Suede AI Skills Directory · Top 100

Top 100 agent skills

find-skills from vercel-labs/skills is the most installed listed skill, with 4,257,002 installs recorded by skills.sh as of November 8, 2026. go-api-design from eduardo-sl/go-agent-skills has the highest Suede Skill Check score among third-party skills in the October 22, 2026 snapshot, at 95/100. Suede AI's own skills are not ranked.

The 100 most installed skills

Install counts come from skills.sh, which counts installs made with the skills CLI from anonymous telemetry, read on November 8, 2026. The directory measures no installs of its own. How the snapshot is taken. 2,869 of the 3,871 listed skills have a count there; the rest are not tracked by skills.sh. The sparkline is eight weeks of installs where skills.sh publishes it.

The 100 highest-scoring skills

Ranked by score, then by curated-list citations. Scores measure structural evidence from published files, as the rubric describes.

Rank	Skill	Publisher	Suede Skill Check	License	What it does
1	go-api-design	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	HTTP/REST API design for Go services: handlers, ServeMux routing, middleware, request validation, pagination, idempotency, health checks, error…
2	go-ci	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Sets up continuous integration for Go projects with GitHub Actions, caching, golangci-lint, test and coverage gates, vulnerability scanning, SAST, Dependabot, and build matrices.
3	go-cli	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Build command-line tools in Go: flag handling, subcommands, stdin/stdout discipline, exit codes, signal handling, and when Cobra/Viper earn their…
4	go-coding-standards	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Applies Go coding standards and style conventions from Effective Go and Go Code Review Comments, including import ordering, struct initialization, receivers, and formatting rules.
5	go-concurrency-review	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Reviews and implements safe Go concurrency patterns: goroutines, channels, sync primitives, context propagation, and lifecycle management, plus debugging race conditions and designing producer/consumer pipelines.
6	go-context	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Explains correct use of context.Context in Go, including propagation, cancellation, timeouts, deadlines, values, and common anti-patterns.
7	go-data-structures	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Correct use of Go's built-in data structures: slices (nil vs empty, append semantics, aliasing, preallocation), maps (comma-ok, sets, iteration…
8	go-database	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Database patterns for Go services: database/sql, connection management, transactions, migrations, query builders, and ORM usage (sqlc, GORM, ent)…
9	go-design-patterns	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Idiomatic Go design patterns: functional options, builder, factory, strategy, middleware chain, pub/sub, and other patterns adapted for Go's type…
10	go-documentation	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Go documentation conventions: godoc comments, package docs, testable Example functions, deprecation notices, doc links, and project docs (README…
11	go-error-handling	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Covers Go error handling patterns including wrapping, sentinel errors, custom error types, and the errors package, for implementing, designing, debugging, and reviewing error handling.
12	go-grpc	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	gRPC services in Go beyond the basics: proto design, status codes and error details, interceptors, deadlines, streaming, health checks, and graceful…
13	go-interface-design	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Guides Go interface design, including implicit interfaces, consumer-side definition, compliance verification, composition, accept-interfaces-return-structs, and common pitfalls, for designing, decoupling, and reviewing code.
14	go-modernize	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Modernize Go code to use current language features and standard library additions, Go 1.21 through 1.27: generics and generic methods, log/slog…
15	go-naming	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Applies Go naming conventions to packages, files, types, functions, methods, receivers, variables, constants, errors, acronyms, and tests, grounded in Effective Go.
16	go-observability	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Structured logging, distributed tracing, metrics, and health checks for Go services. Covers slog, OpenTelemetry, Prometheus, and observability best…
17	go-performance-review	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Detects performance anti-patterns in Go and applies optimizations covering allocations, benchmarks, pprof, GC and GOMEMLIMIT tuning, PGO, and HTTP client reuse.
18	go-refactoring	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Safe refactoring workflow for Go: behavior-preserving steps, compiler-checked renames, extracting packages, breaking circular dependencies, and…
19	go-troubleshooting	eduardo-sl eduardo-sl/go-agent-skills	95/100 · A	MIT	Diagnoses runtime problems in Go programs: panics, stack traces, deadlocks, goroutine leaks, memory leaks, OOM kills, and race reports, using delve and pprof.
20	linkedin-employee-advocacy	sergebulaev sergebulaev/linkedin-skills	94/100 · A	MIT	Guides setting up a LinkedIn employee advocacy program for marketing or sales teams, covering a 14-day launch playbook, brand governance, cadence benchmarks, and ROI.
