rana/yogananda-skills Skills

API surface consistency and design review. Use when reviewing REST endpoints, data models, response shapes, naming conventions, or pagination patterns.

Cognitive archaeology — layered questioning that builds from surface inquiry through assumptions, perspectives, tensions, and meta-cognition to surface what conventional analysis misses. The sequence builds cognitive momentum; each layer prepares the ground for the next. Use for deep exploration of any subject, decision, or design.

Reasoning trace and correction. When thinking went wrong — yours or Claude's — trace back to find where pattern-matching replaced mechanism-tracing, where fear replaced exploration, or where compression happened prematurely. The cognitive equivalent of setting breakpoints in a thought process.

Cross-document coherence and cross-reference integrity check. Use when checking if all project documents tell a consistent story, if identifiers match, if stated state matches actual state, or after significant document changes.

Forward-propagation analysis. Given a proposed change, map 2nd and 3rd order effects across behavior, maintenance, user experience, and future optionality. Use before committing to significant decisions.

Rapid reorientation to a different area of the codebase. Delivers a 60-second briefing on a subsystem's current state, recent changes, key files, and known issues. Use when switching between tasks.

Simplification and editorial sharpening. Use when designs feel heavy, over-engineered, or accumulated rather than composed. The editorial knife.

Inhabit a specific cultural, spiritual, or demographic perspective and audit the design for sensitivity, inclusion, accessibility, and blind spots. Use when checking how the portal serves specific populations.

Consolidate raw explorations from .elmer/proposals/ into curated PRO-NNN entries in PROPOSALS.md. Without arguments, scans all explorations and reports variant clusters. With a PRO-NNN or filename, finds related explorations and synthesizes them.

Comprehensive multi-dimensional pre-implementation quality gate. Combines coherence, gaps, errors, and cross-references in a single pass. Use before starting implementation or at phase boundaries.

Unified document health check combining identifier audit, omission search, and cross-document consistency in a single pass. Replaces running garden, gaps, and coherence separately — reads all documents once, threads findings across phases. Use for recurring document maintenance or pre-implementation review.

Documentation practice quality review. Use when evaluating whether docs serve AI readers (Claude), human developers, and stakeholders effectively.

Detect unconscious architectural evolution. Compare the stated architecture in documents against emergent patterns in the actual code. Surface drift that nobody designed. Use periodically or when the codebase feels inconsistent.

Systematic search for omissions, blind spots, and missing decisions. Use when preparing for implementation, after completing a design phase, or when asking "what am I not seeing?"

Document identifier lifecycle maintenance. Audit ADR-NNN, DES-NNN, and similar identifier systems for safe deletion, merge candidates, category coherence, cross-reference integrity, and cognitive load reduction. Use when identifier systems accumulate weight, after greenfield analysis questions, or when documents feel harder to navigate than they should.

Hidden dependency and assumption detector. Surfaces things the system depends on that aren't explicit — environment variables, implicit service dependencies, timing assumptions, undocumented contracts. The things that break at 2am.

Production hardening checklist derived from the actual stack. HTTP headers, dependency scanning, secret management, input validation, error handling, CSP, CORS. Not a generic OWASP list — reasoned from the specific architecture. Use before deployment, after adding external integrations, or at phase boundaries.

Design-to-code specification. Given a deliverable, DES section, or ADR, produce a concrete implementation plan with file paths, function signatures, SQL migrations, config constants, and test specifications. The bridge from architecture to code.

Incident response readiness evaluation. Assesses runbook coverage, escalation paths, severity classification, communication templates, rollback procedures, and post-incident review process. Use when transitioning from development to production, at phase boundaries, or after a real incident exposes gaps.