code-docs-align
Use when the user says '/code-docs-align', 'check if docs match code', 'verify docstrings', 'find stale comments', 'audit TODOs', 'check ref-doc accuracy', 'documentation accuracy', or wants to verify that documentation, docstrings, comments, and ref-docs actually reflect the current state of the code. This skill bridges /code-audit (code quality) and docs-assess (doc coverage) by checking ACCURACY â do the docs match what the code actually does?
fleet-triage
Cognitive triage of fleet audit findings. Read issue content, evaluate labeling accuracy, and determine open/close/dispatch/relabel actions for fleet-managed issues. Use when triaging undispatched issues or reviewing audit scan results.
usage-board-refactor
Use when refactoring or cleaning the usage-board project, especially to remove unused functions/constants including unused exports, reduce repeated logic without adding trivial wrapper functions, improve readability, and preserve token/cost/session data accuracy. Applies to Vue, Nuxt, shared analytics utilities, websocket module loading, and dashboard aggregation code in this repository.
PageMap
Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
conversation-log
Technical conversation log with factual accuracy and precision tailored specifically for DEVELOPER and ENGINEER profiles. Provides systematic guidance for capturing decisions, outcomes, and next steps. Use when user asks to create technical conversation logs for reviews, architecture discussions, or implementation sessions.
caveman
Ultra-compressed communication mode. Slash token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
PreClick — An MCP-native URL preflight scanning service for autonomous agents.
PreClick scans links for threats and confirms intent match with high accuracy before agents click.
android-check-pr-translations
Audit translation accuracy for strings changed in a GitHub PR. Use when asked to check, review, audit, or verify translations in a pull request. Identifies inaccurate translated strings by comparing PR changes against the English source.
runtime-version-check
Research and verify the latest versions of programming language runtimes (Node, Bun, Deno, Python, Go, etc.) using a two-phase verification process that prioritizes accuracy over speed.
zettelforge
ZettelForge v2.0.0 â Production CTI agentic memory system. Hybrid TypeDB (STIX 2.1 ontology) + LanceDB (vector search). Zero external AI dependencies: fastembed for embeddings, llama-cpp-python for LLM. 75% accuracy on CTI queries, 18% on LOCOMO. Use when agents need persistent memory, threat intel retrieval, entity extraction, graph traversal, or RAG synthesis.
glmocr
Extract text from images using GLM-OCR API. Supports images and PDFs with high accuracy OCR, table recognition, formula extraction, and handwriting recognition. Use this skill whenever the user wants to extract text from images, perform OCR on pictures, scan documents, convert images to text, or process any image files to get their textual content.
awq-quantization
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
audit-content
Verifies truthfulness, accuracy, and link integrity of content before publishing. Catches fabricated statistics, dead URLs, misattributed sources, and company claims that contradict the brand DNA.
agents-review
Reviews and refactors AGENTS.md files in the Nuclia frontend monorepo for completeness, accuracy, and AI-agent usability. Invoke this skill whenever you are working with an AGENTS.md file in apps/ or libs/, when asked to review or improve agent documentation, when creating a new AGENTS.md for a project, or when you notice that an AGENTS.md seems outdated, thin, or missing. Proactively suggest a review even when the user only asks an unrelated question about a project if no AGENTS.md exists for it.
ReNoUn — Crypto Regime Classification
Crypto regime classifier for trading agents. 100% bounded regime accuracy. 50 free calls/day.
ace-tool
Semantic codebase search, code indexing, and prompt enhancement via standalone CLI. Use when: (1) Semantic code search with natural language queries, (2) Code indexing for remote codebase retrieval, (3) Prompt enhancement with codebase context, (4) Before grep/find/glob operations for better accuracy, (5) Complex requirements clarification, (6) Large codebase navigation. Triggers: "search context", "enhance prompt", "find code that", "index project", "clarify requirements". IMPORTANT: Always use ace-tool BEFORE grep/find/glob for semantic-level code location.
citation-check-skill
Vision-enabled verification gate with web search. Use when users want to (1) verify slides/reports/PDFs/images against authoritative online sources, (2) validate that citations actually exist and say what's claimed, (3) check charts/graphs/tables for accuracy, (4) audit AI-generated content in doc-only mode (no external knowledge). Two modes - search mode validates against web, doc-only mode ensures everything traces to provided documents. Supports content in any language.
cost-mode
Cost-conscious Claude Code mode. Reduces token usage 40-70% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.