21	linkedin-profile-optimizer	sergebulaev sergebulaev/linkedin-skills	94/100 · A	MIT	Audits and rewrites a LinkedIn profile end-to-end, covering headline, About section, Featured, banner, photo, Experience metrics, skills, custom URL, and recommendations.
22	let-fate-decide	Trail of Bits Official trailofbits/skills	94/100 · A	CC-BY-SA-4.0	Draws a Tarot spread to inject entropy into planning when prompts are vague or casually delegated, and interprets the spread to guide next steps.
23	fp-check	Trail of Bits Official trailofbits/skills	93/100 · A	CC-BY-SA-4.0	Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented…
24	pr-improver	Trail of Bits Official trailofbits/skills	93/100 · A	CC-BY-SA-4.0	Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the…
25	skill-improver	Trail of Bits Official trailofbits/skills	93/100 · A	CC-BY-SA-4.0	Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger…
26	go-build-release	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Build and release Go binaries that are reproducible and verifiable: version stamping, -trimpath builds, cross-compilation, GoReleaser, checksums…
27	go-defensive-coding	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Prevents panics and subtle runtime bugs in Go, covering typed-nil interfaces, slice aliasing, integer overflow, defer in loops, defensive copying, and zero-value design.
28	go-graphql	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Build GraphQL servers in Go with gqlgen: schema-first generation, resolver structure, the N+1 problem and dataloaders, complexity and depth limits…
29	go-semantic-tools	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Navigates and analyzes Go codebases semantically with gopls, go list for dependency graphs, and go doc for APIs rather than text search.
30	go-test-quality	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Guides Go testing for production code, including subtests, helpers, fixtures, golden files, httptest, testcontainers, fuzz testing, testing/synctest, mocking strategies, test isolation, and coverage analysis.
31	go-test-table-driven	eduardo-sl eduardo-sl/go-agent-skills	93/100 · A	MIT	Deep dive on table-driven tests in Go: when to use them, when to avoid them, struct design, subtest naming, advanced patterns like test matrices and…
32	generate-image	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	MIT	Generates or edits images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos…
33	hypogenic	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	MIT	Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. Use for the `hypogenic`…
34	matchms	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	Apache-2.0	Processes, cleans, compares, and searches tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral…
35	ncats-arax	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	MIT	Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph…
36	neurokit2	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	MIT	Builds and audits reproducible NeuroKit2 research workflows for physiological time-series preprocessing, event/interval analysis, multimodal…
37	opentrons-integration	K-Dense-AI K-Dense-AI/claude-scientific-skills	93/100 · A	MIT	Authors, reviews, migrates, simulates, and troubleshoots official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for…
38	onboarding	coreyhaines31 coreyhaines31/marketingskills	92/100 · A	MIT	When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions…
39	site-architecture	coreyhaines31 coreyhaines31/marketingskills	92/100 · A	MIT	When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the…
40	codeql	Trail of Bits Official trailofbits/skills	92/100 · A	CC-BY-SA-4.0	Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis, with run-all and important-only scan modes.
41	open-sourcing	Trail of Bits Official trailofbits/skills	92/100 · A	CC-BY-SA-4.0	This skill should be used when the user asks to "open source this project", "prepare this repository for public release", "make this repo public"…
42	semgrep	Trail of Bits Official trailofbits/skills	92/100 · A	CC-BY-SA-4.0	Runs a Semgrep security scan over a codebase, detecting languages, selecting rulesets, requiring approval of the plan, and merging output to SARIF.
43	sharp-edges	Trail of Bits Official trailofbits/skills	92/100 · A	CC-BY-SA-4.0	Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs…
44	git-commit	eduardo-sl eduardo-sl/go-agent-skills	92/100 · A	MIT	Structured git commit messages following Conventional Commits format for Go projects. Generates well-scoped, atomic commits with clear descriptions…
45	go-dependency-injection	eduardo-sl eduardo-sl/go-agent-skills	92/100 · A	MIT	Dependency injection in Go: constructor injection, wiring in main, avoiding global state, and when frameworks (wire, fx, dig) earn their complexity…
46	go-project-layout	eduardo-sl eduardo-sl/go-agent-skills	92/100 · A	MIT	Scaffold new Go projects and services: directory structure, cmd/ and internal/ conventions, when to use a flat layout, module naming, and main…
47	cloud-databases-onboarding	Google Official google/skills	92/100 · A	Apache-2.0	Guides users through discovering their database requirements, recommends a Google Cloud database based on a recommendation matrix, and assists in…
48	manual-tester	tronghieu tronghieu/agent-skills	92/100 · A	MIT	Plans and runs manual test sessions of the running app in five modes, including exploratory, smoke, and assessment, and writes manual test plans.
