Generates production-ready Dockerfiles with multi-stage builds, layer caching, security hardening (non-root users, minimal base images), health checks, and automatic .dockerignore creation. Validates output using devops-skills:dockerfile-validator with iterative error fixing. Use when a user wants to create, generate, write, or build a Dockerfile or docker image, containerize an app, set up a container, or needs a Dockerfile for Node.js, Python, Go, Java, or another language. Also applies when the user says 'containerize my app', 'docker-compose setup', 'container setup', or 'optimize my Docker build'.

Validates, lints, and secures Dockerfiles by running syntax checking, detecting security vulnerabilities, validating layer ordering, checking for hardcoded secrets, verifying base image tags, and analyzing build optimization. Use when validating Dockerfile syntax, checking security best practices, optimizing image builds, auditing container security, or debugging Dockerfile errors. Applies to all Dockerfile variants (Dockerfile, Dockerfile.prod, Dockerfile.dev, etc.).

Use when a learner wants to start, work through, or be guided or tutored through the Reviewing skills with review evals lesson — the first lesson on measuring skill quality. Walks them one step at a time through running a review eval on their skill, reading the report by its pattern of suggestions, and meeting the threshold gate that blocks a low-scoring skill, running a check after each step before moving on. Triggers on asks like guide me through reviewing skills with review evals, start the review evals lesson, or how do I score my skill's quality.

Use when a learner wants to start, work through, or be guided or tutored through the Task evals & scenarios lesson — the lesson on measuring a skill's behavior. Walks them one step at a time through generating scenarios from real commits, editing a criteria rubric, running a task eval, and reading the baseline-vs-with-context lift, running a check after each step before moving on. Triggers on asks like guide me through task evals and scenarios, start the task evals lesson, generate scenarios from commits, or how do I measure whether my skill actually works.

Use when a learner wants to start, work through, or be guided or tutored through the Optimizing a skill lesson — the closing lesson on improving a skill. Walks them one step at a time through running the review-eval optimizer loop to raise a skill's score, then dogfooding the skill against real work to catch what the optimizer can't see, running a check after each step before moving on. Triggers on asks like guide me through optimizing a skill, start the optimizing lesson, how do I improve my skill's review score, or dogfood my skill before publishing.

Read the operator's current IANA timezone from the host-owned `tz_state` singleton. Use when a skill needs the zone the operator is in right now — phrasing "today" / "tomorrow", picking the parse zone for a "remind me at 8am" reminder, deciding whether a local time has passed — instead of the container clock, `home_tz`, or a hand-written SQL read.

Deterministically decide whether a deadline/event is past or future relative to the real current instant. The mandated computation path for `rules/temporal-awareness.md` — call it before any "already passed", "still time to act", or upcoming/just-happened framing instead of eyeballing the clock.

Search messages.db for past chat history by keyword and/or sender username. Use when the user references past messages, after context compaction, after a session nuke, or anywhere `rules/context-recovery.md` requires checking the message history before claiming lost context.