Claude Skills by lev-os

Use when reconciling chezmoi local-vs-remote drift, reviewing pending machine-state changes, or performing safe remote-first dotfiles sync across machines.

Use when a long brainstorm or brain dump needs deep capture, prior-art routing, and durable next states.

Use when designing or improving Lev eval packs, inline FlowMind evaluation policy, owner-local runtime scenarios, assurance sizing, adversarial field probes, or promotion gates.

Use when running execution-ready task slices, dispatching verified `lev exec` flows, or reviewing implementation work in the Exec lane.

Use when the user needs to catch up on a conversation or recent tasks, understand unfamiliar project terms, surface decisions, or receive a clear goal closeout.

Use macOS Terminal.app Full Disk Access as a proxy to copy TCC-protected files such as Messages/chat.db or AddressBook into a readable location for agent workflows.

Authors FlowMind .flow.yaml graphs with validate, fix, promote, and measure steps. Use when user writes or audits flows, fixes violations, or advances lifecycle quality.

Convert an explicit user request into a Codex goal and pass its chosen coder, Lev, LazyCodex, SDD, or Fable execution flags to $coder.

Publishes static folders or files to instant shareable here.now URLs. Use when the user wants publish, host, deploy, share a link, or put HTML or assets on the web.

Config-driven workshop intake for URLs, repos, media, PDFs, and skill packages. Use when user wants intake, download, or external content analyzed with project playbooks, ending with a brief, routed recommendation, validation plan, and action dashboard.

Use when guiding decision interviews that produce a design artifact in .lev/pm/designs before proposal or implementation planning.

Run the Lev guard rulebook (dna/gates/guard-rulebook.yaml). `daily` runs the guards grep can be trusted with; `weekly` has an agent check every judgment-based rule with evidence and writes a receipt. Use on a schedule or before landing a large branch.

Compile captured or designed intent into a source-faithful Lev plan, deepen or review an existing plan, and manage its lifecycle under `.lev/pm/plans/`. Use for human runbooks, migrations, architecture plans, multi-slice roadmaps, plan review, or plan state transitions; route SDLC packets to propose and non-coding work to its domain executor.

Use when routing intent into Lev lifecycle work, clarifying an uncertain next step, or invoking and diagnosing the Lev CLI and runtime.

Typed tick loops with FlowMind validation and parallel tick dispatch. Use when running /ll, recurring pipelines, quality loops, or autonomous scheduler ticks.

Compose evidence-backed sales pages, lessons, technical explainers, feedback surfaces, dashboards, and document collections as one deterministic RenderSpec component graph, then render, QA, publish, or attach the HTML.

Use when coordinating a multi-step goal across agents, skills, Lev lifecycle routes, scheduling, research, implementation, review, or human decisions.

Use when the user asks to prove, spike, prototype, POC, validate a production path, compare landing zones, or decide whether an idea should move to propose, monitor, reject, or archive.

Single-model forced-framing diversity with inline synthesis. Turn-manager protocol: unfold → synthesize → reduce → conclude. Use for decision synthesis and strategic alignment. Cheaper than /cdo, richer than /think.

Use when you need an evidence-first provenance report from `cass`, repo docs, `.lev`, `~/.agents/diagrams`, `qmd`, or Grep/Glob tools.

Use when compiling aligned simple intent or a source-faithful Lev plan into a reviewable slice map or one execution-ready Lev task. It does not create or repair broad plans.

Use when current external facts, source-backed comparisons, investigations, or recent community evidence are needed.

Read-only dashboard projecting lifecycle triggers into entities and next actions. Use mid-flow via /sitrep or /status.

Use when creating skills, converting docs/repos/PDFs to skills, installing external skills, auditing skill security, or merging skills

Filesystem-first local skill lookup and ranking from lev-skills inventory. Use when work, lev, or hubs need to discover installed skills without low-quality fallbacks.

Checkpoint sync for the current checkout and recursive dirty submodules. In feature branches, paired main checkout and feature->main landing require explicit --main.

docs (living docs people share, comment on and edit; use only when the user asks for one: names a doc, document, page, memo, spec, PRD, runbook or write-up, asks for somewhere to share or keep editing something, or says yes to your doc offer; a plan, comparison, summary or notes asked in chat stays in chat (at most a one-line doc offer); a report, status update, recap or "something I can send them" with no form named → ask first: reply, doc or file?; tabs hold tables and live charts too; a pa...

