spk-doctrine-profile-load

Loads Spec Kitty agent profiles with governance context for interactive sessions.

1.6k|156|Updated Oct 9, 2025
One-click install
npx skills add https://github.com/Priivacy-ai/spec-kitty --skill spk-doctrine-profile-load
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spk-doctrine-profile-load
Source: https://github.com/Priivacy-ai/spec-kitty/tree/main/src/charter/offering/skills/spk-doctrine-profile-load
Command: npx skills add https://github.com/Priivacy-ai/spec-kitty --skill spk-doctrine-profile-load

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

When working with Spec Kitty outside the automated Mission runtime loop, agents need a reliable way to adopt a specific role with its full governance context. Manually reading raw .agent.yaml files misses organization overlays, specialization lineage, and override semantics, leading to incorrectly applied profiles.

Core Features & Use Cases

  • Resolver-Backed Profile Loading: Resolves profiles through spec-kitty agent profile show so project and organization overlays, specializes_from lineage, and enhances/overrides semantics are correctly applied.
  • Action-Scoped Governance: Loads charter context for specific lifecycle actions (specify, plan, implement, review, merge) via spec-kitty charter context --action.
  • Boundary Enforcement: Applies initialization declarations, specialization boundaries, directive references, and collaboration handoffs, handing off out-of-scope work to allowed collaborators.
  • Use Case: A user asks an agent to act as a security reviewer mid-session. The skill resolves the reviewer profile, loads review-scoped governance, applies the role boundaries, and returns control to the Mission workflow.

Quick Start

Ask the agent to load a specific Spec Kitty profile, such as "load the reviewer profile for the current review action", and it will resolve and apply the full governance context.

Frequently Asked Questions about spk-doctrine-profile-load

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I load a Spec Kitty agent profile in an interactive session?

Resolve the profile with `spec-kitty agent profile show <profile-id>`, then load action-scoped governance with `spec-kitty charter context --action <action> --json`. Apply the initialization declaration, boundaries, and handoffs before starting work.

How do I find available agent profiles in Spec Kitty?

Run `spec-kitty agent profile list --json` to discover resolved profiles when the user has described a role but not selected an ID. Do not infer file paths from IDs, since the resolver owns built-in, organization, and project precedence.

Can I read the .agent.yaml file directly instead of using the resolver?

Only read-only harnesses that cannot invoke the CLI may inspect `packs/built-in/agent_profiles/<profile-id>.agent.yaml` as a degraded fallback. This misses overlays, lineage, and overrides, so the limitation must be stated in the result.

What happens when requested work falls outside a profile's boundaries?

The agent hands the work to an allowed collaborator defined in the profile's collaboration handoffs rather than silently expanding the role. Boundaries are maintained throughout the session.

How do I run a one-shot governed request outside a Mission?

Use canonical dispatch with `spec-kitty dispatch "<request>" --profile <profile-id>` for standalone profile-governed invocation. Mission runtime work should return to spk-run-next instead of creating a parallel ad hoc lifecycle.