REQUIRED before searching for any Polyspace option documentation page. Use when the user asks about a Polyspace option (-c, -target, -sources, -boolean-types, -misra3, etc.), wants to find an option's doc page, or asks 'what does this option do'. This skill contains the only reliable method to locate option reference…
Adds Polyspace justification annotations to C/C++ source code. Use when the user asks to "justify this finding", "add a Polyspace annotation", "mark as false positive", "suppress finding", or wants to add justification comments to Polyspace findings.
A guide for securely connecting to amoCRM, a customer-relationship system, through its API. It covers OAuth sign-in, account structure, and checking leads by source, time, status, owner, and external link.
A workflow for researching commercial demand for a product or service through Wordstat, a Yandex tool that reports search activity. It records the collected queries and classifies them as relevant demand, noise, or uncertain.
A reference guide to Yandex Wordstat API v2, the Yandex service used to study what people search for. It documents requests, authentication, quotas, regions, devices, and search-demand trends.
Use when creating, modifying, auditing, or debugging Metin2 client UI code (uiscript dicts, root ui.py classes, locale entries) — user says "/m2ui", "create UI", "make a window", "add button to", provides a UI screenshot to replicate, asks to "check UI for bugs" / "diagnose", or reports a visibly broken window…
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
Operate a dedicated Codex session-management task: show backup progress and inventories, configure retention, safely back up or clean verified local Codex sessions, restore sessions, exchange cross-device evidence, or migrate legacy archives. Do not use for ordinary project-file backups or ChatGPT web conversations.
Use when a task may depend on prior user preferences, project conventions, architectural rules, workflow decisions, previous Codex work, full-text memory search, durable rule saving, or skill drafting/updating through Hermes Codex Plugin, especially to reduce Codex token spend by recalling minimal relevant context.
Use when the user asks Codex to consult Claude Code, run a Claude advisor pass, get a Claude adversarial review, check a plan or diff with Claude, ask Claude to do a prepared coding, exploration, verifier, scout, or rescue task, inspect Claude advisor job status, fetch a Claude result, or cancel a Claude advisor job.…
Score an existing React + Tailwind site against the anti-slop checklist and produce DESIGN-AUDIT.md with evidence. Use when the user says their site "looks AI-generated", "looks generic", "feels off", asks "why is my site ugly", or wants a design audit/score before improving it. Read-only — never edits source.
Interview the user about taste, brand, and audience, then synthesize a custom design lane (LANE.md + tokens) for their React + Tailwind site. Use when the user wants a design direction, says "make it look premium/professional/not AI-generated", or after /unslop:audit before any re-theming. No code changes — output is…
Systematically apply an approved design lane (LANE.md) to a React + Tailwind site — tokens first, then section-by-section, with build + screenshot verification after every pass. Use when the user says "retheme", "apply the lane", "make it match the design", or after /unslop:interview produced an approved LANE.md.
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
Audit this codebase for wasteful LLM API spend and hand back a concrete, honest fix plan — missing prompt caching, uncapped retries, prompt bloat, no batching, overpowered models. Describes technical waste and published provider rates only; never fabricates a dollar figure. Trigger on requests like "audit my LLM…