groups, performance, common recipes
shell-scripting	Bash/Zsh scripting, argument parsing, error handling, portability
debugging-tools	Chrome DevTools, lldb, strace, network debugging, memory profilers
cli-design	Argument parsing, help text, interactive prompts, config files, distribution
open-source-management	OSS project maintenance - governance, changelogs, community, licensing
meta-repo	Multi-repository management with `meta` - coordinating git/shell commands across many repos, polyrepo orchestration

Testing & QA

Skill	Description
test-strategy	Unit, integration, e2e, contract testing - when to use what
cypress-testing	E2E testing, component testing, custom commands, CI integration
playwright-testing	Browser automation, visual regression, API testing
jest-vitest	Unit testing patterns, mocking, snapshot testing, coverage
load-testing	k6, Artillery, JMeter, performance benchmarks, capacity planning
api-testing	REST/GraphQL testing, contract testing, mock servers
chaos-engineering	Fault injection, resilience testing, game days, failure modes

Security

Skill	Description
skill-audit	AI-powered security audit for agent skills - prompt injection, exfiltration, supply chain, behavioral safety
appsec-owasp	OWASP Top 10, secure coding, input validation, auth patterns
penetration-testing	Ethical hacking, vulnerability assessment, exploit development
cloud-security	IAM, secrets management, network policies, compliance
cryptography	Encryption, hashing, TLS, JWT, key management, zero-trust
security-incident-response	Forensics, containment, root cause analysis, post-mortems

SEO & Search Visibility

Skill	Description
absolute-seo	Comprehensive SEO - technical, on-page, E-E-A-T, schema, CWV, local, link building, international, e-commerce, programmatic, GEO/AEO, audits
keyword-research	Tri-surface keyword research - organic, AEO (snippets/PAA), GEO (AI citations) scoring

Marketing

Skill	Description
absolute-marketing	Unified marketing - copy, content, SEO, email, social, paid ads, CRO, brand, growth, pricing, launches
content-marketing	Blog strategy, SEO content, content calendars, repurposing
email-marketing	Campaigns, drip sequences, deliverability, A/B testing
social-media-strategy	Platform-specific tactics, scheduling, analytics, engagement
growth-hacking	Viral loops, referral programs, activation funnels, retention
copywriting	Headlines, landing pages, CTAs, persuasion frameworks (AIDA, PAS)
brand-strategy	Positioning, voice and tone, brand architecture, storytelling
developer-advocacy	Talks, demos, blog posts, SDK examples, community engagement
video-production	Script writing, editing workflows, thumbnails, YouTube SEO

Sales

Skill	Description
sales-playbook	Outbound sequences, objection handling, discovery calls, MEDDIC
crm-management	Salesforce/HubSpot workflows, pipeline management, forecasting
sales-enablement	Battle cards, competitive intel, case studies, ROI calculators
proposal-writing	RFP responses, SOWs, pricing strategies, win themes
account-management	Expansion playbooks, QBRs, stakeholder mapping, renewal strategy
lead-scoring	ICP definition, scoring models, intent signals, qualification frameworks

HR & People Operations

Skill	Description
recruiting-ops	Job descriptions, sourcing, screening, interview frameworks
interview-design	Structured interviews, rubrics, coding challenges, assessment
onboarding	30/60/90 plans, buddy systems, knowledge transfer, ramp metrics
performance-management	OKRs, reviews, calibration, PIPs, career ladders
compensation-strategy	Market benchmarking, equity, leveling, total rewards
employee-engagement	Surveys, pulse checks, retention strategies, culture building

Finance & Accounting

Skill	Description
financial-modeling	DCF, LBO, revenue forecasting, scenario analysis, cap tables
budgeting-planning	FP&A, variance analysis, rolling forecasts, cost allocation
startup-fundraising	Pitch decks, term sheets, due diligence, investor relations
tax-strategy	Corporate tax, R&D credits, transfer pricing, compliance
bookkeeping-automation	Chart of accounts, reconciliation, AP/AR, month-end close
financial-reporting	P&L, balance sheet, cash flow, board decks, KPI dashboards

Legal & Compliance

Skill	Description
contract-drafting	NDAs, MSAs, SaaS agreements, licensing, redlining
privacy-compliance	GDPR, CCPA, data processing, consent management, DPIAs
ip-management	Patents, trademarks, trade secrets, open-source licensing
employment-law	Offer letters, termination, contractor vs employee, workplace policies
regulatory-compliance	SOC 2, HIPAA, PCI-DSS, audit preparation, controls

