CKGrafico

Read-only exploration of an idea, problem, or requirement before creating a change. Clarifies what is being asked for (scope, acceptance criteria, edge cases, alternatives), using the codebase as grounding evidence, and recommends an approach. Load when exploring or clarifying a task before planning. Invoked by the /plan-explore command (interactive) and the plan-goal pipeline (autonomous).

Parse Azure DevOps user story URL and create OpenSpec change. Use when user provides an Azure DevOps URL.

Parse work item from any URL using browser automation. Use when user provides a URL that doesn't match GitHub/Azure/Jira CLI platforms, or when backlog platform is 'browser'.

Parse GitHub Issue URL and create OpenSpec change. Use when user provides a GitHub Issue URL.

Parse a Jira work item and create an OpenSpec change. Use when the user provides a Jira URL or a bare issue key (e.g. PROJ-123).

Generate or update ARCHITECTURE.md by analyzing the codebase structure. Safe to run at any time. Invoked by the /make-architecture command and the repo-initialize flow.

Generate or update DESIGN.md by analyzing the codebase design system (Tailwind, CSS vars, tokens, UI framework config). Safe to run at any time. Invoked by the /make-design command and the repo-initialize flow.

Generate or update the ob-guardrails-project skill from ARCHITECTURE.md and relevant project files, then wire it into every engineer agent. Invoked by the /make-guardrails command and the repo-initialize flow.

Implement tasks from a plan. OpenSpec-annotated tasks (from ob-plan-propose) run as parallel subagent waves; Todo pane tasks (from /plan-quick) run sequentially in-session. Load when implementing a prepared plan. Invoked by the /plan-apply command (interactive) and the plan-goal pipeline (autonomous).

Archive a completed OpenSpec change and update documentation. Interactive mode finds the oldest merged unarchived change and opens an archive PR; autonomous mode archives a named change in place on the current branch. Invoked by the /plan-archive command (interactive) and the plan-goal pipeline (autonomous).

Read-only exploration of an idea, problem, or requirement before creating a change. Investigates the codebase, weighs tradeoffs, and recommends next steps. Load when exploring or clarifying a task before planning. Invoked by the /plan-explore command (interactive) and the plan-goal pipeline (autonomous).

Parse a work item or idea and produce an OpenSpec change plan (proposal.md, specs, tasks.md) with enriched task assignments (agent, tier, depends_on, touches). Load when turning a requirement into a structured plan. Invoked by the /plan-propose command (interactive) and the plan-goal pipeline (autonomous).

Generic guardrails, foundational rules that all agents follow. Users add specialized guardrails skills for specific concerns. Covers secrets, code quality, security, tool usage, and engineer workflow.

Project-specific rules and constraints extracted from ARCHITECTURE.md. Load this skill before implementing any change to understand boundaries, conventions, and constraints for this codebase.

Capture visual/textual evidence of a completed change and post it as a comment on the originating issue or work item. Best-effort and non-fatal - a screenshot of the running UI (or a text summary for non-UI work) committed under the change's images/ folder, then linked from the backlog item. Load after a change is implemented and pushed. Invoked by the /ops-evidence command and the plan-goal pipeline (pr/push modes).

Create a pull request for the current feature branch, with screenshots if UI changed. Load when shipping a finished feature branch. Invoked by the /ops-ship command and the plan-goal pipeline (pr mode).

Understand and design Loop Task Loops: cadence, iteration lifecycle, state transitions, non-overlapping execution, maximum iterations, chain flow composition, and safe recurring automation patterns. Load this skill when creating, reviewing, or modifying a recurring Loop or reasoning about how its Task chain behaves across iterations.

Understand and design Loop Task Projects: organisational scope for Loops, default-project semantics, membership, colour branding, deletion with reassignment, and safe multi-tenant automation patterns. Load this skill when creating, reviewing, or modifying Projects or reasoning about how Loops are grouped, isolated, and reassigned.

Understand and design Loop Task Tasks: executable work units, success and failure semantics, Task chaining via onSuccess and onFailure, context production and consumption, stdout parsing, parameter interpolation, condition modelling, reuse, and idempotency. Load this skill when creating, reviewing, or modifying Tasks or reasoning about how a Task chain flows context between steps.

Generic guardrails, foundational rules that all agents follow. Users add specialized guardrails skills for specific concerns. Covers secrets, code quality, security, tool usage, and engineer workflow.

Project-specific rules and constraints extracted from ARCHITECTURE.md and project config files. Load this skill before implementing any change to understand boundaries, conventions, and constraints for this codebase.

Parse GitHub Issue URL and create OpenSpec change. Use when user provides a GitHub Issue URL.

{what this skill teaches agents}

PAO workflow for scanning, drafting, and presenting community responses with human review gate

Team initialization flow (Phase 1 proposal + Phase 2 creation)

Set up and use dependency injection in TypeScript with inversify-props (a wrapper over InversifyJS 8). Use when wiring up a DI container in a Vue, LitElement, vanilla TS or framework-agnostic app, registering singletons/transients/request-scoped services, injecting dependencies with property or constructor @inject, auto-generating ids from class names, or mocking injected services in tests. For React, prefer the companion inversify-hooks skill.

Set up and use dependency injection in React with inversify-hooks (a React layer over inversify-props / InversifyJS 8). Use when wiring up a DI container in a React app, injecting services into components via the useInject hook, registering singletons/transients, injecting dependencies into other services with @inject, or mocking injected services in tests.