Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
70,704 results · page 696 of 2,357
- View details
go-cli-errors-observabilitySkillMonitoring & ops
Design and review recoverable Go CLI errors, exit semantics, structured logging, debug modes, traces, profiles, redaction, and user-consented diagnostic bundles. Use when a CLI needs actionable failures, safe support evidence, production troubleshooting, or observability that does not corrupt comman
Ready to connect★ 1k
- View details
go-cli-process-controlSkillDev tools
Execute and supervise external programs safely from Go CLIs with explicit arguments, typed failure classification, working directories, environments, bounded streams, deadlock-safe pipes, contexts, timeouts, signals, platform adapters, descendant cleanup, runner seams, and lifecycle tests. Use when
Ready to connect★ 1k
- View details
go-cli-release-automationSkillMedia
Design, implement, and review secure Go CLI release automation with versioned tags, GoReleaser, GitHub Actions, checksums, signing, provenance, changelogs, Homebrew distribution, least-privilege credentials, verification, and recovery. Use when publishing CLI artifacts, configuring release CI, addin
Ready to connect★ 1k
- View details
go-cli-sql-storageSkillDatabases & data
Design, implement, test, and ship SQL-backed persistence for Go CLIs using database/sql, explicit pool ownership, bounded startup checks, embedded migrations, transaction boundaries, parameterized queries, adapter error mapping, Scanner and Valuer types, SQLite or server databases, and real-driver i
Ready to connect★ 1k
- View details
go-cli-terminal-experienceSkillMedia
Design and review adaptive Go CLI terminal experiences with explicit human, plain, and structured modes; per-stream TTY detection; color and accessibility controls; prompts; progress; secret input; cancellation; and broken-pipe handling. Use when a Go CLI must work safely for people, scripts, AI age
Ready to connect★ 1k
- View details
go-cli-testingSkillFiles & storage
Design, implement, stabilize, and review Go CLI tests across fresh command trees, pure logic, table-driven cases, streams, typed configuration, files, environment, function-backed HTTP fakes, repositories, subprocesses, capability profiles, race checks, and artifact behavior. Use when adding command
Ready to connect★ 1k
- View details
go-cobra-applicationsSkillDev tools
Build, refactor, test, and review Cobra-based Go applications with intentional command trees, fresh constructors, suggestions, typed boundaries, scoped flags, local or remote configuration, explicit precedence, safe live reload, context propagation, stable streams, shell completion, and generated do
Ready to connect★ 1k
- View details
go-concurrency-pipelinesSkillMedia
Design, implement, test, and review bounded in-process Go concurrency using goroutines, channels, iterators, mutexes, shared collections, WaitGroup, errgroup, backpressure, ordering, cancellation, and deterministic lifecycle checks. Use when building worker pools, streaming pipelines, concurrent bat
Ready to connect★ 1k
- View details
go-http-client-resilienceSkillMonitoring & ops
Design, implement, test, and review resilient Go HTTP client boundaries with context propagation, layered timeouts, transport reuse, request construction, authentication, status classification, bounded bodies, retry safety, backoff, rate limits, pagination, observability, and deterministic fakes. Us
Ready to connect★ 1k
- View details
go-http-server-applicationsSkillMedia
Design, build, test, and review production Go HTTP servers covering inbound adapters, modern ServeMux routing, middleware, strict bounded request decoding, response commitment, transparent ResponseWriter wrapping, server timeouts, health semantics, graceful shutdown, shared-state safety, and httptes
Ready to connect★ 1k
- View details
go-idiomatic-api-designSkillMedia
Design and review stable, idiomatic Go package APIs covering naming, exported declarations, embedding, receivers, typed-nil interfaces, generics, functional options, method sets, errors, wire contracts, compatibility, and examples. Use when creating a reusable Go package, reviewing its public surfac
Ready to connect★ 1k
- View details
go-language-correctnessSkillDocs & knowledge
Review and improve Go language-level correctness across numeric conversions, overflow, slices, maps, range loops, comparisons, strings, runes, UTF-8, defer evaluation, and version-dependent semantics. Use when reviewing agent-generated Go, debugging surprising mutation or memory retention, validatin
Ready to connect★ 1k
- View details
go-performance-testingSkillDocs & knowledge
Design, run, compare, and interpret Go performance evidence using benchmarks, B.Loop, benchstat, pprof, traces, escape analysis, cache locality, false sharing, sync.Pool, GC limits, container CPU behavior, and PGO. Use when investigating Go latency, throughput, CPU, memory, allocations, contention,
Ready to connect★ 1k
- View details
goal-convergenceSkillAI & models
Goal-oriented autonomous loop with external completion oracle. Keeps iterating until verifiable stopping conditions are met, checked by a separate model.
