Groove Daily Start

Architectural audit that hunts dead code, duplicated functionality, anti-patterns, type confusion, and code smells across a whole codebase. Use when the user asks for architectural analysis, to find dead or unused code, identify duplication, or assess codebase health. Don't use for style/formatting, performance profiling, security audits, or feature-level code review.

Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations. Use for polypharmacy review, prescribing decision support, and safety analysis when adding or switching drugs.

General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping. Use when reviewing any contract or term sheet, deciding when to engage outside counsel, defining IP strategy, evaluating regulatory exposure (HIPAA, GDPR, FDA, fintech), or when user mentions general counsel, GC, legal review, contract risk, term sheet, IP assignment, or regulatory exposure. NOT a substitute for licensed counsel — surfaces questions to bring to qualified attorneys.

Auto-intercepts English messages for grammar / word-choice / expression issues (max 3 per message); auto-translates Chinese / Japanese / Korean / Spanish / other-language messages with vocabulary extraction. Also handles word lookups, phrase lookups (e.g. 'break the ice'), translation requests, and quiz/review. Logs every prose input (clean OR with issues) to `prose_log` so fluency rate is tracked over time. Pushes 3 due-for-review words at the first session of each day (spaced repetition: 1/3/7/14/30/90 days). Triggers: any English message, any Chinese message, any non-English-non-Chinese prose, single English word, idiom, '查单词', '学英语', 'what does X mean', vocabulary review. Data stored at ~/.learnwy/english-learner/ with mastery + fluency tracking.

Audits, scores, and refactors AGENTS.md and CLAUDE.md agent instruction files using execution-first standards: working commands, real-failure gotchas, signal-to-noise, and @import progressive disclosure. Runs a 12-check quick triage or a 49-check full audit with letter grades, then proposes minimal diffs. Use when asked to audit, review, score, refactor, or improve agent instruction files, fix stale commands, reduce bloat, write a new AGENTS.md, or when asking "my AGENTS.md is bad", "help me write a CLAUDE.md", or "improve my agent instructions". For SKILL.md skill files use agent-skills-creator; for general docs use docs-writing; for mining session history into instruction suggestions use the external cadence-advise skill where installed.

Document lessons, update rules/templates/docs. Use to capture learnings after review.