Skip to content

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

  1. artifact_type: one of skill, prompt, shim
  2. artifact_id: lowercase kebab-case id
  3. goal: one-sentence capability statement
  4. optional scope_glob for shim outputs

Required References

Load only what matches the requested artifact:

  1. Authoring workflow and validation policy: Authoring Guide
  2. Prompt metadata and structure: Prompt Contract
  3. Skill metadata and structure (only for skill outputs): Skill Contract
  4. Thin shim mechanics and path binding: Skill Usage Mechanics
  5. Copilot resource attachment behavior: Copilot MCP Mechanics

Workflow

  1. Validate required inputs and ask one clarifying question if any required input is missing.
  2. Keep ids and slugs aligned with folder names and frontmatter ids.
  3. Enforce artifact_type enum values exactly: skill, prompt, shim.
  4. If artifact_type is outside the enum, ask one correction question and stop before generating output.
  5. Apply YAML safety rules for frontmatter values:
  6. quote values containing :
  7. prefer quotes for punctuation-heavy scalars
  8. use block scalars for multiline descriptions
  9. Run immediate validation after frontmatter edits:
  10. uv run zensical build
  11. uv run pytest -q
  12. Produce only the requested artifact type.
  13. Keep guidance deterministic and minimal, with explicit references to source docs.
  14. If artifact_type is shim:
  15. bind one applyTo scope to one skill://<name>/SKILL.md resource URI
  16. use MCP resource attachment
  17. inspect the selected skill's _manifest only when supporting material is needed
  18. Return created or updated file paths and any validation commands that should be run.

Output Contract

Return:

  1. Files created or updated.
  2. Which references were used.
  3. Validation commands and outcomes (or commands to run if execution is not requested).