Skills your AI team can install today
100 signed skills and professions from 3 vendors, with 55 videos and 123 articles. Read any page free; a free account downloads them.
Video Director
Script in, shot list out — the one artifact the camera, the screen recorder and the editor all read. Decides the package mode, names the engine on every row, quantizes generated-clip durations to the lengths the models actually produce, and lays out a timeline that accounts for transition overlap, so the video does not end in black. Cuts follow a seam rule in the renderer's own transition vocabulary. Every voiceover line is timed per beat against a measured speech rate for 7 languages; a beat that does not fit goes back to the writer with the number of words that do. Fills a @di-atomic/video-analyst template with no hand edits, splitting each section by its measured pace, and prints every departure the engines force with the template's sample size, handing the worst back for a decision. Five verifiers print PASS/FAIL with numbers before any render is paid for. 5 recipes + 14 registry items + 7 references. guidance-only — agents reach it via skill_read.
@di-atomic · v0.3.0 · 0 installs · 1 video · 2 articles
Top 10 skills
By installs across brandsTop 10 skills
By installs across brands
Recently updated
Newest versions first
Watch: skills in action
Demos, walkthroughs and setup guides
Professions
Whole roles, each a bundle of skills
Browse by category
29 categories
Browse by category
29 categories
Media
19 skills
Communication
17 skills
Data Collection
9 skills
Collections
Skills that work together, picked by OPVSCollections
Skills that work together, picked by OPVSAll skills
75 skills and 25 professionsOPVS Protocol
@opvs-ai · Protocol
OPVS federated agent messaging — the full mail surface. Register an address, send / receive / pair / discover across brand and server boundaries, plus the OPVS Mail layer: recipient-driven status state machine (ack/seen/working/resolved/declined), threaded conversations, and outbound webhook subscriptions for status changes + deliveries + replies. First-published at v1.1.0 with Initiative A envelope contract + Initiative B 4-layer content (references + research-grounded learnings citing Matrix, ActivityPub, AT Protocol, AutoGen, A2A, MCP, XMPP + registry playbooks). Supersedes @opvs-ai/opvs-messaging — 14 methods (superset of opvs-messaging's 8): the 8 core messaging ops plus updateStatus + thread + 4 webhook ops.
Skill▶ 14 imagesCode Index
@opvs-ai · Developer Tools
Brand-scoped code-index reads for repository orientation, directory trees, stored files and symbols, pre-write existence checks, imports, callers, and the tests a change can break, per-directory parse fidelity, and the project's index jobs.
Skill▶ 14 imagesAgentBoard
@opvs-ai · Board
Task management with AgentBoard — get/assign/progress tasks, manage boards and columns, post comments and results. Proxied through the dashboard gateway at /api/v1/board/*.
Skill▶ 14 imagesAgentMemory
@opvs-ai · Memory
Structured memory management — search past memories, create, correct and remove memories, and view memory statistics for AI agents. Proxied through the dashboard gateway at /api/v1/memory/*.
Skill▶ 14 imagesAgentDocs
@opvs-ai · Docs
Versioned documentation management with AgentDocs — list projects, read/create/update/delete pages, full-text search, and history/rollback. Proxied through the dashboard gateway at /api/v1/docs/*.
Skill▶ 14 imagesVoice Builder
@di-atomic · Foundation
Foundation skill — extract or build a brand voice profile (voice.md + about-me.md) from existing copy or a guided interview. Ships an installable registry of starter voices (4 trait variants x 4 ICP archetypes x 7 language profiles) so the agent installs-and-tunes instead of re-deriving. Deterministic analysis + multilingual transcreation + a compliance hard-gate for regulated industries (REACH/CLP/biocides). v0.3.0: GUIDANCE-ONLY (skills:[] + peer_dependencies) — the agent's own LLM builds the voice following SKILL.md; state persists via the upstream OPVS coordination skills (agentdocs / agentmemory) declared as peers. Multilingual EN/DE/HE/RU/RO/FR/ES.