Product Management

Skill	Description
product-strategy	Vision, roadmapping, prioritization frameworks (RICE, ICE, MoSCoW)
user-stories	Acceptance criteria, story mapping, backlog grooming, estimation
product-analytics	Funnels, cohort analysis, feature adoption, metrics (NSM, AARRR)
posthog	PostHog integration - product analytics, feature flags, A/B testing, session replay, surveys
competitive-analysis	Market landscape, feature comparison, positioning, SWOT
product-launch	Go-to-market, beta programs, launch checklists, rollout strategy
product-discovery	Jobs-to-be-done, opportunity solution trees, assumption mapping

Support & Customer Success

Skill	Description
customer-support-ops	Ticket triage, SLA management, macros, escalation workflows
knowledge-base	Help center architecture, article writing, search optimization
customer-success-playbook	Health scores, churn prediction, expansion signals, QBRs
community-management	Forum moderation, engagement programs, advocacy, feedback loops
support-analytics	CSAT, NPS, resolution time, deflection rate, trend analysis

Business Strategy

Skill	Description
api-monetization	Usage-based pricing, rate limiting, developer tiers, Stripe metering
saas-metrics	MRR, churn, LTV, CAC, cohort analysis, board reporting
pricing-strategy	Packaging, freemium, usage-based, enterprise tiers, price testing
partnership-strategy	Co-marketing, integrations, channel partnerships, affiliates

Monitoring

Skill	Description
supaguard	Synthetic monitoring from source code - Playwright script generation, multi-region checks, alerting

Operations & Automation

Skill	Description
incident-management	On-call rotations, runbooks, post-mortems, status pages, war rooms
no-code-automation	Zapier, Make, n8n, workflow automation, internal tooling

Data Engineering

Skill	Description
data-pipelines	ETL/ELT, Airflow, dbt, Spark, streaming vs batch
data-warehousing	Star schema, slowly changing dimensions, Snowflake, BigQuery
data-quality	Validation, monitoring, lineage, Great Expectations, contracts
analytics-engineering	dbt models, semantic layers, metrics definitions, self-serve analytics
real-time-streaming	Kafka, Flink, event sourcing, CDC, stream processing patterns

Mobile Development

Skill	Description
react-native	Expo, navigation, native modules, performance, OTA updates
ios-swift	SwiftUI, UIKit, Core Data, App Store guidelines, performance
android-kotlin	Jetpack Compose, Room, coroutines, Play Store, architecture
mobile-testing	Detox, Appium, device farms, crash reporting, beta distribution

Game Development

Skill	Description
unity-development	C# scripting, ECS, physics, shaders, UI toolkit
game-design-patterns	State machines, object pooling, event systems, command pattern
pixel-art-sprites	Sprite creation, animation, tilesets, palette management
game-audio	Sound design, adaptive music, spatial audio, FMOD/Wwise
game-balancing	Economy design, difficulty curves, progression systems, playtesting

Technical Writing

Skill	Description
codedocs	AI-agent-friendly codebase docs - generate layered docs, answer questions docs-first, update incrementally via git diff
technical-writing	API docs, tutorials, architecture docs, ADRs, runbooks
developer-experience	SDK design, onboarding, changelog, migration guides
internal-docs	RFCs, design docs, post-mortems, runbooks, knowledge management

Project Management

Skill	Description
agile-scrum	Sprint planning, retrospectives, velocity, Kanban, estimation
project-execution	Risk management, dependency tracking, stakeholder communication
remote-collaboration	Async workflows, documentation-driven, meeting facilitation

Blockchain & Web3

Skill	Description
web3-smart-contracts	Solidity, auditing, DeFi patterns, gas optimization, security

Cross-Functional

Skill	Description
technical-interviewing	Coding challenges, system design interviews, rubric calibration
customer-research	Surveys, interviews, NPS, behavioral analytics, persona building
presentation-design	Slide structure, storytelling frameworks, data visualization
spreadsheet-modeling	Formulas, pivot tables, dashboards, macros, financial models

Video Creation

Skill	Description
video-creator	End-to-end video orchestrator - 7-step workflow from interview to 4K render
remotion-video	Core Remotion framework - compositions, animations, rendering, project setup
video-scriptwriting	Interactive script writing - interview framework, YAML scene format, pacing
video-audio-design	Audio design - ElevenLabs TTS, background music, SFX generation, mixing
video-analyzer	FFmpeg + AI vision analysis - frame extraction, scene detection, design system extraction

Full Registry

155+ skills across 25 categories.

Creating Skills

Use the skill-forge skill to generate new skills:

/skill-forge <url-or-topic>

URL input - provide a GitHub repo or docs URL and skill-forge crawls it
Domain topic - provide a topic like "marketing" or "typescript" and skill-forge runs a brainstorm session to scope and build the skill

See CONTRIBUTING.md for the full guide on creating and submitting skills.

Contributing

We welcome contributions! Whether it's a new skill for a framework you love or fixing a typo in an existing one, check out the contributing guide.

Star History

License

MIT