miethe

Drives the Research Foundry control plane — a Markdown/YAML-first research pipeline that captures an idea, routes it through source discovery, claim mapping, synthesis, and deterministic verification, then publishes an evidence bundle. Use when the operator wants to run, plan, or audit an end-to-end research run with the `rf` CLI, or wants claim-traceable, governance-gated research instead of a freehand answer.

Installs and initializes a Research Foundry workspace from scratch, then orchestrates a Claude Code agent swarm to produce a claim-verified evidence bundle. Covers the uv-tool install, `rf init`, `rf doctor` bootstrap sequence; the two swarm-drive patterns (RF-native `rf swarm run` vs. Claude-Code-orchestrated discovery feeding `rf ingest`); the deterministic tail that converts raw sources into a verified, governance-gated report; and key-profile governance. Cross-links the `research-foundry` skill for the full 21-step pipeline loop and per-command reference. Use when an agent needs to stand up a Research Foundry workspace from scratch or orchestrate a Claude Code agent swarm into a claim-verified evidence bundle.

Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

TypeScript authentication framework (framework-agnostic). Features: email/password, OAuth (Google, GitHub, Discord), 2FA (TOTP, SMS), passkeys/WebAuthn, session management, RBAC, rate limiting, database adapters. Actions: implement, configure, secure authentication systems. Keywords: Better Auth, authentication, authorization, OAuth, email/password, 2FA, MFA, TOTP, passkeys, WebAuthn, session management, RBAC, rate limiting, database adapter, TypeScript auth, social login, Google auth, GitHub auth, Discord auth, email verification, password reset. Use when: implementing TypeScript auth, adding OAuth providers, setting up 2FA/MFA, managing sessions, configuring RBAC, building secure auth systems.

Delegate bounded subtasks to IBM Bob Shell CLI. Use when the user wants to use Bob, delegate to Bob, run Bob for drafting/scaffolding/exploration, or compare Codex work with Bob output. Do NOT use for architecture-heavy integration work or cross-layer backend changes.

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Use when changing artifact identity, versioning, manifests, search/matching, content resolution, repository interfaces, or the local/enterprise DB split in the SkillMeat codebase (skillmeat/core/, skillmeat/cache/, skillmeat/storage/, skillmeat/sources/) — i.e. the informal "Registry Core" kernel this AOS has not yet named as a literal module. Trigger keywords: registry core, artifact identity, repository interface, IArtifactRepository, ICollectionRepository, RepositoryFactory, cache.db, SKILLMEAT_EDITION, alembic multi-head, schema drift, cli_snapshot.json, deprecation window, backward compatibility, breaking change to core. Do NOT use for CLI-surface/agent-facing command routing (use `skillmeat-cli`), for BOM/attestation authoring (use `asdlc-skillbom-builder`), or for bundle/deployment-set packaging (use `asdlc-sam-artifact-packager`).

Use when packaging SkillMeat artifacts (skills, agents, commands, context entities, bundles, deployment sets, or project-starter templates) for deployment or distribution — creating a bundle (`skillmeat bundle create`/`add-member`), building and publishing a `.skillmeat-pack` round-trip (`bundle build-pack`/`publish-pack`/`export`/`import`), assembling a deployment set (`deployment-set create`/`add-member`/`deploy`), registering a project-starter scaffold template (`template create`), deploying a single artifact (`skillmeat add`, `skillmeat deploy`), or taking a safety snapshot before a risky change (`skillmeat snapshot`/`rollback`). Covers local-collection vs enterprise-edition packaging differences and post-deploy verification. Do NOT use for generating BOM/attestation provenance — use `asdlc-skillbom-builder` first. Do NOT use for pre-packaging quality review — use `asdlc-skill-review-board` first.

Use when an agent needs to produce SkillBOM provenance for skills, agents, commands, or other SkillMeat artifacts — generating a BOM snapshot (`skillmeat bom generate`), signing or verifying it with Ed25519 (`skillmeat bom sign|verify|keygen`), wiring git hooks that link commits to BOM state (`skillmeat bom hook install`), inspecting materialization sidecars for parameterized deploys (`skillmeat bom materializations`), or recording an owner-scoped attestation (`skillmeat attest create|list|show`). Covers exactly what fields a SkillBOM entry carries, how BOM ties into git history, and the honest gaps in promotion/approval status and policy enforcement. Do NOT use this skill for packaging artifacts into bundles/deployment-sets/templates — use `asdlc-sam-artifact-packager` instead. Do NOT use for pre-packaging quality review — use `asdlc-skill-review-board` first.

