adversarial-squad
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so…
Load a Spec Kitty agent profile on demand for interactive sessions, including identity, governance scope, boundaries, and initialization. Triggers: "act as the architect", "load the reviewer profile", "switch to researcher", "use the planner role", "adopt a profile".
$ npx -y skills add spec-kitty/spec-kitty --skill spk-charter-profile-load --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/spk-charter-profile-loadContext preview
The summary Claude sees to decide when to auto-load this skill.
Load a Spec Kitty agent profile on demand for interactive sessions, including identity, governance scope, boundaries, and initialization. Triggers: "act as the architect", "load the reviewer profile", "switch to researcher", "use the planner role", "adopt a profile".
name: spk-charter-profile-load description: >- Load a Spec Kitty agent profile on demand for interactive sessions, including identity, governance scope, boundaries, and initialization. Triggers: "act as the architect", "load the reviewer profile", "switch to researcher", "use the planner role", "adopt a profile". argument-hint: "<profile-id>"
Use this skill when the agent needs a profile outside the runtime loop or the user asks to adopt a specific role.
1. Identify the requested profile, action, and active Mission context. 2. Resolve the profile through the CLI:
spec-kitty agent profile show <profile-id>
3. Load action-scoped governance:
spec-kitty charter context --action <action> --json
4. Apply the resolved initialization declaration, specialization boundaries, directive and tactic references, collaboration handoffs, and mode defaults. 5. Return to `spk-run-next` for Mission advancement.
Do not substitute a raw `.agent.yaml` read for resolution. A narrowly scoped read-only-harness fallback is documented in the reference below.
For a one-shot governed request outside a Mission, use:
spec-kitty dispatch "<request>" --profile <profile-id>
checklist, standalone dispatch, and the bounded read-only fallback.
Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.
Deploy a bounded, profile-loaded adversarial review squad at a mission point-cut so…
Understand how Spec Kitty manages git: what git operations Python handles automatically, what…
Orchestrate the implement-review loop for Spec Kitty work packages using any configured…
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify…
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define…
Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows…