opsmill

Audits documentation completeness for a feature branch, subject, or set of existing docs — maps changes across Infrahub's documentation layers, reports gaps, and optionally applies the fixes. TRIGGER when: the user wants to audit or check documentation coverage, find doc gaps after a feature branch, or verify docs are still current for a subject or specific files. DO NOT TRIGGER when: authoring new documentation from scratch → use the add-docs flow; only linting/formatting Markdown → run `uv run invoke docs.lint`.

Perform a dual-lens critical review of the specification and plan from both product strategy and engineering risk perspectives before implementation.

General code quality review — project guideline compliance, bug detection, code quality analysis.

Code comment accuracy verification, documentation completeness assessment, comment rot detection.

Error handling review — silent failure detection, catch block analysis, error logging.

Comprehensive code review using specialized agents — orchestrates code, comments, tests, errors, types, and simplify agents sequentially.

Code simplification suggestions — clarity, unnecessary complexity, redundant abstractions. Advisory only.

Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.

Archive a feature specification into main project memory after merge, resolving gaps and conflicts

Run the full speckit workflow end-to-end — specify, plan, critique, tasks, implement, review, extract — making all decisions autonomously.

Commit changes at meaningful checkpoints throughout the workflow

Extract knowledge, guidelines, and ADRs from one or more completed spec directories into the project documentation system.

Reconcile implementation drift by updating the feature's own spec, plan, and tasks

Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.

General code quality review — project guideline compliance, bug detection, code quality analysis.

Code comment accuracy verification, documentation completeness assessment, comment rot detection.

Performs root-cause analysis of a bug — from a GitHub issue, an issue URL, or a free-text description — before any reproduction or fix is written. TRIGGER when: triaging or diagnosing a bug, investigating why something misbehaves, an issue number/URL handed over for analysis, needing the root cause before touching code. DO NOT TRIGGER when: a failing reproduction test already exists and you are ready to fix → opsmill-dev-fixing-bugs; writing that reproduction test → opsmill-dev-test-driving-bugs; capturing a new bug as a ticket → opsmill-dev-creating-issues.

Produces a breaking-change / deprecation / opportunity report for a dependency-bump PR, grounded in how this codebase actually uses each bumped package, not the changelog alone. TRIGGER when: the user gives a PR URL or number for a dependency version bump (Dependabot, Renovate, or hand-rolled) and asks what could break, what changed, or whether it is safe to merge (e.g. "scan this dependabot PR", "what breaks if we take this bump", "is <PR url> safe to merge"). DO NOT TRIGGER when: the PR is a feature or bugfix rather than a dependency version bump → a code-review or bug skill instead.

Ports an existing fix from one long-lived branch to another (e.g. a stable fix landed on the development branch), adapting it to the target branch's current code rather than cherry-picking blindly. TRIGGER when: phrasings like "backport <fix/PR/commit> to <branch>", "port this stable fix to develop", "land <ticket> on <branch> too", or a fix that already exists on one branch has to land on another. DO NOT TRIGGER when: syncing one whole branch into another wholesale → opsmill-dev-merging-branches; replaying local work onto its base → opsmill-dev-rebase; fixing a brand-new bug that has no existing fix → opsmill-dev-analyzing-bugs / opsmill-dev-fixing-bugs.

Stages and commits the current changes onto a safe working branch, enforcing branch discipline and optionally pushing upstream. TRIGGER when: the user wants to commit, save, or check in the current changes. DO NOT TRIGGER when: opening a pull request → opsmill-dev-pr.

Turns a single feature idea, improvement, or bug into ONE well-structured GitHub issue. TRIGGER when: the user wants to file/open/create an issue, turn a feature idea or improvement into a ticket, or capture something missing or broken as a ticket. DO NOT TRIGGER when: breaking work into multiple issues or planning a body of work → a planning skill; writing a full Product Requirements Document → opsmill-dev-creating-prd; the idea is still fuzzy and unhardened → opsmill-dev-grilling-ideas first.

Synthesises the current conversation context into a Product Requirements Document and publishes it to GitHub (as a comment on a referenced issue, or a new issue). Synthesises from context; does not interview. TRIGGER when: the conversation has produced enough understanding of a feature and the user wants it captured as a PRD. DO NOT TRIGGER when: a single small issue is enough → opsmill-dev-creating-issues; the idea has not been stress-tested yet → opsmill-dev-grilling-ideas first; bug reports.

Implements and validates the fix for a bug once a failing reproduction test exists. TRIGGER when: a bug has a failing reproduction test and you are ready to make it pass, implementing the root-cause fix, the final step of the bug-fixing pipeline. DO NOT TRIGGER when: no reproduction test exists yet → opsmill-dev-test-driving-bugs; still diagnosing, or asked to fix a bug with no analysis or reproduction test yet → opsmill-dev-analyzing-bugs.

Stress-tests a fuzzy or vague feature idea before any PRD, spec, or ticket is written. TRIGGER when: the user has a fuzzy feature idea — one or two paragraphs, vague on users / scope / success — and wants to harden it, or says "grill / stress-test / pressure-test this idea." DO NOT TRIGGER when: the idea is already turned into a spec or PRD; bug fixes or refactors; the idea is hardened and you are ready to write the PRD → opsmill-dev-creating-prd.

Analyzes and correlates live Infrahub data via the MCP server — answers operational questions, detects drift, and investigates impact. TRIGGER when: querying infrastructure data, checking compliance, investigating change impact, producing ad-hoc reports. DO NOT TRIGGER when: writing automated checks, building transforms, designing schemas, populating data files. ALWAYS pass the user's question verbatim as args — this skill runs in a forked context and cannot see the parent conversation. Invoking without args will fail.

Shared references and cross-cutting rules for all Infrahub skills — GraphQL syntax, .infrahub.yml format, and common patterns. DO NOT TRIGGER directly — loaded automatically by other Infrahub skills when they need shared references.

Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, querying live data, populating objects.

Creates, validates, and modifies Infrahub schema YAML files — nodes, generics, attributes, relationships, and extensions. TRIGGER when: designing data models, adding schema nodes, validating schema definitions, planning schema migrations, modeling file objects / attachments / uploads (storing PDFs, diagrams, images, certificates, documents as Infrahub objects). DO NOT TRIGGER when: populating data objects, writing checks/generators/transforms, querying live data.

Creates Infrahub Generators — design-driven automation that builds infrastructure objects from templates and topology definitions. TRIGGER when: building design-to-implementation workflows, auto-creating objects from templates, topology-driven generation. DO NOT TRIGGER when: designing schemas, writing data transforms, querying live data, populating static data files.

Creates Infrahub check definitions — Python validation logic, GraphQL queries, and YAML-driven tests for proposed change pipelines. TRIGGER when: writing validation checks, creating Python checks, building data quality guards for proposed changes, writing or running tests for a check. DO NOT TRIGGER when: designing schemas, querying live data, building transforms or generators.

Creates Infrahub transforms that convert data into JSON, text, CSV, or device configs using Python or Jinja2 templates, with YAML-driven tests. TRIGGER when: building config generation, data export, format conversion, Jinja2 templates, artifact pipelines, writing or running tests for a transform. DO NOT TRIGGER when: designing schemas, writing validation checks, creating generators, querying live data.

Converts CSV/TSV inputs into Infrahub object YAML and loads them onto a fresh branch. Handles a single file, a folder of files, an explicit list of paths, and one-big-denormalized-sheet exports. TRIGGER when: importing CSV, loading CSV/TSV into Infrahub, ingesting spreadsheet data, converting CSV to Infrahub objects, splitting a denormalized CSV across multiple kinds. DO NOT TRIGGER when: running `infrahubctl import load` against an LDJSON dump (different format and tool), designing or modifying schemas (this skill is read-only against the schema and fails closed on unmapped columns), exporting data from Infrahub (use `infrahubctl object get -o csv` for single-kind export), or ingesting JSON/XLSX (v1 is CSV+TSV only).

Shared references and cross-cutting rules used by all Infrahub skills. Contains GraphQL query syntax, .infrahub.yml configuration format, and common rules for git integration, display label caching, and Python environment setup. DO NOT TRIGGER directly — loaded automatically by other Infrahub skills when they need shared references.

Audit an Infrahub repository against all best practices and rules. Use when reviewing a project for compliance, onboarding to an existing repo, or before deployment to catch issues early.

Analyze and correlate Infrahub data using the MCP server. Use when querying live infrastructure data to answer operational questions, detect drift, correlate node types, investigate service impact, check maintenance windows, or produce ad-hoc reports — without writing pipeline code.

Create and manage Infrahub check definitions. Use when writing validation logic, creating Python checks that run in proposed change pipelines, or building data quality guards for Infrahub.

Create and manage Infrahub Generators. Use when building design-driven automation that creates infrastructure objects from templates, topology definitions, or any design-to-implementation workflow in Infrahub.

Create and manage Infrahub custom menus. Use when designing navigation menus, organizing node types in the UI, or customizing the Infrahub web interface sidebar.

Create and manage Infrahub object data files. Use when populating infrastructure data, creating device instances, locations, organizations, module installations, or any other data objects for an Infrahub repository.