Answer CCDash project-intelligence questions using the shipped MCP tools when available and the in-repo `ccdash` CLI otherwise. Use when the operator or another agent asks about project status, feature forensics, workflow failure patterns, after-action reports, session intelligence (transcripts, search, detail), runtime validation posture, CLI timeout or caching behavior, container project onboarding, watcher binding, or how to troubleshoot the shipped CCDash API/worker/MCP surfaces. Keep routing aligned with the current shipped runtime contract and repo docs.

Audits CHANGELOG coverage for a git commit range; read-only — surfaces gaps for human remediation. Use this skill before a version bump, in CI, or ad-hoc to verify that all non-trivial commits are reflected in the changelog. Co-loaded with the release skill on every /release:bump invocation. Does not write or modify any files; outputs structured gap reports and exit codes only.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Integrate Claude Agent SDK into Python apps with subscription OAuth, structured output, MCP tools, and provider abstraction. Captures production-validated patterns and bug workarounds. Use when adding Claude Agent SDK to a Python application, enabling Claude subscription auth (OAuth) alongside API key auth, building multi-turn agent workflows with tool use, integrating MCP tools, or setting up provider abstraction.

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Use this skill when authoring, modifying, or validating SkillMeat Dynamic Workflow scripts (.claude/workflows/*.js). Covers the full governed procedure: loading the master contract and per-workflow spec, choosing patterns from the pattern library, generating scripts against ExecutionGraph/ExecutionReport schemas, validating against the four-constraints checklist (no FS/shell in script, Mode D as boundary, edit-less reviewers, no Date.now/Math.random), syntax-check recipe (async-IIFE wrap for node --check), dry-run guidance, saving to .claude/workflows/, and registering in workflow-registry.md. Use whenever creating a new workflow, extending an existing one, or reviewing a workflow script for compliance.

Delegate bounded subtasks to IBM Bob Shell CLI. Use when the user wants to use Bob, delegate to Bob, run Bob for drafting/scaffolding/exploration, or compare Claude Code work with Bob output. Do NOT use for architecture-heavy integration work or cross-layer backend changes.

Answer CCDash project-intelligence questions using the shipped MCP tools when available and the in-repo `ccdash` CLI otherwise. Use when the operator or another agent asks about project status, feature forensics, workflow failure patterns, after-action reports, artifact intelligence, live agent counts, system metrics, runtime validation posture, CLI timeout or caching behavior, project registration, or how to troubleshoot the shipped CCDash API/worker/MCP surfaces. Keep routing aligned with the current shipped runtime contract and repo docs.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Audits CHANGELOG coverage for a git commit range; read-only — surfaces gaps for human remediation. Use this skill before a version bump, in CI, or ad-hoc to verify that all non-trivial commits are reflected in the changelog. Co-loaded with the release skill on every /release:bump invocation. Does not write or modify any files; outputs structured gap reports and exit codes only.

Use this skill when creating, updating, or querying AI-optimized tracking artifacts. Invoke for: creating phase progress tracking, updating task status, querying pending/blocked tasks, generating session handoffs, validating artifacts, or understanding how to use progress files for orchestration. Provides YAML+Markdown hybrid format with 95% token reduction. Core functions: CREATE, UPDATE, QUERY, VALIDATE, ORCHESTRATE.

Orchestrate the full blog workflow for Signal to System: from post conception through design, drafting, editorial review/revision, and publication prep. Use when starting a new post from a topic, continuing from a spec, reviewing/revising an existing draft, or preparing content for publication. Coordinates drafting, voice calibration, review feedback, series continuity, and publication preparation. Handles all content phases (design → draft → review → publish) and editorial modes (review, revise, story-craft).

