ad-hoc-profile-load

Solid

Load an agent profile on demand to adopt a specific role for the current session. Applies the profile's identity, governance scope, boundaries, and initialization declaration without requiring a running mission. Triggers: "act as the architect", "load the reviewer profile", "switch to implementer", "use the researcher persona", "start a session as planner", "adopt the curator role", "initialize profile", "assume the designer identity". Does NOT handle: mission advancement (use runtime-next), charter interview/generation (use charter-doctrine), or profile creation (use spec-kitty agent profile create).

AI & Automation 1,281 stars 105 forks Updated today MIT

Install

View on GitHub

Quality Score: 92/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# ad-hoc-profile-load Load an agent profile interactively to adopt a specific role for the current session. This skill is for ad-hoc use outside the mission runtime loop — when a user wants an agent to behave as a particular role without starting a formal mission. --- ## When to Use This Skill Use this when the user asks you to: - Act as a specific agent role (architect, reviewer, implementer, etc.) - Load a profile for an interactive session - Adopt role-scoped boundaries and governance context - Switch roles mid-conversation Do NOT use this when: - A mission is running and `spec-kitty next` is driving the loop — the runtime assigns profiles automatically via DDR-011 matching - The user wants to create a new profile — use `spec-kitty agent profile create` - The user wants to modify an existing profile — edit the YAML directly --- ## Step 1: Resolve the Profile If the user names a profile directly, load it. If they describe a role or task, resolve the best match. **By explicit ID:** ```bash spec-kitty agent profile show <profile-id> ``` ```python from doctrine.agent_profiles import AgentProfileRepository repo = AgentProfileRepository(project_dir=project_agents_dir) profile = repo.resolve_profile("architect") ``` **By task context (when the user describes what they want to do):** ```python from doctrine.agent_profiles.profile import TaskContext context = TaskContext( languages=["python"], frameworks=["fastapi", "<project-test-runner>"], file_patt...

Details

Author
Priivacy-ai
Repository
Priivacy-ai/spec-kitty
Created
7 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

aitask-pick

Select the next AI task for implementation from the `aitasks/` directory.

4 Updated today
beyondeye
Code & Development Listed

aitask-pickrem

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

4 Updated today
beyondeye
Code & Development Listed

aitask-explore

Explore the codebase interactively, then create a task for implementation.

4 Updated today
beyondeye
AI & Automation Solid

agent-context-loader

PROACTIVE AUTO-LOADING: Automatically detects and loads AGENTS.md files from the current working directory when starting a session or changing directories. This skill ensures agent-specific instructions are incorporated into Claude Code's context alongside CLAUDE.md, enabling specialized agent behaviors. Triggers automatically when Claude detects it's working in a directory, when starting a new session, or when explicitly requested to "load agent context" or "check for AGENTS.md file".

2,274 Updated today
jeremylongshore
AI & Automation Listed

agent-builder

Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design artifacts — saved to $HOME/.ai-first-kit/ with optional framework-specific configuration for Claude Code, OpenAI Agents SDK, Anthropic Agent SDK, CrewAI, or custom frameworks. Reads the organizational genome, governance, gates, and role definitions to produce agent configurations that embody a specific role in the organization. Use when the user says 'create agent instructions', 'build an agent', 'agent system prompt', 'configure an agent', 'agent for this role', 'OpenAI agent', 'CrewAI agent', 'create agent config', 'deploy an agent', or 'what tools should this agent have'. Also use when the user has completed role-value-mapper and wants to actually deploy agents that follow the organizational genome, or when they ask 'how do I make an agent follow our rules' or 'how do I create an OpenClaw agent for our org' — even if they don't use the word 'builder'. This skill MUST be consulted because it

5 Updated 3 days ago
synaptiai