Create, validate, and modify Infrahub schemas. Use when designing data models, creating schema nodes with attributes and relationships, validating schema definitions, or planning schema migrations for Infrahub.

Analyzes and correlates live Infrahub data via the MCP server — answers operational questions, detects drift, and investigates impact. TRIGGER when: querying infrastructure data, checking compliance, investigating change impact, producing ad-hoc reports. DO NOT TRIGGER when: writing automated checks, building transforms, designing schemas, populating data files. ALWAYS pass the user's question verbatim as args — this skill runs in a forked context and cannot see the parent conversation. Invoking without args will fail.

Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, querying live data, populating objects.

Shared references and cross-cutting rules for all Infrahub skills — GraphQL syntax, .infrahub.yml format, and common patterns. DO NOT TRIGGER directly — loaded automatically by other Infrahub skills when they need shared references.

Creates Infrahub check definitions — Python validation logic and GraphQL queries for proposed change pipelines. TRIGGER when: writing validation checks, creating Python checks, building data quality guards for proposed changes. DO NOT TRIGGER when: designing schemas, querying live data, building transforms or generators.

Creates Infrahub Generators — design-driven automation that builds infrastructure objects from templates and topology definitions. TRIGGER when: building design-to-implementation workflows, auto-creating objects from templates, topology-driven generation. DO NOT TRIGGER when: designing schemas, writing data transforms, querying live data, populating static data files.

Creates Infrahub custom navigation menus for the web UI sidebar, organizing node types into logical groups. TRIGGER when: designing sidebar menus, grouping node types in UI, customizing Infrahub web interface navigation. DO NOT TRIGGER when: designing schemas, writing checks or transforms, populating data objects.

Creates and manages Infrahub object data YAML files for populating infrastructure instances — devices, locations, organizations, and modules. TRIGGER when: creating device instances, populating data files, defining locations or organizations, adding infrastructure objects. DO NOT TRIGGER when: designing schemas, writing Python checks/generators, querying live data.

Creates, validates, and modifies Infrahub schema YAML files — nodes, generics, attributes, relationships, and extensions. TRIGGER when: designing data models, adding schema nodes, validating schema definitions, planning schema migrations. DO NOT TRIGGER when: populating data objects, writing checks/generators/transforms, querying live data.

Stages and commits the current changes onto a safe working branch, enforcing branch discipline and optionally pushing upstream. TRIGGER when: the user wants to commit, save, or check in the current changes. DO NOT TRIGGER when: opening a pull request → pr.

Turns a single feature idea, improvement, or bug into ONE well-structured GitHub issue. TRIGGER when: the user wants to file/open/create an issue, turn a feature idea or improvement into a ticket, or capture something missing or broken as a ticket. DO NOT TRIGGER when: breaking work into multiple issues or planning a body of work → a planning skill; writing a full Product Requirements Document → creating-prd; the idea is still fuzzy and unhardened → grilling-ideas first.

Stress-tests a fuzzy or vague feature idea before any PRD, spec, or ticket is written. TRIGGER when: the user has a fuzzy feature idea — one or two paragraphs, vague on users / scope / success — and wants to harden it, or says "grill / stress-test / pressure-test this idea." DO NOT TRIGGER when: the idea is already turned into a spec or PRD; bug fixes or refactors; the idea is hardened and you are ready to write the PRD → creating-prd.

Watches an open pull request's CI until green and fixes failing checks. TRIGGER when: the user wants to watch a pull request's CI, babysit a PR until it goes green, or fix failing CI checks on an open PR. DO NOT TRIGGER when: opening the PR in the first place → pr; rebasing the branch onto its base → rebase.

Opens a pull request, publishing the current branch as a PR. TRIGGER when: the user wants to open a pull request, publish the current branch as a PR, or take the current work through to an open PR. DO NOT TRIGGER when: only committing changes → commit; babysitting CI after the PR is already open → monitoring-pull-requests.

Shared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative path.

Rebases a feature branch onto its latest base, resolving conflicts while preserving the intent of local changes, optionally force-pushing and watching CI afterward. TRIGGER when: the user wants to rebase a feature branch, update a branch against its base, or replay local work on top of the latest upstream. DO NOT TRIGGER when: merging a release branch into dev → merging-branches; only watching CI on an already-open PR → monitoring-pull-requests.

Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.

Convert tasks from tasks.md into GitHub issues.

Upgrade the Infrahub platform version in this project. Handles downloading the new compose file, upgrading the SDK, updating version references across Dockerfile, docker-compose.override.yml, and .envrc, and rebuilding the Docker image. Use this skill whenever the user asks to upgrade, bump, or update the Infrahub version — even if they just say something like "bump infrahub to 1.9" or "upgrade to latest infrahub" or "update infrahub version".