Ready to connect★ 1k
- View details
goal-filterSkillMonitoring & ops
Gives your agent a goal claude skill that scores marketing ideas ON GOAL, PARTIAL, or OFF against one primary goal.
Ready to connect★ 1k
- View details
goal-progressSkillDev tools
Explicitly attach verified checklist progress to one native Codex Goal. Use only when the user explicitly selects Goal Progress or invokes $codex-goal-progress:goal-progress. Do not use for an ordinary Goal, a status question, or update_plan.
Ready to connect★ 1k
- View details
governance-statusSkillDev tools
Check active governance policies and recent activity summary
Ready to connect★ 1k
- View details
governance-syncSkillAI & models
Audit or explicitly synchronize Claude and Codex repository governance without overwriting conflicts. Triggers: governance sync, CLAUDE.md, AGENTS.md, instruction mirror.
Ready to connect★ 1k
- View details
governed-executionSkillDev tools
Use when executing an accepted HOTL workflow through the best available host or fallback driver.
Ready to connect★ 1k
- View details
graph-engineerSkillDev tools
As the Graph Engineer on the Team Skills Platform, responsible for code graph construction, dependency analysis, impact assessment, architecture visualization, and refactoring safety evaluation, providing structured evidence for architecture decisions and code changes. Use when the user explicitly n
Ready to connect★ 1k
- View details
graphifySkillDev tools
Integrate Graphify as an optional knowledge-graph capability for brownfield structure scanning, dependency path analysis, and architecture Q&A. It does not replace the `/team-*` main chain; outputs uniformly fall back to handoff and artifacts evidence.
Ready to connect★ 1k
- View details
graphify-integrationSkillProductivity
Optional knowledge-graph integration. When `graphify-out/graph.json` is present, architect/researcher/reviewer/task-builder agents can query symbol-level dependencies (IMPORTS, CALLS, EXTENDS, IMPLEMENTS, DEPENDS_ON) instead of grepping. Degrades gracefully when the graph is missing. Trigger phrases
Ready to connect★ 1k
- View details
graymatterSkillDocs & knowledge
Lets your agent keep durable memory across sessions and inspect your organization's data models and API schemas.
★ 1k
- View details
graymatter-analyticsSkillDatabases & data
Use when GrayMatter should support analytics work by retrieving durable context, checking retrieval receipts, loading the live api-docs schema, and helping create user/workspace-specific semantic layers without assuming tenant business objects exist.
Ready to connect★ 1k
- View details
graymatter-contextSkillDocs & knowledge
Compile bounded, task-specific GrayMatter context and inspect authorized procedures or retrieval receipts. Use when a task needs grounded prior context, a reusable method, or an explanation of why particular memory was selected.
Ready to connect★ 1k
- View details
graymatter-memorySkillSearch
Search, retrieve, save, revise, and forget secure durable GrayMatter memory. Use when a task may depend on prior decisions, preferences, todos, artifacts, or long-lived context, or when the user asks to remember, update, or forget information.
Ready to connect★ 1k
- View details
grillSkillMedia
Use when the user wants a plan, design, or PRD stress-tested before any build — relentlessly interrogates one decision at a time, grounds every question in the codebase, hunts contradictions against the domain language and the code, and challenges the load-bearing assumptions. Triggered by "grill me
Ready to connect★ 1k
- View details
growth-engineeringSkillFiles & storage
Guides your agent to design growth strategies like referral programs, viral loops, and launch playbooks with models.
Ready to connect★ 1k
- View details
growth-planSkillDocs & knowledge
Lets your agent write a 20-30 page growth plan with forecasts, budget splits, and a 30/60/90 timeline.
Ready to connect★ 1k
- View details
gsc-ai-performanceSkillSearch
Analyzes a Google Search Console AI Performance Report CSV to show how your pages appear in AI search results.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
68,574 of the 70,704 skills listed here can be served through Ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.