Skill▶ 14 imagesCopy Engine
@di-atomic · Communication
Draft / edit / score / audit marketing copy for any surface (landing-page hero, pricing, cold-email, follow-up, ad headline, blog intro, video script). Voice-aware, product-context-aware, compliance-aware for regulated industries (REACH / CLP / biocides), multilingual EN/DE/HE/RU/RO/FR/ES. Backed by 43 metric-bearing real exemplars + 8 enforcement scripts, incl. the story-led founder's-epiphany register and timed video scripts written as a per-beat, per-language beat table. Guidance-only — no callable API; the agent's own LLM composes the copy following SKILL.md, modelling each draft on a real metric-bearing exemplar from registry/ and gated by scripts that print PASS/FAIL with numbers. State persists via the upstream OPVS Coordination skills (agentdocs / agentmemory / agentboard) declared as peers.
Media Skills
@spideriq · Data Collection
Browse and search a brand's SpiderMedia asset catalog (DAM) — the read-only discovery layer over every image, video, and doc already ingested across SeaweedFS, Cloudflare R2, and PeerTube. List/filter/search assets and read one asset's full metadata. Read-only and per-tenant; it reflects what the brand's workers and content pipeline already produced.
Gateway Skills
@spideriq · AI Gateway
SpiderGate V2 LLM gateway — OpenAI-compatible chat completions and embeddings backed by litellm.Router across 100+ providers, plus live event stream monitoring. Task-based routing aliases (spideriq/coding, spideriq/extraction, agent/embed-small), client-created aliases over your own provider keys, per-call observability through LangFuse traces, and SSE event stream for monitoring agent activity in real time. A setup skill walks the owner from no key to a connected agent, in chat.
AgentRooms
@opvs-ai · Communication
Slack-style room / channel communication — channels, direct messages, reactions, read receipts, and file attachments. Runs on the existing AgentBoard Rooms backend with no new infrastructure.
Skill▶ 14 imagesMedia Generator
@di-atomic · Media
The eyes and hands of the studio — guidance for generating brand-keyed images, videos, voiceovers, carousels, screenshots, and composed media. The agent composes the generation itself following SKILL.md: every model call SpiderGate-routed per-tenant (Mode A gate proxy / Mode B credential-pool), every asset SpiderMedia-persisted, every output verified by the bundled enforcement scripts. 8 use-case recipes + 33 evidence-bundled registry items + a client-grade verify-all gate. v1.3.0: converted to the guidance-only meta-package shape (skills:[] + peer_dependencies) — no phantom backend; agents reach it via skill_read.
Skill▶ 14 imagesICP Discovery
@di-atomic · Data Collection
Front-of-funnel targeting PLANNER (guidance-only). Product (url/text) in → a ranked set of ~25 diverse, downstream-complete ICPs out, each carrying both Google-Maps fields (SpiderMaps) and firmographic fields (SpiderPeople) + a 1-10 conversionLikelihood, plus a recommended SpiderFlows fetch plan per ICP. The agent's own LLM composes the ICPs by following SKILL.md + 10 sourced exemplar ICPs + 5 references + 7 learnings + 2 verifier scripts. Extracted from cognitoAI orbital_scan + icp_discovery + icp_research; multilingual + compliance-vocab aware. Output drops glue-free into outbound-engine + copy-engine.
Skill▶ 14 imagesSmartlead
@di-atomic · Communication
Launch and run Smartlead cold-email campaigns end-to-end — DNS pre-flight (SPF/DKIM/DMARC/MX), mailbox warmup + readiness gating, campaign create/ sequence/leads/schedule/start, real-time reply webhooks, and a 1:1 human follow-up loop via spidermail. Path-1 skill over the real Smartlead REST API (30-method contract, live-confirmed). The send hand outbound-engine delegates to; finishes cognitoAI's stubbed campaign export. Four enforcement scripts gate every destructive step with PASS/FAIL numbers.
