thewebcooperative/the-collective-hub
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: The Collective Hub planning documentation

Browse Source
This commit is contained in:
dallensmith
2026-06-05 22:49:03 -04:00
commit 293415f349
29 changed files with 4551 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.roo/rules-skill-writer/5_examples.xml
+77
View File
@@ -0,0 +1,77 @@
<complete_examples>
<example name="create_project_mode_specific_skill">
<scenario>Create a new mode-specific project skill to standardize a workflow in one mode.</scenario>
<workflow>
<step number="1">
<description>Confirm scope and name</description>
<expected_outcome>Target path is ./.roo/skills-&lt;mode&gt;/&lt;skill-name&gt;/SKILL.md and the name is spec-compliant</expected_outcome>
</step>
<step number="2">
<description>Create folder and SKILL.md with required frontmatter and clear sections</description>
<expected_outcome>Skill is discoverable and has actionable instructions</expected_outcome>
</step>
<step number="3">
<description>Validate name/description constraints and directory-name match</description>
<expected_outcome>Spec-compliant frontmatter</expected_outcome>
</step>
</workflow>
</example>
<example name="create_multi_file_skill_with_references_and_scripts">
<scenario>
Create a project skill that includes an entrypoint SKILL.md plus reference material and a validation script.
The goal is progressive disclosure: only read references when needed, and execute scripts for deterministic checks.
</scenario>
<workflow>
<step number="1">
<description>Choose structure based on fragility and size</description>
<expected_outcome>
Use SKILL.md as the entrypoint, references/ for long-lived guidance, and scripts/ for validation/automation.
</expected_outcome>
</step>
<step number="2">
<description>Draft SKILL.md as navigation (not a dumping ground)</description>
<expected_outcome>
SKILL.md contains:
- Frontmatter (name/description)
- When to use / When NOT to use
- A numbered workflow with explicit "read this file when..." pointers
- A "Files" section that links one level deep:
- references/SCHEMA.md (read when needing field definitions)
- references/TROUBLESHOOTING.md (read when validation fails)
- scripts/validate_input.(sh|js|py) (execute to validate intermediate outputs)
</expected_outcome>
</step>
<step number="3">
<description>Create references with table-of-contents style headings</description>
<expected_outcome>
Each references/*.md file starts with a short contents list so the agent can jump to relevant sections.
</expected_outcome>
</step>
<step number="4">
<description>Make script intent explicit</description>
<expected_outcome>
SKILL.md clearly states whether the script should be executed (preferred) or read as reference.
The script produces verifiable output (e.g., JSON report or "OK"/error list) to support feedback loops.
</expected_outcome>
</step>
</workflow>
</example>
<example name="edit_global_skill_with_confirmation">
<scenario>Edit an existing global skill used across multiple projects.</scenario>
<workflow>
<step number="1">
<description>Locate the global skill path and read SKILL.md</description>
<expected_outcome>Exact file to change is known</expected_outcome>
</step>
<step number="2">
<description>Apply the minimal edit and re-check frontmatter constraints</description>
<expected_outcome>Global skill updated safely and remains spec-compliant</expected_outcome>
</step>
</workflow>
</example>
</complete_examples>