49	tao-run-deft-aoi-cosmos3	NVIDIA Official NVIDIA/skills	92/100 · A	Apache-2.0 AND CC-BY-4.0	Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly…
50	tao-run-deft-object-detection	NVIDIA Official NVIDIA/skills	92/100 · A	Apache-2.0	Runs the DEFT data augmentation loop for Grounding DINO object detection, with baseline inference, gap analysis, unique-neighbor mining, retraining, and source pool preparation.
51	docx	Anthropic Official anthropics/skills	91/100 · A	Proprietary	Creates, reads, edits, and manipulates Word documents and templates, including formatting, tables of contents, tracked changes, comments, images, and find-and-replace.
52	linkedin-comment-drafter	sergebulaev sergebulaev/linkedin-skills	91/100 · A	MIT	Drafts LinkedIn comments on another person's post from its URL, or reposts it with commentary, producing 1-3 variants in the user's voice.
53	linkedin-interviewer	sergebulaev sergebulaev/linkedin-skills	91/100 · A	MIT	Interviews the user to gather raw material for posts, building a Story Bank of roles, numbers, turning points, and positions.
54	linkedin-post-writer	sergebulaev sergebulaev/linkedin-skills	91/100 · A	MIT	Drafts a new LinkedIn post from scratch using one of 20 hook formulas and an angle library, picked by engagement goal.
55	linkedin-reply-handler	sergebulaev sergebulaev/linkedin-skills	91/100 · A	MIT	Drafts a reply to one LinkedIn comment from its URL, or to every comment worth answering on a post in one batch.
56	post-patch-validation	Trail of Bits Official trailofbits/skills	91/100 · A	CC-BY-SA-4.0	Validates security patches with reproducible baseline-versus-patched evidence, including original exploits, root-cause variants, behavior…
57	trailmark-finding-triage	Trail of Bits Official trailofbits/skills	91/100 · A	CC-BY-SA-4.0	Performs graph-assisted triage of a single security finding, SARIF result, or suspicious function using Trailmark reachability, taint, privilege-boundary, and blast-radius evidence.
58	agent-ready	mblode mblode/agent-skills	91/100 · A	MIT	Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents hitting 404s on guessed URLs.
59	agent-skills-creator	mblode mblode/agent-skills	91/100 · A	MIT	Creates and improves portable Agent Skills using a validator and routing scenarios, with evidence-based decisions to keep, cut, merge, or retire skills.
60	chat-history	mblode mblode/agent-skills	91/100 · A	MIT	Recovers decisions, previous fixes, and research from past AI conversations with source evidence, reading local Claude Code, Codex, Grok, and Cursor history.
61	ci-speedup	mblode mblode/agent-skills	91/100 · A	MIT	Cuts CI wait by measuring a pipeline's critical path from run timestamps, then splitting, sharding, and trimming setup, with a before and after ledger.
62	pr-babysitter	mblode mblode/agent-skills	91/100 · A	MIT	Monitors or repairs an open GitHub PR, handling CI failures, conflicts, review threads, and merge readiness while reporting state changes.
63	iso-standards-readiness	K-Dense-AI K-Dense-AI/claude-scientific-skills	91/100 · A	MIT	Prepares and structurally reviews readiness evidence for ISO 13485, ISO 14971, ISO/IEC 17025, and ISO 15189 standards, covering scope, controlled documents, and risk files.
64	treatment-plans	K-Dense-AI K-Dense-AI/claude-scientific-skills	91/100 · A	MIT	Formats and structurally validates treatment-plan documentation after licensed professionals have supplied and verified clinical decisions, without making clinical decisions itself.
65	tao-finetune-anomalygennext	NVIDIA Official NVIDIA/skills	91/100 · A	Apache-2.0	Validate a user AnomalyGenNext dataset and recipe, freeze its validation set, and prepare a canonical texture fine-tuning recipe. Use when…
66	tao-prepare-anomalygennext-inputs	NVIDIA Official NVIDIA/skills	91/100 · A	Apache-2.0	Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext. Use when turning box-level…
67	warp-compile-time-optimizer	NVIDIA Official NVIDIA/skills	91/100 · A	Apache-2.0	Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is…
68	diagnosing-superpowers	obra obra/superpowers	90/100 · A	MIT	Diagnoses why a superpowers session went wrong, such as repeated work or ignored plans, and helps build a bug report for maintainers.
69	aso	coreyhaines31 coreyhaines31/marketingskills	90/100 · A	MIT	Audits and optimizes App Store and Google Play listings to improve app visibility and store ranking.
70	co-marketing	coreyhaines31 coreyhaines31/marketingskills	90/100 · A	MIT	Finds co-marketing partners, plans joint campaigns, and brainstorms partnership opportunities, including partner marketing, integration marketing, and cross-promotion.
71	marketing-ideas	coreyhaines31 coreyhaines31/marketingskills	90/100 · A	MIT	When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing…
72	referrals	coreyhaines31 coreyhaines31/marketingskills	90/100 · A	MIT	When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user…
73	schema	coreyhaines31 coreyhaines31/marketingskills	90/100 · A	MIT	When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup,"…
74	vulnerability-triage-brocards	Trail of Bits Official trailofbits/skills	90/100 · A	CC-BY-SA-4.0	This skill should be used when the user asks to "triage a vulnerability report", "assess a CVE", "evaluate a bug bounty submission", "decide if a…
75	transcriptapi	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Provides YouTube access for transcripts, video and channel search, channel browsing, playlists, and within-channel search from pasted links, IDs, or handles.
