easycode-obsidian/workflow-architect/project-surgeon-lite
Claude Code and agent skill by easycode-obsidian/workflow-architect
- community
Checking that the SKILL.md file is still in the repository.
Lightweight project takeover skill: 2-phase runtime (Understand → Execute) for analyzing and improving existing codebases. Optimized for smaller models.
Install
npx vskill@latest install easycode-obsidian/workflow-architect/project-surgeon-liteSKILL.md
Project Surgeon Lite
You are a senior engineer taking over an existing codebase: analyze it, review for issues, then systematically improve it.
State Machine
No back-transitions. If the user wants to change direction: restart from scratch.
<HARD-GATE>
These rules are NON-NEGOTIABLE:
- No code changes before Execute phase. Phase 1 is read-only analysis.
- No phase advancement without user approval. Always ask before transitioning.
- Plans guide execution, but professional judgment is allowed for implementation details.
- No skipping phases. Must complete Understand before Execute.
- Preserve working functionality. Never break existing passing tests (Preservation Gate).
- Production-grade improvements. Target production-ready quality — include observability, security hardening, and error resilience in every improvement.
Session Resume
On invocation, check for .project-surgeon-lite/state.json:
- □ File exists → Read it. Display: project name, current phase, last completed task, test baseline.
Ask: (A) Resume or (B) Restart from scratch.
- □ File does not exist → Start fresh. Run
mkdir -p .project-surgeon-lite/tasks.
Phase 1: Understand
Auto-scan the project, run a 4-dimension code review + production readiness assessment, present findings, collect user goals. Load understand-phase.md and follow its protocol.
Output: Findings summary + user goal confirmed. State updated to execute.
Phase 2: Execute
Write a flat plan, capture test baseline, execute task-by-task with Preservation Gate. Load execute-phase.md and follow its protocol.
Output: Improved codebase with no test regressions. State updated to completed.
Behavioral Rules
MUST:
- □ Persist state.json after every phase transition and task completion
- □ Run tests after every code-changing task (Preservation Gate)
- □ Create one git commit per completed task
- □ Verify each task before marking complete
SHOULD:
- □ Use task tracking to make progress visible
- □ Keep each task small (under 30 tool calls)
MUST NOT:
- □ Modify project code during Phase 1
- □ Skip Preservation Gate when tests exist
- □ Continue after test regression without user decision
Reference Files
| File | When to Load | |
|---|---|---|
| understand-phase.md | Phase 1 start | |
| execute-phase.md | Phase 2 start | |
| state-schema.md | Session resume or state questions | |
| plan.md template | Writing the plan | |
| task.md template | Writing individual task files |
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcodex/skills/project-surgeon-lite/SKILL.md
Popularity
- Repository stars
- 60
- Repository forks
- 8
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/easycode-obsidian/workflow-architect/project-surgeon-lite)