Project decisions and context can be hard to recover after long sessions. This skill organizes AI runtime memory into local files and provides query tools for timelines, tags, and summaries.

htmx questions often need exact attribute, event, and header behavior. This skill gives Claude, Codex, and Claude Code a local htmx reference index.

Video transcripts are hard to collect and clean by hand. This skill guides Claude, Codex, and Claude Code through subtitle extraction, cleanup, and summary preparation.

Dependency setup often fails when projects mix global packages with local requirements. This skill checks project files and guides isolated setup for common ecosystems.

Skill mirrors can drift when maintainers edit multiple AI tool directories. This skill checks counts, names, metadata, and content hashes across the three mirrors.

Plain text logs are hard to search and correlate. This skill helps implement JSON logging, request context, redaction, and aggregation-ready fields.

Teams often need a repeatable way to create and maintain Claude Agent Skills. This skill provides a practical guide for skill structure, metadata, sharing, and troubleshooting.

Code edits can lose context, overwrite work, or be hard to reverse. Safe Edit adds backups, diffs, rollback notes, modular planning, and verification.

Teams lose context when completed work is not documented. This skill turns changes, impact, validation, and follow-up tasks into a structured completion report.

New contributors often lose time finding setup steps, architecture context, and ownership rules. This skill turns project facts into a structured README that supports onboarding, debugging, and delivery.

Messy repositories make navigation, ownership, and refactoring harder. This skill provides safe folder layouts and cleanup workflows for JavaScript and frontend projects.

Feature ideas often fail because requirements and task boundaries stay unclear. This skill turns discovery answers into a structured implementation plan.

Performance regressions are hard to catch when teams review LCP, INP, and CLS late. This skill gives Claude, Codex, and Claude Code focused guidance for measuring, diagnosing, and fixing Core Web Vitals issues.

Hardcoded values make code harder to change and can expose secrets. This skill guides reviews toward constants, configuration files, and environment variables.

ML projects can look accurate while data leakage or weak evaluation hides serious flaws. This skill guides structured checks for splits, metrics, training, and deployment readiness.

Connecting AI assistants to services requires careful server design. This skill guides planning, TypeScript structure, tool annotations, testing, and evaluation for MCP servers.

Large implementation files are hard to review, test, and maintain. This skill checks line counts and guides modular refactoring with clear thresholds.

Weak error handling hides failures and exposes technical messages to users. This skill guides Claude, Codex, and Claude Code toward safer recovery patterns.

Dependency updates can introduce vulnerable or untrusted packages. This skill guides audits, safer updates, SBOM creation, and CI checks.

Custom charts often need interactions that simple chart libraries cannot express. This skill guides D3.js SVG setup, data binding, scales, axes, tooltips, zoom, transitions, and color choices.