Claude Skills by nexuslinkproductions

Use before claiming a test/validator/gate result is commit-linked, on origin/main, on a specific sha, green-on-HEAD, or pre-existing — to avoid attributing worktree-derived results to a commit without verifying all inputs. Requires disposable-fresh worktree for clean-checkout reruns (never checkout over an existing path).

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Native token efficiency mode that compresses output, minimizes verbosity, and enables caveman-style communication. Use when the user wants to save tokens, reduce output length, work in minimal-verbosity mode, or mentions token budgets or caveman mode.

The DECISION LENS for trading peers — recalls the CURRENT signal snapshot per market from the live ledger and renders it through the sim arsenal off ONE call: quantum factor-circuit order-optimal sequencing + decision-sim CVaR-robust sizing, sized against the MEASURED per-factor edge (from the edge-audit), correlation-aware. Emits an actionable call per market {side, sizePct, confidence, sequence}. Flat/zero-size when there is no measured edge after cost — the honest default. Sibling of trade...

The EDGE LENS for trading peers — recalls EVERY factor/indicator running from the live forecast ledger (no enumeration) and renders the whole pile through the edge arsenal off ONE call: multi-horizon scoring (the ladder) + deflated Sharpe (overfit) + Benjamini-Hochberg FDR (multiple-testing across the fleet) + spread-bounce + maker-fee falsification, then ranks only what survives ALL of it. Use when a peer must answer "does ANY running factor have real, overfit-corrected, multiple-testing-cor...

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Resolves and loads task-relevant skills from the canonical local skill root after the workspace authority chain is loaded. Use when the user wants to discover available skills, load skill capabilities, or needs to know what skills are available for a task.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

VideoDB integration skill — stub. Populate with VideoDB API usage, query patterns, and YURI integration notes when VideoDB is actively used.

Engineering visual analysis of the Yuri OS architecture graph. Reads _SYSTEM/yuri-graph-state.json and reports structural insights, optimization opportunities, dead-ends, missing returns, duplicate functionality, and merge candidates. Use when reviewing system architecture, planning refactors, or assessing graph health.

Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.

Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy/ΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math / quantum / graph / telemetry data, build a 3D / WebGL / three.js / react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, ...

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Invoke when user asks to run the ADW loop / agentic engineering loop / software factory workflow.

Unified code quality intelligence layer that diagnoses code smells (Long Method, Feature Envy, design pattern issues), prescribes targeted Fowler refactoring techniques, and reviews code for security, performance, and clarity. Use when user says 'review this code', 'refactor this', 'what's wrong with this method', 'code smells', or 'clean this up'.

Unified sales and outreach skill generating cold outreach openers, social selling sequences, objection rebuttals, and ad creative for any paid platform — multi-persona aware, adapting tone and offer frame to buyer type. Use when user says 'write a cold email', 'outreach sequence', 'objection handling', 'ad copy', or 'sales pitch'.

6-perspective adversarial review for high-stakes turns (architecture decisions, refactor planning, deployment review) — fans out architect, adversary (7-vector attack), maintainer, ops, product, and security perspectives in parallel, then consolidates. Use when user says 'review this decision', '/shura', 'adversarial review', 'what could go wrong', 'architecture review', or 'deployment review'.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.