OPVS Messaging
@opvs-ai · Protocol
OPVS federated agent messaging — register, send, receive, pair, and discover agents across the OPVS protocol network. Renamed from opvs-protocol at Wave 1 for clarity. Proxied through the dashboard gateway at /api/v1/opvs/*. v1.1.0 ships Initiative A envelope contract + Initiative B 4-layer content (references + research-grounded learnings citing Matrix, ActivityPub, AutoGen, A2A, MCP, XMPP + registry playbooks).
Skill▶ 14 imagesExplainer Illustrations
@di-atomic · Media
The planning brain between copy and render. Reads an article / case study / changelog / concept brief, extracts the cognitive anchors, and emits a structured shot list of 4–8 illustrations that EXPLAIN the topic (not decorate it) — one insight per image, the right composition pattern, one of 5 style packs (clean-line-art / whiteboard-sketch / isometric-tech / corporate-flat / editorial-illustration), with a render-mode hint and a compliance gate for regulated topics. Hands the prompts to @di-atomic/media-generator to render (SpiderGate-routed, reference-anchored, SpiderMedia-hosted). 6 use-case recipes + 39 evidence-bundled registry items + 5 PASS/FAIL enforcement scripts (incl. brand-fidelity). guidance-only skill (nested skills:[{id,schema}] with a no-methods schema + peer_dependencies) — agents reach it via skill_read.
Skill▶ 14 imagesUrl Utils
@di-atomic · Utility
URL hygiene for AI agents — parse, normalize, strip tracking, build GA4-correct UTM links, validate, canonicalize, infer platform, compare, expand short-links, and trace redirect chains. Guidance-only: the agent's own runtime executes the pure-logic patterns taught in SKILL.md, backed by 22 installable registry assets (UTM templates, per-platform tracking-param sets, CMS canonical rules) and 3 deterministic enforcement scripts (verify-url, strip-tracking, lint-utm).
Publish Skills
@spideriq · Content
AI-native website builder. One SpiderIQ skill (`spiderpublish`) that lets agents author, theme, and deploy entire client-facing sites end-to-end — pages, blog, docs, components, navigation, settings, media, custom domains, Liquid templates, programmatic-SEO directories, a safe two-phase edge deploy, and a live AI-agent embed (`kind='agent'` flow) — without leaving the conversation. A workspace can hold multiple projects (websites); every content call optionally targets one via a proj_… id. (Workspace/brand administration moved to @spideriq/workspace-skills.)
Skill▶ 14 imagesSection Designer
@di-atomic · Media
Design a webpage section, page hero, pricing block, feature grid, cta, faq, footer, testimonial in any of 150 named design-system languages (linear-app, stripe, vercel, apple, airbnb …) or 5 mood directions (Editorial / Brutalist / Glass / Soft-Neo / Terminal). Runs a mandatory script-driven critique (WCAG AA contrast, tap-target size, AI-slop blacklist, token-verbatim, heading hierarchy) before hand-off. Hands off composed markup + tokens + script receipt; the agent uses its own publishing skills (@spideriq/spiderpublish for CMS, @opvs-ai/agentdocs for archive) to ship. Adapted from nexu-io/open-design (Apache-2.0) — see ATTRIBUTION.md + LICENSE-upstream.
Skill▶ 14 imagesCRO Optimizer
@di-atomic · Data Collection
Close the CRO loop. After a fix ships, cro-optimizer reads the test outcome (PostHog/GA4), decides whether the result is REAL — running a mandatory significance gate + a causal-overreach gate PostHog doesn't — reverts confirmed losers via SpiderPublish, and writes the verified brand-prior back into cro-audit's baseline so the program learns instead of believing its own wins. GUIDANCE-ONLY: the agent's own LLM does the reasoning per SKILL.md, grounded in 18 test-outcome evidence cards + 6 references + 5 cycle recipes + 2 enforcement scripts; state persists via the upstream OPVS coordination skills declared as peers. It decides + routes — it does not measure (PostHog/GA4 do) or deploy (SpiderPublish does).
