Authoring Bootstrap¶
Use this prompt to author or update docs-first MCP modules in this repository, including repository-specific Copilot thin shims.
Supplied Inputs¶
artifact_type: {{artifact_type}}artifact_id: {{artifact_id}}goal: {{goal}}scope_glob: {{scope_glob}}
Inputs¶
- artifact_type: one of skill, prompt, shim
- artifact_id: lowercase kebab-case id
- goal: one-sentence capability statement
- optional scope_glob for shim outputs
Required References¶
Load only what matches the requested artifact:
- Authoring workflow and validation policy: Authoring Guide
- Prompt metadata and structure: Prompt Contract
- Skill metadata and structure (only for skill outputs): Skill Contract
- Thin shim mechanics and path binding: Skill Usage Mechanics
- Copilot resource attachment behavior: Copilot MCP Mechanics
Workflow¶
- Validate required inputs and ask one clarifying question if any required input is missing.
- Keep ids and slugs aligned with folder names and frontmatter ids.
- Enforce artifact_type enum values exactly: skill, prompt, shim.
- If artifact_type is outside the enum, ask one correction question and stop before generating output.
- Apply YAML safety rules for frontmatter values:
- quote values containing
: - prefer quotes for punctuation-heavy scalars
- use block scalars for multiline descriptions
- Run immediate validation after frontmatter edits:
uv run zensical builduv run pytest -q- Produce only the requested artifact type.
- Keep guidance deterministic and minimal, with explicit references to source docs.
- If artifact_type is shim:
- bind one applyTo scope to one
skill://<name>/SKILL.mdresource URI - use MCP resource attachment
- inspect the selected skill's
_manifestonly when supporting material is needed - Return created or updated file paths and any validation commands that should be run.
Output Contract¶
Return:
- Files created or updated.
- Which references were used.
- Validation commands and outcomes (or commands to run if execution is not requested).