76	youtube-api	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Retrieves YouTube data without Google API quotas or OAuth setup, including transcripts, video metadata, channel info, search results, and playlists.
77	youtube-channels	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Browses a YouTube channel from a handle or URL, listing recent uploads, searching within the channel, and resolving a handle to a channel ID.
78	youtube-data	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Retrieves structured YouTube data without Google API quotas or OAuth, including transcripts, video metadata, channel upload history, search results, and playlist contents.
79	youtube-full	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Provides YouTube access for transcripts, video and channel search, channel browsing, playlists, and within-channel search, for video summaries, quotes, translations, and topic research.
80	youtube-playlist	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Lists and browses the videos in a YouTube playlist from pasted links or IDs, and works through a playlist for transcripts or research.
81	youtube-search	ZeroPointRepo ZeroPointRepo/youtube-skills	90/100 · A	MIT	Finds YouTube videos and channels on any topic, including creators who cover a subject, tutorials, talks, and channel lookups by name or handle.
82	go-binary-size	eduardo-sl eduardo-sl/go-agent-skills	90/100 · A	MIT	Reduce the size of compiled Go binaries and container images: linker flags, inlining budget, CGO and build tags, embedded assets, dependency weight…
83	go-openapi	eduardo-sl eduardo-sl/go-agent-skills	90/100 · A	MIT	Spec-first REST development in Go with OpenAPI: generating server interfaces and clients with oapi-codegen, request validation middleware, RFC 9457…
84	go-skills-router	eduardo-sl eduardo-sl/go-agent-skills	90/100 · A	MIT	Index and routing table for this repository's Go skills: maps a task to the skill that owns it, names the secondary skills worth loading alongside…
85	chapter-writing	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Drafts story chapters and scenes as prose, including chapter outlines, next chapters, and continuing the story within a story project.
86	character-management	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Creates and updates characters in a story project, including profiles, relationships, family trees, timelines, arcs, and relationship graphs.
87	discovery-drafting	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks about "pantsing", "discovery write", "write without an outline", "discovery draft", "write into the…
88	genre-craft	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks about "mystery", "fair play", "clue", "red herring", "romance beats", "HEA", "thriller", "ticking…
89	interactive-fiction	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Plans and writes branching interactive fiction such as choose-your-own-adventure stories and gamebooks, including choice graphs, branch drafting, and where branches rejoin.
90	line-editing	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Edits and polishes prose at the line level, covering copyediting, proofreading, tightening sentences, grammar and punctuation checks, and dialogue punctuation.
91	plot-structure	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Builds story structure, including plot arcs, plot points, timelines, foreshadowing tracking, pacing, a sagging middle, act structure, and plot outlines.
92	premise-workshop	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Develops story premises by brainstorming ideas, testing whether an idea is strong enough, and workshopping loglines and story concepts.
93	reader-panel	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	Simulates a beta read with reader personas, showing how genre readers might react and whether they would keep reading before real beta readers.
94	scene-craft	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks to "plan a scene", "scene structure", "sequel scene", "dialogue subtext", "deep POV", "psychic…
95	series-continuity	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks to "write a sequel", "write a prequel", "start book two", "continue the series", "companion novel"…
96	story-init	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story"…
97	theme-craft	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks about "theme", "controlling idea", "thematic argument", "moral argument", "thematic arc", "flat arc"…
98	voice-style	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks to "create a style sheet", "style guide", "house style", "keep the voice consistent", "voice drift"…
99	worldbuilding	danjdewhurst danjdewhurst/story-skills	90/100 · A	MIT	This skill should be used when the user asks to "create a location", "add a location", "magic system", "political system", "build the world", "add…
100	agent-platform-deploy	Google Official google/skills	90/100 · A	Apache-2.0	Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cost, troubleshoots errors, and undeploys models.

Browse ranked shortlists by task for the best skill for a specific job.

Rising this week

The 100 listed skills with the most installs in the latest week skills.sh reports, among the 191 skills it keeps eight weeks of history for.

Explore Rising Skills with quality scores and source reports, or search from inside your agent.

Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills

Top 100 agent skills

The 100 most installed skills

The 100 highest-scoring skills

Rising this week

Find your next useful skill