Directory
Discover and filter AI agent skills. 27,776 active skills available.
Popular guides from the directory
Start with intent-focused guides, then come back to the full directory when you need broader coverage.
category guide
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
category guide
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
category guide
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
best guide
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
best guide
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
category guide
AI Agents for Freelancers
Browse AI agent skills for freelancers handling client research, proposals, outreach, delivery systems, documentation, and repeatable admin work.
Results
spec-first-development
Use before implementing any change that adds, removes, or modifies package behavior, public API, types, or contracts. Ensures the governing spec is updated before code is written and a verification test plan exists.
spec-code-conformance
Mandatory verification loop after any SPEC.md or contract document change. Compares spec against implementation code, fixes code to match spec, repeats until zero discrepancies, then runs regression tests. Spec is always the source of truth — never modify the spec within this workflow.
semver-api-surface
Manages semantic versioning and public API surfaces for multi-package monorepos. Use when adding, changing, or removing exported interfaces, types, or functions to determine version impact and maintain compatibility.
scenario-verification-harness
Applies the Robota scenario verification loop by checking scope, preserving canonical ownership, re-recording only when necessary, and stopping on strict-policy failures. Use when scenario files, example flows, or execution-path behavior changes.
robota-sdk-usage
Guide Robota SDK usage patterns, constructor configuration, and migration from deprecated packages. Use when working on Robota setup, constructor options, or SDK migration.
repo-writing
Applies Robota's repository writing rules for `.design/`, general documentation, and conventional commit messages. Use when editing docs, ADRs, design notes, or preparing commit text.
repo-change-loop
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
pre-refactor-test-harness
Before modularizing or refactoring a package, analyze the code for extraction points, write characterization tests for current behavior, then modularize under test protection. Use when a package has monolithic files that need to be broken into testable modules.
post-implementation-checklist
Mandatory checklist after completing implementation work — SPEC verification, README update, npm publish, content/ docs update, docs site deploy
pnpm-monorepo-build
Provide pnpm monorepo build commands and workflow guidance. Use when running package builds, filtered builds, or discussing build order.
plugin-development
Guide plugin development workflows with validation, disable strategies, and error handling. Use when working on plugin development, plugin system changes, or plugin options validation.
package-code-review
Systematic per-package code review using six specialist perspectives (Correctness, Architecture, Type Safety, Security, Performance, Maintainability) with severity labels. Use when reviewing an entire package or a set of changed files for quality, compliance, and improvement opportunities.
logging-level-guide
Defines when to use each log level (error, warn, info, debug) and common logging anti-patterns. Use when adding or reviewing log statements in production code.
harness-governance
Governs the Robota harness by checking rule-skill-owner consistency, finding undefined terminology, spotting examples that violate rules, and preferring mechanical checks over duplicated prose. Use when editing AGENTS, skills, or repository guidance.
execution-caching
Provide execution caching workflows to reduce repeated runs and costs. Use when discussing cached execution, cache invalidation, or cache system operations.
effect-style-error-modeling
Models success and failure explicitly in TypeScript using Result or Either-like flows instead of uncontrolled exceptions. Use when implementing predictable error propagation across async workflows.
deploy-to-vercel
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
ddd-tactical-patterns
Applies Domain-Driven Design tactical patterns (Aggregate, Bounded Context, Value Object, Domain Event) to structure domain models with clear transactional boundaries. Use when designing domain objects, deciding ownership, or separating contexts.
cqrs-event-projection-basics
Applies practical CQRS and event projection fundamentals in TypeScript systems by separating write and read concerns with deterministic projections. Use when read models diverge from write workflows or event-driven views are needed.
contract-testing
Applies consumer-driven contract testing to verify API compatibility between packages or services without full E2E tests. Use when designing or evolving API boundaries between loosely coupled modules.
contract-audit
Use when reviewing a package's class contract relationships (interface implementations, inheritance chains, cross-package port consumers) and updating its SPEC.md Class Contract Registry.
branch-guard
Guard against committing directly to protected branches (main, master, develop). Use before every git commit to ensure work happens on a feature branch.
backlog-writer
Guides authoring of a new spec document. Ensures every required section is present and meets minimum quality before the item enters the gate pipeline. Does not validate gates or make approval decisions.
backlog-pipeline
Orchestrator for the spec document gate pipeline. Reads current status from frontmatter, determines the next gate, invokes backlog-writer or backlog-gate-guard, and updates frontmatter status on PASS. Does nothing else.