Loading...
Loading...
Found 505 Skills
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers.
FORGE SM Agent — Decomposes requirements into stories with test specs. Usage: /forge-stories
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.
Brainstorm a raw product idea with the user — explore angles, users, value props, features, monetization — and produce a structured brainstorm note. Use when the user wants to explore or flesh out an idea without committing to evaluation or building: "давай побрейнштормим", "помозгуем над идеей", "разберём идею", "покрутим идею", "brainstorm with me", "explore this idea", "help me think through an idea", "flesh out this idea". Not for economic verdicts, specs, or implementation — that is idea-forge.
Set up the local specs, work, and .p2p filesystem conventions, with optional tracker, triage labels, and domain-doc pointers.
Hunt shadow / zombie / undocumented API surface (OWASP API9 Improper Inventory Management) — enumerate the full API version history (v1/v2/beta/legacy paths, header- and subdomain-based versioning), pull and diff every reachable OpenAPI/Swagger spec (including ones only findable via the Wayback Machine), and behaviorally diff old vs. current versions for auth/rate-limit/validation regressions rather than just response-shape differences. Distinct from hunt-api-misconfig, which owns exploitation once you have a spec or endpoint (mass assignment, JWT, OData, Swagger-chain attacks); distinct from hunt-subdomain, which owns host-level discovery. This skill owns the version-inventory and behavioral-diff workflow itself. Use when the target has versioned API paths, multiple specs, a changelog referencing deprecated endpoints, or a mobile app whose hardcoded backend calls look older than the current web app's.
The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the "Canva look." Use when someone wants to design in Canva, make social graphics, set up a Brand Kit, batch-produce graphics (Bulk Create), resize one design for every platform (Magic Resize), use Canva's AI (Magic Studio), or asks why their posts look like a template. Uses the SCALE framework. Reads brand-profile + design-and-templates + voice-builder first. The agent specs, and creates designs directly where the Canva MCP/Connect APIs are connected; the human approves every visual; the export publishes via WoopSocial. Never strips watermarks, impersonates another brand, or uses unpermitted likeness; AI-disclosure + accessibility floor apply. Distinct from design-and-templates (the brand system this executes), image-prompt + the image tools (dedicated generation), ai-image-editing (the edit router), and capcut/descript (video editing).
Find the perfect gaming monitor on Newegg by asking the user about their needs and returning the top matching monitors with parsed specs (size, resolution, refresh rate, panel type, response time) and direct purchase links. Use this skill whenever users want help choosing or finding a gaming monitor — even if they don't mention Newegg by name. Always trigger on phrases like: "help me find a gaming monitor", "what monitor should I buy for gaming", "recommend a 144Hz/240Hz monitor", "best monitor for FPS games", "I need a monitor under $X", "OLED gaming monitor recommendation", "curved ultrawide monitor for gaming", "我想买个电竞显示器", "推荐一个游戏显示器", "帮我找显示器", "144Hz显示器推荐", or any question about choosing or comparing gaming monitors for purchase. This skill handles the full flow: gathering requirements → searching Newegg → parsing specs → showing ranked results with clickable buy links.
This skill should be used when the user's request or requirement is ambiguous and needs iterative questioning to become actionable. Trigger on "clarify requirements", "refine requirements", "요구사항 명확히", "요구사항 정리", "뭘 원하는 건지", "make this clearer", "spec this out", "scope this", "/clarify". Turns vague inputs into concrete specs. For strategy blind spots use unknown; for content-vs-form reframing use metamedium.
The Instagram SEO / keyword-search skill -- IG-specific search depth, distinct from the cross-cutting social-seo. Use when someone wants an Instagram post/Reel to rank in search, needs IG keyword research, or wants a searchable caption/profile. Instagram shifted from hashtag-based discovery to keyword-based search (hashtags deprioritized to 3-5 topic labels). Search runs semantic analysis -> metadata matching -> visual recognition (checks alt text + visual MATCH the caption). Uses the MATCH framework. Reads brand-profile + the post's topic first. The agent researches the keyword cluster (never fabricates volume), writes the search-first caption (primary keyword first, no stuffing), specs on-screen text + spoken keyword, and advises profile fields/alt text. WoopSocial publishes the caption; profile fields, alt text, and IG Search/Insights stay native. No keyword stuffing; caption must match the visual. Distinct from social-seo, pinterest-seo, and hashtag-strategy.
Scope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system mapping, goals/non-goals, a Decision Log for one-way-door choices, a live Open Questions backlog, and a real migration + test plan. Read when asked to write a spec, scope this feature, turn this proposal into a spec, plan the implementation, or break this into tasks. Do NOT fire on frame a proposal or write the PRD (sibling frame-a-proposal — a PRD frames a change before it is accepted; this skill starts once one is), record a decision or write the ADR (record-a-decision), write a postmortem (write-a-postmortem), or review this design (review-a-design) — those are separate skills. Complements the platform open-knowledge skill; does not replace it.
Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools over HTTP (POST /mcp). Use when migrating OpenAPI 2.0 specs to OpenAPI 3.x for MCP, annotating specs with x-google-api-management.mcp and x-google-mcp-tool, securing tools/list with JWTs or API keys, connecting Google ADK (McpToolset) or Apigee API hub and Agent Registry, or troubleshooting MCP JSON-RPC errors (-32601, -32602, -32000). Do not use for Apigee X proxy bundles, outbound LLM model routing, or GKE Gateway API.