Seryozh
- 15 skills
- 0 followers
- 3 hours ago last updated
- ▌ Linkedin Control · seryozh bundleRead and operate LinkedIn from an agent by driving the user's own logged-in browser, because LinkedIn cannot be fetched or scraped from outside a session. Use when a task needs a LinkedIn profile, company page, post, comment thread, activity history, connection list, invitation queue, inbox, search result, or Sales Navigator record; when drafting a connection note, DM, comment, or post that a human will send; or when a LinkedIn selector, click, or extraction just broke. Covers the shadow-DOM layout, the durable addressing attributes, the wrong-person targeting hazard, the rate and policy limits, and the failure catalogue. Do not use for sending at scale or for bulk data collection.
- ▌ Department Making · seryozh bundleDesign, simplify, and validate recurring or durable agent-department systems for a real job, business function, project, or repeated workflow. Use when someone asks to create an agent organization, decide between skills, subagents, chats, shared state, and automations, define stable handoffs and authority, or repair an overcomplicated multi-agent design. Do not use merely to coordinate one active task or cast the five Prism roles; use prism-team for that. This skill designs the operating system and pilot, not the current run's completion claim.
- ▌ Blue Exact Builder · seryozh bundleConvert an accepted specification into a deterministic working artifact and prove it on the judged surface. Use when requirements and acceptance criteria are settled and an agent must implement code, documents, data, configurations, designs, or other deliverables exactly; repair a failed build without redesigning it; or replace completion claims with reproducible verification. Do not use while material product, policy, or creative direction is unresolved.
- ▌ Red Adversarial QA · seryozh bundlePerform strict, read-only adversarial QA of artifacts and their completion claims. Use after a build, migration, analysis, document, dataset, workflow, or other deliverable needs an independent gate; when tests may be shallow; when a claimed PASS must be falsified before release; or when exact failure evidence and the smallest repair path are required. Never use this role to edit the target or silently repair it.
- ▌ Violet Meta Thinking · seryozh bundleStep one level above the immediate task to check whether even perfect execution would achieve the real outcome, account for the people, incentives, authority, hidden constraints, and immediate downstream effects around it, and return the smallest concrete correction. Use when work may be locally correct but globally wrong; when a consequential plan, decision, message, filing, build, or analysis risks optimizing a proxy; when broader organizational, personal, legal, financial, creative, or operational context could change the right move; or when the user asks for meta-thinking. Do not invoke for routine low-stakes work whose outcome and frame are already clear.
- ▌ Design The Conversation · seryozh bundleDesign where a message leads before writing it. Use before sending or drafting any outreach, cold email, follow-up, LinkedIn note, text, or reply whose purpose is to move a real relationship forward: map the destination, write the closing turn first, work backwards, then branch-test every question so that each plausible answer has a next move. Use whenever a draft ends in a question and nobody has said what the answer unlocks. Do not use for a message that only has to inform, confirm, or thank.
- ▌ Green Systems Architect · seryozh bundleStructure messy systems, requirements, operations, or research evidence into a coherent, evidence-grounded blueprint with explicit boundaries, components, interfaces, dependencies, failure traces, and acceptance checks. Use when an agent must design or repair a system model, research architecture, process, specification, responsibility map, evidence map, or multi-part plan whose relationships matter. Do not invoke for simple work that is already clear and can be completed directly without added structure.
- ▌ Bettercontact Enrichment · seryozh bundleFind and qualify work-email candidates with BetterContact's asynchronous API while controlling credits, preserving row identity, and separating deliverable results from catch-all or uncertain records. Use when a user asks to check a BetterContact balance, test the service, enrich a confirmed person-and-company list, run a bounded benchmark, or prepare evidence-safe candidates for later review. Requires explicit approval before any credit-consuming request and never sends outreach or writes to a CRM.
- ▌ Yellow Creative Explorer · seryozh bundleOpen a creative problem into genuinely distinct, audience-aware directions, test each direction against the factual floor and real experience, recommend the strongest path, and lock a committed brief once a direction is chosen. Use for visual, editorial, product, messaging, campaign, naming, experience, format, or strategy work that needs lateral exploration before precise execution, or when the current solution space feels generic or stuck. Do not invoke when a clear approved specification only needs exact implementation.
- ▌ Humanizer · seryozh bundleMake any outgoing text read like a person typed it, not an AI. Use BEFORE showing or sending anything a human will read as writing - emails, texts, LinkedIn messages, chat replies to teammates, bios and profile copy, job application answers, documents, scripts, web copy - and whenever asked to humanize, de-AI, or fix robotic text. Not needed for code, data, or plain factual answers inside this conversation.
- ▌ Prism Team · seryozh bundleCast, fuse, and coordinate the smallest useful combination of five reusable thinking roles: Green for systems architecture, Yellow for creative exploration, Blue for exact building, Red for adversarial QA, and Violet for meta-thinking. Use to route one active task when different temperaments, color cooperation, a multi-color subagent, separated builder and critic passes, or visible bounded handoffs would materially improve the result; or when the user asks for the colored agents, Prism Team, color combinations, a role deck, a card game, or agents with personalities. This skill owns active-run casting and role handoffs. It does not redefine completion, which belongs to own-the-outcome, or design a durable organization, which belongs to department-making. Do not use for a clear low-stakes task one agent can finish reliably.
- ▌ Discuss First · seryozh bundleTalk one decision through in short, natural turns before building. Use when the user says to discuss or plan first, asks the agent to wait or keep it short, says they do not understand, asks a question instead of giving a work order, or is still shaping a direction that needs their approval. Do not use after the user has clearly approved a build or asked for a concrete artifact.
- ▌ Show The Work · seryozh bundleRecover, verify, and turn observable work into a clear human progress story, proof-led explainer, handoff page, or partner-ready research note. Use when a user asks to show what was done, explain how a result was reached, continue a prior session, summarize progress with an honest percentage, build a page someone can forward or defend on a call, or keep updates in the concise factual voice of verified fact plus next action. This skill never exposes hidden chain-of-thought and never sends or publishes without explicit approval.
- ▌ Own The Outcome · seryozh bundleTake responsibility for the user's real-world result instead of producing a plausible answer. Clarify the real outcome, choose rigor in proportion to risk, verify on the surface the user will judge, attack the final result, and report what remains unproven. Use for consequential or multi-step research, documents, data, plans, campaigns, builds, audits, or migrations; whenever the result must survive criticism; and whenever the user asks for thoroughness in words such as "use own the outcome", "отвечай за результат", "сделай досконально", "тщательно", "дотошно", "разберись как следует", "make sure it is actually right", or "be thorough". This skill owns the definition and final evidence of done. It does not design durable departments or route a colored role team. Scale rigor to stakes; do not add ceremony to small routine chores.
- ▌ Layout Forensics · seryozh bundleAudit and rebuild a web layout from the live rendered page instead of from a screenshot. Measures real geometry, type, spacing, colour contrast, tap targets and reading load out of the browser, computes what is usually left to taste (visual weight per band, first-glance saliency, alignment lanes, spacing-scale conformance), writes acceptance criteria, builds the proposed version as real HTML in the site's own cascade, then re-measures and returns PASS or FAIL per criterion. Use when someone asks what is wrong with a page or section, why a layout feels cluttered, heavy, empty or confusing, where the eye goes, how a section should be rearranged, or when an agent is about to rebuild a section and needs a spec it can be held to. Works from a screenshot alone in a reduced mode, and says so.