一键导入
skill-nix-research
// Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks.
// Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks.
Execute general implementation tasks following a plan. Invoke for general implementation work.
Research blockers and spawn new tasks to overcome them, updating parent task dependencies
Archive completed and abandoned tasks with CHANGE_LOG.md updates and memory harvest suggestions
Execute general implementation tasks following a plan. Invoke for general implementation work.
Research blockers and spawn new tasks to overcome them, updating parent task dependencies
Archive completed and abandoned tasks with CHANGE_LOG.md updates and memory harvest suggestions
| name | skill-nix-research |
| description | Conduct Nix/NixOS/Home Manager research using MCP-NixOS, web docs, and codebase exploration. Invoke for nix research tasks. |
| allowed-tools | Agent, Bash, Edit, Read, Write |
Thin wrapper that delegates Nix research to nix-research-agent subagent.
This skill activates when:
Validate task_number exists and task_type is "nix".
Update status to "researching" BEFORE invoking subagent.
Domain-specific context for the nix-research-agent:
.claude/extensions/nix/context/{
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "research", "skill-nix-research"],
"timeout": 3600,
"task_context": {
"task_number": N,
"task_name": "{project_name}",
"description": "{description}",
"task_type": "nix"
},
"focus_prompt": "{optional focus}",
"metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}
Use Agent tool with subagent_type: "nix-research-agent".
CRITICAL: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
.return-meta.json file now before proceeding to postflight. Use the schema from
return-metadata-file.md with the appropriate status value for this operation.
If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 4b). Do NOT skip these stages for any reason.
Read the metadata file from specs/{N}_{SLUG}/.return-meta.json.
Update state.json and TODO.md based on result.
Add research artifact to state.json. Update TODO.md per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.
Commit changes with session ID.
Brief text summary (NOT JSON).