Drive the standalone CCDash CLI from natural language to answer questions about project status, feature forensics, agent sessions, workflow failures, and after-action reports. Use when the operator or another agent asks about CCDash project health, agent-session analytics ("why did FEAT-X take so long", "what sessions ran for this feature", "which workflows are failing"), wants an AAR / narrative feature report, or needs help installing / authenticating the `ccdash` CLI against a target server. Routes intent to `ccdash` subcommands with the right `--output` mode, echoes provenance IDs for chaining, and degrades gracefully through `ccdash doctor` on transport/auth failures. Do not use for unrelated coding tasks, writing UI components, or anything outside CCDash project/session intelligence.

Create, maintain, and review software application demos as versioned, executable product artifacts. Generates repeatable screenshots, browser walkthrough videos, animations, voiceover scripts, captions, thumbnails, talking points, and review reports from scenario manifests using Playwright + Remotion + FFmpeg pipelines. Use when the user asks to build/refresh/review a demo, capture screenshots or a walkthrough video, scaffold demo infrastructure, or wire demo workflows into CI. Dry-run first; only writes files on explicit apply/setup/initialize requests.

Apply a naturalness and humanization pass to blog drafts to reduce AI-detectable patterns. Use after /voice-writer has produced a draft, or on any content that reads too much like polished AI output. Preserves Nick Miethe's voice characteristics while adding sentence variation, unexpected word choices, natural imperfections, and conversational flow. Works best when applied to drafts that are already technically sound and voice-calibrated.

Drive the MeatyWiki CLI end-to-end — knowledge-compilation loop (ingest → classify → extract → compile → file-back → lint) over a file-first Obsidian-compatible markdown vault. Use when running any MeatyWiki CLI task, compiling inbox sources, querying/searching the wiki (including semantic/vector search), checking lens scores, managing workflow runs, or evaluating decisions. Triggers: "meatywiki", "compile loop", "ingest into wiki", "vault", "knowledge compilation", "semantic search", "lens score", "fidelity", "freshness", "workflow run", "decision table". Do NOT use for: non-MeatyWiki knowledge systems, Portal UI, SAM/CCDash (those are separate skills/projects).

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Use this skill when scaffolding a new project or feature from context (PRD, implementation plan, project directory, or free-text description). Transforms context into a deployed Bundle of artifacts via structured Intent extraction and ranked artifact search. Invoked by /scaffold:project and /scaffold:feature commands. Trigger phrases: 'scaffold my project', 'set up my Codex environment', 'create a starter bundle', 'scaffold from my PRD', 'build my artifact bundle', 'feature scaffold', 'scaffold feature'. Requires a seeded local collection (≥20 artifacts) and a running SkillMeat API.

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Route an idea or request through the Agentic Operator — classify route × tier and dispatch to rf, arc, skillmeat, meatywiki, intenttree, or multi-hop workflows. Use when the user brings an idea to route, requests escalation to a new tier, approves/rejects a pending gate, or asks for run status/history. Triggers: "op new", "route this", "which subsystem", "escalate", "approve", "reject", "what's the status", "spin up". Do NOT use for: direct subsystem command invocation (use rf, intenttree, council-review, meatywiki, skillmeat-cli skills instead).

Manage SkillMeat and Claude Code environments through natural language. Use this skill for artifact discovery/deployment/management, bundles, MCP and context entity operations, and Memory & Context workflows. This skill uses progressive disclosure: load only the specific workflow or reference docs needed for the current user request.

Expert reference for Claude Code itself — features, setup, troubleshooting, and enterprise use. Use this skill when answering questions about Claude Code installation, authentication, slash commands, agent skills, MCP server configuration, hooks, plugins, subagents/agent teams, sessions, IDE integration (VS Code, JetBrains, desktop, Chrome, Slack), CI/CD integration, enterprise deployment (SSO, sandboxing, monitoring), extended thinking, prompt caching, checkpointing, cost tracking, or debugging Claude Code behaviour. Distinct from the Agent SDK: this skill is about operating and understanding Claude Code as a tool, not about building applications on the Claude Agent SDK.

Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective, image generation, SVG/animation generation, multimodal screenshot-to-code. Actions: query, search, analyze, generate, review, visualize with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation, image gen, UI mockup, SVG, animation, multimodal. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs, generating UI mockups, creating SVG animations, screenshot-to-code workflows.

