A one-pass QA workflow that audits a plugin skill file against official docs, fixes issues in place, and writes a verification report.
Drop in a CSV and get an immediate statistical summary plus only the visualizations that actually fit the data.
A meta-skill that upgrades one existing Lattice skill through a fixed six-step pipeline: baseline diff, dependency map, precision rewrite, three-tool QA gate, and independent verification.
Audits a Claude/Lattice skill through three independent personas and returns only high-confidence, practical gaps in a severity-ordered report with concrete fixes.
Treats the Lattice repo's skills/ directory as the source of truth and audits then fixes documentation drift across README, docs/, PROJECT.md, CLAUDE.md and GitHub issue templates.
A framework for scoring AI agent output quality against fixtures and baselines so regressions are caught before they ship.
A hands-on reference for wiring up axe-core, auditing against WCAG 2.2 AA, and writing keyboard, screen reader and ARIA tests.
A compact web accessibility reference covering WCAG 2.2 AA criteria, ARIA patterns, keyboard navigation and axe-core testing.
Rules that keep subagent transcripts out of your main context by running agents in the background and passing results through files.
A skill that computes construction project schedule, cost, quality and safety KPIs with EVM formulas and rolls them into a dashboard summary.
A Python skill that auto-detects MEP/structural/architectural clashes from BIM element bounding-box data, grades severity, and exports an Excel clash report.
Turns site inputs — work quantities, labor, equipment and weather — into a structured daily progress report exported to Excel or plain text.
Turns daily site output records into planned-vs-actual productivity metrics, trends, benchmark comparisons, and completion forecasts.
Turns an experiment blueprint JSON into a runnable Python project skeleton with baselines, training, evaluation and ablation configs.
Searches arXiv and Semantic Scholar, analyses research gaps, and proposes novel hypotheses for a given topic.
A dating-coach skill that reads your crush's signals, builds a stage-by-stage strategy, and drafts messages, confessions and crisis replies.
Switches a coding agent's account only on explicit request, then verifies the new identity by asking the runtime itself instead of diffing credential files.
A rulebook for delegating independent, non-overlapping tasks to parallel agent workers or selected persistent role sessions.
A judgment skill that returns a single artifact-free CONTINUE/STOP verdict on whether a work traversal earns its cost or is just process ceremony.
Scans your codebase into a claude-db code graph and writes a five-note project profile covering stack, layout, conventions, workflows and architecture.