local-image-generator

Use when manually generating or updating the canonical 3-workflow GitHub Actions CI/CD set (deploy.yml, provision.yml, post-merge-deploy.yml) for a Node.js + React application deployed to a VM via Terraform and Docker Compose. Also use when an operator invokes /cicd.generate, or when updating existing workflows to match project conventions. In `smaqit.new-greenfield-project`, the deployment agent generates workflows during Phase 5 using these patterns as reference — invoke this skill directly only when generating CI/CD outside the zero-to-prod flow. Note: `copilot-setup-steps.yml` is provided by the smaqit framework and is not generated by this skill.

Use when deploying a Node.js backend + React frontend application to a remote VM via rsync. Used in the Phase 5 dev environment sweep of `smaqit.new-greenfield-project` to validate the deployment approach locally before CI/CD. Also use as a manual fallback for direct VM deployment outside the CI/CD pipeline.

Use after any deployment to confirm the application is healthy before closing the task or proceeding. Checks the health endpoint, verifies the deployed commit SHA against the current local commit, and validates the SPA root HTTP response. Produces a PASS/FAIL report per check with a final summary. Also use when a deployment task asks to confirm success or when re-verifying after a fix.

Use when configuring a custom domain with a Let's Encrypt TLS certificate for a running nginx server. Covers DNS propagation verification, nginx server_name update, Certbot certificate issuance, HTTPS smoke tests, and auto-renewal verification. Also use when activating a purchased domain for a deployed application, setting up HTTPS post-deployment, or when a spec references INF-TOPOLOGY-004 through INF-TOPOLOGY-007 as pending TLS configuration.

Use when writing deploy stamp files (DEPLOY_SHA, DEPLOY_TIME) to the VM after a successful deployment, or when re-stamping without a full redeploy. Also use when the health endpoint returns "sha":"unknown" after deployment, when a deployed PR needs a notification comment, or when smaqit.infrastructure-deploy-rsync invokes the post-deploy stamp step. Produces DEPLOY_SHA and DEPLOY_TIME files in /opt/him/backend/ on the VM and optionally posts a deploy comment on the merged PR.

Use when validating staged files before committing to catch .env files, plaintext API keys/secrets, draft spec files on main-branch commits, and large files over 1 MB. Also use when setting up the automated git pre-commit hook via the bundled install script so checks run automatically on every commit. Produces a PASS/FAIL report per check, with filenames and matching lines listed for failures.

Use this skill when making any Cyso Cloud decision — selecting a VM flavor, estimating cost, configuring Terraform credentials, looking up platform endpoints or resource IDs, setting up the OpenStack CLI, or running pre-flight checks. Routes the agent to the correct reference documentation before acting, preventing guesses on Cyso-specific facts (auth URL, image IDs, flavor names, credential formats).

Use when provisioning cloud infrastructure for the HIM Corporate application on Cyso Cloud (OpenStack) using Terraform. Covers application credential sourcing, Object Storage backend initialization, SSH keypair variable configuration, `terraform init/plan/apply`, and fixed IP retrieval. Produces a running Cyso VM accessible via SSH, with Cinder data volume attached and security group configured on ports 22/80/443. Also use when re-running Terraform after infrastructure changes or when an operator invokes `/provision.cyso`.

Use when configuring a GitHub repository with the secrets and variables required for CI/CD workflows. Covers Actions secrets (VM_SSH_KEY, VM_HOST, Terraform backend credentials, cloud provider credentials, GH_TERRAFORM_TOKEN) and the DEMO_MODE Actions variable. Uses the `gh` CLI. Prevents GITHUB_TOKEN reserved-name collisions and SSH key trailing-newline drift. Also use when setting up a new deployment repository, rotating CI/CD credentials, or verifying that all required repository secrets and variables are present.

Use before any local deployment or credential operation that requires secrets from a local HashiCorp Vault instance. Verifies Vault is running, unsealed, and authenticated on 127.0.0.1:8200. Also runs an interactive credential loader script that prompts for all project secrets and writes them to Vault. Use for first-time setup, adding a new project's credentials, or when a Vault path is missing. Also use when setting up Vault for the first time on a new machine, or when a caller cannot reach Vault and needs troubleshooting guidance.

