kanopi

Automatically check code against PHPCS, ESLint, WordPress Coding Standards, or Drupal Coding Standards when user asks about code style, standards compliance, or best practices. Invoke when user mentions "coding standards", "code style", "linting", "PHPCS", "ESLint", or asks if code follows conventions.

Generate a PR description and create a GitHub pull request. Invoke when user wants to create a pull request, says "create a PR", "submit a PR", "open a pull request", or uses /pr-create. Requires user confirmation before creating the PR (irreversible GitHub action). Supports ticket numbers and --concise mode.

Generate changelog entries, a deployment checklist, and update a release PR description. Invoke when user asks to prepare a release, generate a changelog, create a deployment checklist, or uses /pr-release. Requires user confirmation before updating the PR (modifies publicly visible content). Supports version numbers and focus areas (changelog/deploy/update).

Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification, and appends the Assisted-by git trailer recording which AI model (Claude, GPT, Gemini, or any other LLM) assisted the change. Invoke when user mentions "commit", "staged", "committing", or asks for help with commit messages.

Automatically validate implementations in real browsers after code is written or when user says "test this", "test what you built in the browser", "check it in a real browser", or "validate at the breakpoints". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility compliance (WCAG AA contrast, keyboard navigation, ARIA), validate interactions, and generate detailed technical reports with file paths and specific fixes.

Review a pull request or analyze local changes before submitting. Auto-activates when user mentions reviewing a PR, asks for code review, wants to analyze their changes before submitting, or mentions "pr-review self". Invoke when user provides a PR number to review or says "review self", "review my changes", or "pr review". Supports focus areas: code, security, breaking, testing, size, performance.

Generate and maintain patches for Composer-installed packages (Drupal contrib modules, WordPress packages, PHP libraries) using cweagans/composer-patches. Invoke when the user needs to modify a contrib or vendor package, mentions "composer patch", "patch a module", "patch a contrib module", "cweagans", "diff -ruN", "extra.patches", or needs a package change that applies cleanly in CI. Covers generating diff -ruN patches, handling new files, wiring composer.json, and verifying the patch applies.

Create, list, and tear down git worktrees following Kanopi's branch naming conventions so developers and agents can work multiple tickets in parallel without clobbering each other's working tree. Handles DDEV isolation automatically (folder-derived project name, no pinned ports) for Drupal and WordPress, and plain worktree setup for Next.js. Invoke when the user wants to start a ticket in a fresh worktree, run more than one Claude Code or Claude Desktop session at once, says "create a worktree", "new worktree for tw1234", "spin up a parallel branch", "work on two tickets at once", "/worktree-manager", or asks how to clean up a finished worktree. Use this skill even if the user only says "I need to work on another ticket without losing my current one."

Analyze WordPress block theme projects for FRD generation. Provides block/pattern inventory analysis, theme.json specifications, plugin justification framework, Core Web Vitals performance budget, and WordPress-specific estimation patterns.

Generate properly formatted Teamwork CSV files from Functional Requirements Documents. Converts FRD requirements into CSV backlog with task hierarchy, priorities, story points, and estimated hours. Automatically populates estimated time from story point conversion. Invoke when user asks to "export to CSV", "create Teamwork backlog", or needs project backlog file.

Generate comprehensive FRD markdown structure with all required sections. Provides section templates, numbering conventions (FR-XXX, TR-XXX, US-XXX), platform-specific additions, and output format guidelines. Invoke when requirements are gathered and ready to structure into FRD document.

Provide story point estimation guidance with hour calculations for software development tasks. Uses Fibonacci sequence (1, 2, 3, 5, 8, 13, 21, 34+) and converts story points to hours. Includes platform-specific adjustments and velocity calculations.

Deploy the demo application to the shared environment. Invoke when the user says "deploy the demo", "push the demo live", or uses /demo-deploy.

Quick reference for common HTTP status codes. Invoke when the user asks "what does 404 mean", "HTTP status code reference", or similar lookup questions.

Generate CANT-tagged behavioral eval cases when adding or updating a skill in a Kanopi skills plugin (cms-cultivator, delivery-record, premium-service-skills, devops-skills, pm-skills, or any repo derived from skills-plugin-template). Invoke when a new skill needs gate and pressure cases, when the user says "add CANT evals", "behavioral evals for this skill", "pressure case", "gate case", "test this skill's promises", or after writing a SKILL.md with side effects or honesty rules.

Generate a Delivery Record for a significant AI-assisted output — code (PR), FRD, audit, discovery, design-handoff, strategy, client-comm, design, QA, launch, deployment, devops, project-setup, or ongoing-improvement. Refuses to write without a named human reviewer and the two checkpoint notes. Writes to docs/delivery-records/ in a repo or to Drive in Claude Desktop, and indexes the result in the project's Teamwork "Delivery Records" notebook. Invoke at the end of a unit of work, after /pr-create for code, or via /delivery-record.

Validate a Delivery Record file against the kanopi/delivery-record schema. Reads predicate_type to resolve the schema version, then enforces required fields, checks-value validity (pass|fail|n/a), and the per-activity_type required-keys policy. Applies the threshold rule (fail needs a waiver, n/a needs a justification) as soft warnings, or hard failures with --strict. Invoke as /delivery-record-verify <path>, or with no path to validate all docs/delivery-records/*.md.

EXAMPLE — delete this skill when adopting the template. Demonstrates the required frontmatter shape, the openai.yaml Codex policy convention, and the routing-eval wiring. A real description states what the skill does, when to invoke it, and lists specific trigger phrases like "example the widget" or "run the demo workflow".