feat: improve skill scores for monoco-toolkit

[yogesh-tessl]

Hey @IndenScale 👋

"The First L3 Agentic Orchestration Platform". The jump from L2 chat-based agents to autonomous engineering systems with objective Definition of Done, isolated worktrees, and governance-as-code is an ambitious thesis. 1,066 commits and a Linux distro metaphor for AI orchestration show you're building something with real architectural depth. Wanted to suggest a few improvements to the SKILL.md.

I ran your skills through tessl skill review at work and found some targeted improvements. Here's the full before/after:

Skill	Before	After	Change
engineer	36%	94%	+58%
monoco-atom-doc-extract	61%	94%	+33%
principal	43%	74%	+31%

Changes made

Description improvements (biggest impact across all 3 skills):

• engineer (0% → 85%): Rewrote from generic "code generation, testing, and maintenance" role label to a detailed description listing specific Monoco CLI actions (branching, linting, submission) with an explicit "Use when..." clause
• monoco-atom-doc-extract (33% → 100%): Expanded description with concrete file format triggers (.docx, .pptx, .xlsx), specific capabilities (configurable DPI, quality, page ranges), and a "Use when..." clause for document-to-image conversion
• principal (10% → 85%): Replaced abstract jargon ("requirement modeling, system evolution") with concrete actions (transforms requirements into Issues/ADRs, uses 5W2H analysis, prepares handoffs with acceptance criteria) plus explicit trigger guidance

Content improvements:

• engineer (40% → 100%): Consolidated 3 redundant sections (Role Preferences, Mindset, Rules, Compliance) into a single concise Rules section; added copy-paste-ready monoco issue CLI commands at each workflow step; preserved the decision branches table for error recovery
• monoco-atom-doc-extract (73% → 88%): Trimmed unnecessary "When to Use" section; added verify step after extraction; restructured examples to show extract → verify workflow
• principal (50% → 50%): Consolidated redundant role description; streamlined 5W2H into a checklist item; preserved the handoff template and ADR references

Name fixes (validation):

• monoco_atom_doc_convert → monoco-atom-doc-convert (kebab-case)
• monoco_atom_doc_extract → monoco-atom-doc-extract (kebab-case)

I kept this PR focused on the 3 skills with the biggest improvements to keep the diff reviewable. Happy to follow up with reviewer and monoco-atom-doc-convert content improvements in a separate PR if you'd like.

Honest disclosure. I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.

Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me - @yogesh-tessl - if you hit any snags.

Thanks in advance 🙏

[gemini-code-assist]

Code Review

This pull request refactors and updates the skill definitions for the Engineer and Principal agents, as well as the document conversion and extraction atom skills. The Engineer and Principal skills now feature more structured workflows and specific CLI command examples. Additionally, atom skill names were updated to use hyphens. Feedback was provided to improve the markdown formatting in the Principal skill's implementation guide template for better readability.

[gemini-code-assist]

For better readability in the markdown source, consider adding a blank line after the ### Architecture heading. This was present in the previous version and improves separation between the heading and the placeholder text.

Suggested change

	[Key design decisions and component impacts]
	[Key design decisions and component impacts]