AI Context Kit

Create canonical SKILL.md artifacts with deterministic schema, workflow, safety, and quality checks.

Always-on guardrail that grounds date, time-of-day, elapsed-time, and pacing statements in a real local clock reading instead of an estimate. Use whenever the session references the current time, a stated time budget, session duration, a date-dependent schedule, or a timestamp written into an artifact — including direct questions like "what time is it", "what's today's date", "what day is it". Do not use this to fetch time from a network service — local time only.

Validate SKILL.md artifacts for schema, quality, safety, portability, and scoring compliance.

Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance.

Capture the current session state as a checkpoint artifact per spec section 4.4. Use when the user signals session end or explicitly requests a checkpoint. Do not use mid-session or without user approval.

Load a checkpoint artifact at session start and restore the session state it describes per spec section 4.4 restore rules. Use only when a checkpoint file is explicitly provided at the beginning of a session.

Validate AGENTS.md files for structural completeness, operational contract coverage, neutrality, and repository alignment.

Enforce coordinated updates across specs, templates, prompts, samples, and docs to prevent repository guidance drift.

Create project-context AGENTS.md files using phased discovery, required operational sections, and session-state modeling.

Validate project-context AGENTS.md files for required sections, session-state model completeness, role quality, and scoring compliance.

Create complete user-context instruction files using a structured discovery workflow and repository format rules.

Validate user-context instruction files against schema, section completeness, quality checks, and scoring criteria.