- Fixed description: 'Managed Cluster Platform' → 'Model Context Protocol'
- MCP = AI assistant integration server, not cluster management
- Updated root SKILL.md: Added (EXPERIMENTAL) flag to glab-mcp entry
- Updated help output wording in references/commands.md to match glab 1.85.0
- Changed experimental notice: 'might be broken' → 'not ready for production use'
Fixes#23 - glab-mcp had completely wrong description causing
discoverability issues for users searching for Model Context Protocol
or AI assistant integration features.
Co-authored-by: Steven (Bot) <steven@winkintel.com>
- Declare required binary: glab
- Declare optional binary: cosign (for attestation features)
- Add notes about GitLab authentication requirements
- Document potential sensitive file access (SSH keys, Docker config)
Fixes#21 - ClawHub was flagging skill as suspicious due to
mismatch between claimed requirements (none) and actual
requirements/sensitive file access. This update provides
transparency about what the skill needs and accesses.
Co-authored-by: Steven (Bot) <steven@winkintel.com>
Per OpenClaw skill-creator guide:
> A skill should only contain essential files that directly support
> its functionality. Do NOT create extraneous documentation or
> auxiliary files.
RELEASE_NOTES_BEST_PRACTICE.md contained development process notes
not needed for AI agent skill functionality.
Kept README.md for GitHub repository UI display.
Closes#17
Co-authored-by: Ubuntu <ubuntu@vps-9755df38.vps.ovh.us>
- Added decision trees to root skill:
* "Should I create an MR or work on an issue first?"
* "Which CI command should I use?" (pipeline vs job level)
* "Clone or fork?" (access and use case guidance)
* "Project vs group labels?" (scope decision tree)
- Enhanced glab-label with decision tree and workflows
- Enhanced glab-job with pipeline vs job decision tree
- Added "Related Skills" sections to all major skills:
* glab-mr → glab-issue, glab-ci, scripts
* glab-issue → glab-mr, glab-label, glab-milestone, glab-iteration, scripts
* glab-ci → glab-job, glab-schedule, glab-variable, glab-mr, scripts
* glab-repo → glab-auth, glab-ssh-key, glab-deploy-key, glab-config, glab-variable, scripts
* glab-auth → glab-config, glab-ssh-key, glab-gpg-key, glab-repo
* glab-label → glab-issue, glab-mr, scripts
* glab-job → glab-ci, glab-variable, glab-schedule, scripts
- All cross-references include relevant automation scripts
Addresses #15 Phase 3 objectives:
✅ Root skill enhanced with decision trees and navigation
✅ 4+ decision trees added to guide command selection
✅ Cross-links added between related skills
✅ "Related Skills" sections improve discoverability
✅ Decision trees provide actionable guidance
Improvements:
- Better skill discovery through cross-linking
- Decision trees reduce "which command?" confusion
- Clear guidance on pipeline vs job, clone vs fork, project vs group labels
- Scripts referenced in related skills for automation opportunities
Co-authored-by: Ubuntu <ubuntu@vps-9755df38.vps.ovh.us>
- Enhanced all skill descriptions with specific triggers and use cases
- Removed duplicate help output from top 5 skill bodies (mr, issue, ci, auth, repo)
- Added actionable workflow sections with real-world examples
- Improved root skill (gitlab-cli-skills) with better organization and common workflows
- Reduced token consumption by ~60-70% in updated skills
- Better alignment with OpenClaw progressive disclosure pattern
Addresses #11 Phase 1 objectives:
✅ All skill descriptions enhanced with triggers
✅ Duplicate content removed from SKILL.md files
✅ Workflows added to: glab-mr, glab-issue, glab-ci, glab-auth, glab-repo
✅ Root skill improved with navigation and common workflows
Skills now follow OpenClaw patterns:
- YAML frontmatter includes triggers
- Progressive disclosure (workflows in SKILL.md, details in references/)
- Concise, actionable content focused on procedural knowledge
Co-authored-by: Ubuntu <ubuntu@vps-9755df38.vps.ovh.us>
Vince Lozada