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, find-and-replace in Word files, working with tracked c...

Complete Go-To-Market strategy suite combining 5 frameworks from Maja Voje's GTM Strategist. Covers: Power Hour (GTM 1-pager hypothesis), ICP Validation (empirical customer profiling, beachhead market selection), Positioning (competitive analysis, messaging architecture, strategic narrative), Pricing (willingness-to-pay testing, pricing models, offer design), and Motion (PLG/SLG/CLG/content/partnership selection, 90-day sprint planning). Use when starting a product launch, validating GTM assu...

Config-driven content intake system for GitHub repos, videos, articles, PDFs, and skill packages. Acquires content, analyzes against project playbooks, and recommends disposition (integrate/extract/monitor/pass/vendor). Triggers on: intake, download, analyze this url, check out this repo, review this video, evaluate content, install skill, skill://

Use when any research, search, or information gathering is needed. Thin router over the Lev timetravel research engine — handles strategy selection (quick/full/deep/max/social/academic), adapter parallelism, and synthesis. Triggers on: research, search, investigate, deep dive, look up, find information, analyze, compare, academic search, social search, comprehensive research.

CMS meta-layer for Kingly AI OS — manages the Notion-native type system. Provides four foundational databases (ContentTypes, FieldDefinitions, IntentRegistry, FlowMindTemplates) that make all schemas, intents, and workflow templates discoverable at runtime. Load this skill when: creating or modifying content type definitions, registering new intents, importing skill schemas into Notion, exporting type definitions to YAML, compiling FlowMind templates into executable RunPlans, or bootstrapping...

Apply the 12 rules of product craft to build products users love and return to. Covers user personas, UX principles, brand foundation, information architecture, design systems, state design, onboarding, performance, micro-interactions, and activation events. Use when auditing product quality, designing UX, planning onboarding, or defining activation metrics.

Investigative research engine combining OSINT tradecraft with UX research principles. Deploys an interactive dashboard with iterative deepening rounds, knowledge graph visualization, domain-based research routing, and Sherlock-style deduction chains. Use when asked to research, investigate, analyze, deep-dive, build a dossier, do OSINT, profile a person/company/topic, or conduct multi-round research. Triggers: 'research', 'investigate', 'deep dive', 'OSINT', 'dossier', 'profile', 'intelligenc...

Local skills runtime lookup — the portal for finding and discovering all available skills. Uses `~/.agents/lev-skills.sh` + `~/.agents/skills-inventory.jsonl` as source of truth. Triggers on: skill discovery, find skills, what skills do I have, discover skills, list skills, skill lookup, available skills, search skills, skill inventory.

Browser-only social signal extraction worker for the Lev graph. Extracts themes, hooks, and positioning signals from LinkedIn, X, and Substack. Produces strict JSON output conforming to SocialSignalExtractionSchema. All outputs must be funneled back through the Lev Graph Operator (Notion CMS write + Event Log emission). Never writes to Notion directly — returns JSON for the parent skill to persist. Use when scanning social channels for content signals, monitoring target creators, researching ...

Route GitHub gh, Notion ntn, Slack CLI/API, Exa research, AgentMail, and Herdr/OMP terminal-agent work through one self-contained integration router. Use for GitHub, Notion, Slack, Exa, AgentMail, Herdr, OMP, ntn, slack, gh, mailbox, or terminal-agent coordination.

Run one neutral prompt independently across every discovered model from selected CLI providers, then compare all answers and failures. Use for naming, short judgment questions, sanity checks, and cross-model test matrices; never use it to execute coding work.

[OMX] Adversarial dynamic e2e QA workflow - generate hostile scenarios, test, verify, fix, report, and clean up

Routes UX/product design runs, user research/persona synthesis, wireframes, flows, IA, pencil visuals, and agentic CLI UX. Infers full run vs research vs CDO-backed persona mode from context, asking one question only when ambiguous.

Use when routing tracked work through lifecycle lanes, resolving workstream context, or deciding which lifecycle skill owns the next entity transition.

Use when attaching a session to a workstream, or scanning, finding, resuming, merging, branching, or untangling Lev workstreams.