Creates .gitlab-ci.yml files, configures pipeline stages, defines CI jobs and runners, sets up deployment workflows, and generates reusable GitLab CI/CD templates following current best practices and security standards. Use when users ask to create or build a GitLab CI/CD pipeline, CI config, build pipeline, deploy pipeline, GitLab YAML, CI jobs, or any .gitlab-ci.yml configuration from scratch or for a new project.

Validates .gitlab-ci.yml syntax, detects security misconfigurations in job definitions, checks for deprecated keywords, ensures proper stage ordering, and audits pipeline configurations for best practices. Use when working with .gitlab-ci.yml files, validating GitLab CI/CD pipeline syntax, debugging configuration errors, checking for hardcoded secrets or credentials in pipeline jobs, optimizing pipeline performance with DAG or cache, or performing security audits on GitLab CI/CD configurations.

Start a FastAPI dev server, verify docs and OpenAPI schema, test endpoints, and run pytest. Use when running, checking, or debugging a FastAPI application.

Scaffold a new FastAPI project with an opinionated directory layout, pydantic-settings config, and starter files. Use when creating a new FastAPI application from scratch.

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.

Use when a learner wants to start, work through, or be guided or tutored through the Skills in 30 minutes lesson — their first Tessl skill. Walks them one step at a time through finding the bundled commit-conventions skill on disk and triggering it on a real diff in their own repository, running a check after each step before moving on. Triggers on asks like guide me through skills in 30 minutes, start the first lesson, or walk me through my first skill.

Use when a learner wants to start, work through, or be guided or tutored through the Writing your first skill lesson — authoring their own commit-conventions skill from scratch. Walks them one step at a time through scaffolding a skill with the Tessl CLI, writing its SKILL.md, linting it against the Agent Skills spec, and installing it from their local filesystem so their agent fires it on intent, running a check after each step before moving on. Triggers on asks like guide me through writing my first skill, start lesson 2, help me author a skill, or walk me through scaffolding and linting a skill.

Use when a learner wants to start, work through, or be guided through the "Skills vs MCP, and context files" lesson (Skill Foundations, lesson 3). Walks them through it as a guided read in their own repository — opening their context files, comparing a skill with an MCP server, and applying a two-question rule to place any piece of guidance. Triggers on asks like "guide me through the skills vs MCP lesson", "walk me through context files vs skills", "tutor me on when to use a skill, a context file, or MCP", or "help me work out where this instruction belongs".

Manages architecture project state in .arch/state.json and .arch/decisions.md. Use when reading or updating project phase state, checking architecture status or project progress, asking "what phase are we in", tracking component acceptance, recording or logging decisions, or validating phase transitions.