Skill▶ 14 imagesSales Pipeline
@di-atomic · Communication
The own-stack RevOps operator. Teaches an OPVS/OpenClaw agent to run the CRM the stack already owns — the AgentBoard deals/contacts/companies boards — through the full deal lifecycle (new lead → qualify → demo → proposal → negotiation → won/lost): compose a lead dossier from SpiderPeople/SpiderSite/IDAP + icp-discovery, trigger SpiderFlow automation on stage changes, progress stages only on logged buyer signal, run a Cardone-grade fast+persistent follow-up cadence, close + feed win-loss to agentmemory, and emit stage-velocity KPIs. Wraps NO third-party CRM (AgentBoard IS the CRM); ships NO backend. Backed by 81 evidence-bundled registry assets (incl. Belfort Straight-Line + Cardone closing/follow-up methods, re-expressed) + 23 learnings + 5 enforcement scripts. guidance-only meta-package: the agent's own LLM operates the CRM following SKILL.md; state + IO live in the declared peers.
Skill▶ 14 imagesRetention
@di-atomic · Communication
The keep-customers brain (guidance-only): branches on business model FIRST (agency | saas_b2b | b2c — three different playbooks; a discount saves a B2C buyer and gets an agency fired), scores churn risk on the model's own signals, picks the right save move, schedules the timed sequence, and hands the draft to its peers to send. Picks up where sales-pipeline ends. No callable API — the agent's own LLM runs the decision tree in SKILL.md, composing @di-atomic/outbound-engine (sequence) + smartlead (send) + copy-engine (copy) + voice-builder (register) + @spideriq/publish-skills (SpiderFlow timing) + the OPVS coordination peers (state/recall). Backed by 70 metric-bearing real exemplars + 21 learnings + 4 enforcement scripts. Compliance-aware (CA ARL single-offer + regulated-product claim limits).
Skill▶ 14 imagesOutbound Engine
@di-atomic · Communication
The outbound EMAIL brain (guidance-only) — mode-aware. Resolves the AUDIENCE first (does the recipient know you?): that picks the infrastructure, which dictates the format. cold-volume → smartlead (warmup + mailbox round-robin) · cold-agent → AgentBoard, one card = one lead, spidermail sends while smartlead only WARMS · broadcast → opt-in audiences via the house notification layer. Cold: pick 1 of 14 copywriting frameworks + tone + CTA + personalization, write the multi-touch ladder with per-email anti-repetition, 5 scripts gate it. Broadcast: author one issue against the house invariants behind a human [TEST]→approve gate. Provisions the boards (campaign · outreach · deals). No callable API — the agent's own LLM composes following SKILL.md, anchored on 47 registry items + 13 references + 12 recipes. It never sends: it delegates to @di-atomic/smartlead, @spideriq/spidermail and @spideriq/mcp-admin. GDPR/CAN-SPAM-aware.
Skill▶ 14 imagesHook Generator
@di-atomic · Media
Generate platform-tuned, voice-aware hooks for any surface — LinkedIn, X/Threads, Instagram captions, cold-email subject lines, regulated-product copy — and the first 3 seconds of a TikTok, Reel or Short, written as what is said, what is on screen and what the first frame shows. Guidance-only: the agent's own LLM composes hooks following SKILL.md, installs from 64 source-attributed exemplars in registry/ (11 of them short videos measured against their creator's own median), and gates output with six enforcement scripts (length / AI-slop + BPR/CLP compliance / structure diversity / build-diary launch headlines / video hook / coordination) — PASS/FAIL with numbers. Recipes route on occasion first, then platform. The opener primitive that feeds post-writer, section-designer, outbound-engine and copy-engine's video script. Multilingual DE/FR/ES/RU/RO gated pending native-speaker validation.
Skill▶ 14 imagesExecutor
@opvs-ai · Orchestration
Run a supported skill on an OPVS CRM task or board server-side. Executor fetches data, runs the skill, writes findings back and advances cards. The agent gets a job ID and checks progress without relaying bulk results through its conversation.