Deploy and manage NotebookLM documentation sync for any Claude Code project. Installs Python scripts + Claude Code hook that automatically syncs markdown files to a Google NotebookLM notebook on every Write/Edit. Supports install, status, resync, batch sync, cleanup, and uninstall workflows. Use when setting up NotebookLM sync in a new project, checking sync health, or managing notebook sources.

Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Generate detailed style specification from SDS style entity and plan. Enforces blueprint tempo ranges, resolves tag conflicts using conflict matrix, and maximizes information density with minimal tags. Use when creating genre-specific musical identity including tempo, key, mood, instrumentation, and vocal profile.

Generate execution plan from Song Design Spec (SDS). Extracts section structure, calculates target metrics, and produces ordered work objectives for downstream workflow nodes. Use when processing SDS to determine song arrangement, section ordering, target word counts, and evaluation criteria.

{ONE_SENTENCE_PURPOSE}. Use when {TRIGGER_CONDITION}.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Apply targeted fixes to failing artifacts based on validation issues. Improves hook density, singability, rhyme tightness, section completeness, and profanity compliance with minimal changes. Use after VALIDATE fails (≤3 iterations) to address specific quality issues before re-composing.

Score composed artifacts against blueprint rubric. Evaluates hook density, singability, rhyme tightness, section completeness, and profanity compliance. Returns scores and issues list to determine if fix loop is needed. Use after COMPOSE to validate artifacts before rendering.

Merge style, lyrics, and producer notes into render-ready composed prompt. Enforces character limits, resolves tag conflicts, normalizes living artist influences, and formats with clear section tags. Use when creating final prompts for music rendering engines with strict format and policy compliance.

Generate song lyrics with citations from pinned sources. Enforces rhyme scheme, meter, syllable counts, hook strategy, and profanity filter while retrieving from MCP sources with deterministic hash-based pinning. Use when creating lyrics with structural constraints, source attribution, and policy compliance.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Use this skill when creating, updating, or querying AI-optimized tracking artifacts. Invoke for: creating phase progress tracking, updating task status, querying pending/blocked tasks, generating session handoffs, validating artifacts, or understanding how to use progress files for orchestration. Provides YAML+Markdown hybrid format with 95% token reduction. Core functions: CREATE, UPDATE, QUERY, VALIDATE, ORCHESTRATE.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Create components and pages following the Family Gifting Dashboard "Soft Modernity" design system. Use when building UI components, pages, or implementing design specifications. Includes Apple-inspired warmth, generous radii, diffused shadows, and token-optimized styling.

Use this skill when implementing real-time features with WebSockets, including connection lifecycle management, pub/sub event patterns, state synchronization between client and server, event broadcasting, and integration with frontend state management (React Query, SWR, etc.). Covers FastAPI/Node.js/Express backends and React/Next.js/Vue frontends with fallback strategies and error recovery.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses. This is a test.

Use this skill when creating, updating, or querying AI-optimized tracking artifacts (progress files, context notes, bug fixes, observation logs) in YAML+Markdown hybrid format for 95% token reduction. Invoke for: creating phase progress tracking, updating task status and blockers, querying pending work across phases, generating session handoff reports, validating artifact completeness, or migrating existing markdown files to hybrid format. Provides three embedded agents (artifact-tracker, artifact-query, artifact-validator) plus Python migration tools for efficient multi-phase project tracking.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.

Run an Agent Review Council over a product, workflow, codebase, architecture, prompt, agent package, or GTM artifact. Produces evidence-backed structured findings, scorecard, risks, decision record, and validation plan.

Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".

Use when creating custom, interactive data visualizations with D3.js—building bar/line/scatter charts from scratch, creating network diagrams or geographic maps, binding changing data to visual elements, adding zoom/pan/brush interactions, animating chart transitions, or when chart libraries (Highcharts, Chart.js) don't support your specific visualization design and you need low-level control over data-driven DOM manipulation, scales, shapes, and layouts.

Comprehensive data visualization skill covering visual execution and technical implementation. Includes perceptual foundations, chart selection, layout algorithms, and library guidance. Load on-demand when building charts, graphs, dashboards, or any visual data representation.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.