Use when a freshly provisioned Ubuntu VM needs to be bootstrapped after cloud-init completes. Covers cloud-init verification, data volume mount and fstab registration, app directory ownership fix, `.env` file creation, and Docker group setup. Produces a VM ready for application deployment on Ubuntu 22.04/24.04.

Validate and elicit deployment phase parameters from session context before deployment begins. Invoke automatically before starting the Deployment phase to confirm or default execution preferences.

Use when orchestrating the complete SDLC for a new project — from raw project assets to a running production application accessible via browser. Covers requirements extraction, specification (business, functional, stack, infrastructure, coverage), task creation, development, IaC generation + dev environment sweep (local provisioning + deploy + verify), CI/CD production deployment, optional domain/TLS, validation, and tagged release. Re-entrant: use the pre-condition checklist to resume at any phase. Also use when the user says "take this from zero to prod", "run the full smaqit pipeline", "deploy a new project end-to-end", or when starting implementation on a freshly initialized repository.

Use this skill when the user wants to extract structured requirements candidates from raw project assets such as code prototypes, documents, or meeting notes. Produces `.smaqit/requirements-extract.md` — an enumerated, categorised inventory that specification agents can consume directly. Also use when the user asks to analyse assets, mine files for requirements, or prepare input for any spec workflow.

Use when implementation or deployment is confirmed and spec files need to be brought in sync with the live codebase. Updates frontmatter fields (`status`, `deployed`, `updated`) and flips acceptance criteria checkboxes (`[ ]→[x]` or `[ ]→[!]`) without running a full spec agent. Also use when the user asks to mark a spec as deployed, update spec status after a release, or record which acceptance criteria are met.

Manages a live Q&A knowledge manifest at `.smaqit/compendium.md`. Invoked when the user says `list compendium`, `fetch from compendium [query]`, `update compendium [question]`, or `remove from compendium [question]`. Lists all Q&A entries grouped by category, semantically searches for relevant entries, upserts a Q&A pair (add or update), or removes an entry after confirmation.

Bootstrap a new smaqit project by generating a structured .github/copilot-instructions.md from a template and creating the base project directory structure (`docs/`, `assets/`, `assets/raw/`). Use when the user asks to start a new smaqit project, init this project with smaqit, or set up smaqit for this project.

Generates a live project dashboard from the current codebase state and writes it to `.smaqit/project-recap.md`. Invoke with `project.recap` to generate the dashboard, or `project.recap --refresh` to force re-scan even if the output file already exists.

Builds and maintains a documentation topology map for the current project, identifying the full tech stack and discovering section-level documentation URLs across multiple platforms (GitHub, official docs, ReadTheDocs, pkg.go.dev, npm, PyPI, and more). Writes a persistent map to `.smaqit/references/project-research.md`; adds task-specific annotation when a task is active. Invoke when the user asks to research project dependencies, build or refresh the documentation map, or find documentation for project tools and libraries.

Execute git operations (commit, tag, push) for local releases

Execute git operations for PR-based releases (commit, push via report_progress)

End session by documenting the entire conversation. Use at session completion to create history entries.

Summarize session progress as a structured table of accomplished and pending steps. Invoke when the user asks for a "recap of the session", "review of the session", or "progress on the session".

Start a new chat with full project context. Use when beginning a session to load README, recent history, and task planning.

Generate a succinct title for the current session based on work accomplished. Use when finishing sessions to create history file titles.

Mark a task as completed by updating a task's status. Verify its acceptance criteria and record state in PLANNING.md. Use when marking a task as done — whether just implemented, retroactively closing completed work, or responding to a status update request. Follow the steps and mode-specific rules to ensure proper task management.

Create a new task with auto-numbering. Use when creating new tasks to track work.

Start working on a task. Supports autonomous mode (AI completes) or assisted mode (user approval required). Use when beginning work on tasks to set proper workflow.

Start testing session with focused context. Use when beginning test workflows with the user-testing agent.

Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.