walterra/eddoapp/eddo-work
Claude Code and agent skill by walterra/eddoapp
- community
Checking that the SKILL.md file is still in the repository.
Structured work mode for implementing complex tasks with phases. Use when user says "what next?" followed by "let's work on this" or "start working". Provides REFINE, IMPLEMENT, REVIEW, COMPLETE, and GITHUB_PR phases with gates and reflection checklists. Works with eddo-todo for task tracking.
Install
npx vskill@latest install walterra/eddoapp/eddo-workSKILL.md
Eddo Work
Structured implementation phases for complex tasks. Uses eddo-todo for task management.
Related Skills
- eddo-todo: Core task management commands (REQUIRED - load this skill first)
Prerequisites
Load the eddo-todo skill first and set up variables:
File Tracking
Track all files you modify during implementation in the agent:files metadata field (array of relative paths). This enables the Eddo UI to show which files were touched per task.
Update metadata when you modify files:
Get current file list from git:
Trigger Pattern
Critical Rules
- Test every change - never assume fixes work without verification
- Only complete subtasks when FULLY WORKING and VERIFIED
- Never git commit/push without user confirmation
- Follow all workflow phases - no shortcuts
- STOP at gates for user check-in
- MANDATORY: Execute reflection checklist at end of EVERY phase
- MANDATORY: Output reflection results with ✅/❌ for each item
Phase 1: REFINE
Start session:
Investigate:
- Review todo description for context and requirements
- Read relevant codebase files
- Ask clarifying questions if needed
- Define success criteria
- Log surprising findings:
$EDDO note <id> "Discovered X depends on deprecated Y"
Create implementation plan as subtasks:
Why subtasks over markdown checkboxes:
- Each step is a first-class todo (completable, time-trackable)
- Progress visible in UI (X of Y complete)
- Steps appear in
nextcommand when taggedgtd:next
<gate> STOP - Present plan (list subtasks) and ask:
- If no GitHub issue: "1. Create GitHub issue first? 2. Approve plan? (y/n)"
- If issue exists: "Approve implementation plan? (y/n)"
</gate>
Link GitHub issue (REQUIRED if exists):
<reflection> ⚠️ MANDATORY STOP - Output this checklist:
</reflection>
Phase 2: IMPLEMENT
View progress:
Execute subtasks:
Track touched files: After modifying files, update the parent todo's agent:files metadata:
Validate after changes:
- Lint, format, typecheck
- Run automated tests
- Fix issues before continuing
User testing (if applicable):
- Present test steps
- STOP: "Please verify: [test description]. Pass? (y/n)"
Documentation:
- If structure/features changed, propose CLAUDE.md updates
- STOP: "Update CLAUDE.md? (y/n)"
Changeset (if project uses them):
<reflection> ⚠️ MANDATORY STOP - Output this checklist:
</reflection>
Phase 3: REVIEW
Self-assessment:
- Review changes for bugs, edge cases, quality issues
- Log issues found:
$EDDO note $PARENT_ID "Review caught edge case: empty array crashes map()" - Fix any issues found
Visual validation (UI changes):
Read with read tool, compare Expected vs Actual.
Final validation:
Run all checks/tests again.
<gate> STOP: "All tests passing. Any issues to address? (describe or 'none')" </gate>
<reflection> ⚠️ MANDATORY STOP - Output this checklist:
</reflection>
Phase 4: COMPLETE
Verify: All subtasks must be completed.
Finalize file tracking:
Finish session:
Completion:
- If parent has
externalId: Do NOT runcomplete- GitHub sync handles it - If no
externalId:$EDDO complete $PARENT_ID -m "Done"
<gate> STOP: "Task complete! Options:"
- Create PR (closes GitHub issue → auto-completes todo)
- Continue with next todo
- Done for now
</gate>
<reflection> ⚠️ MANDATORY STOP - Output this checklist:
</reflection>
Phase 5: GITHUB_PR
Preflight:
- On
main: STOP, ask to create feature branch - Unstaged changes: STOP, ask what to do
Create PR:
- Title: Follow project's commit conventions
- Description: Concise, reference GitHub issue (e.g., "Closes #123")
- No "generated by" or "co-authored" text
<reflection> ⚠️ MANDATORY STOP - Output this checklist:
</reflection>
Example Flow
Security
- Security scanPassed, 93 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/chat-agent/skills/eddo-work/SKILL.md
Popularity
- Repository stars
- 58
- Repository forks
- 4
- 7-day trend score
- 20
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/walterra/eddoapp/eddo-work)