Analyze and prioritize TODO items from TODOS.md. Use when planning work or deciding what to implement next.
Analyze the TODO items in TODOS.md and produce a prioritized list with implementation guidance.
Before starting:
TODOS.md exists in the current working directory. If it does not exist, STOP and ask the user where their project TODOs live.Copy this checklist and track progress:
List TODOs Progress:
- [ ] Step 1: Read TODOS.md
- [ ] Step 2: Read project context (optional)
- [ ] Step 3: Extract TODO items
- [ ] Step 4: Analyze each item
- [ ] Step 5: Sort by priority score
- [ ] Step 6: Output prioritized list
- [ ] Step 7: Interactive Q&A (if items need clarification)
- [ ] Step 8: Update TODOS.md with clarifications
For each TODO item, evaluate:
| Factor | Low | Medium | High | |--------|-----|--------|------| | Requirements Clarity | One-liner with no context, unclear intent | Some details but gaps remain | Detailed spec with acceptance criteria | | Ease of Implementation | Can't assess without clearer requirements | Moderate effort, approach is clear | Straightforward, clear path | | Value to Project (weighted 2×) | Can't assess without clearer requirements | Useful improvement | Core functionality, high impact |
Assessing Value to Project:
If requirements clarity is LOW, do NOT attempt to infer what the item means.
A one-liner TODO like "Add feature X" with no additional context = LOW clarity, regardless of how obvious it might seem.
Priority = ((Clarity + Ease + (Value × 2)) / 4 × 10) × Personal Multiplier
Where each factor is scored 1-3 (Low=1, Medium=2, High=3). Value is weighted 2× because alignment with project goals is the strongest signal for prioritization.
Personal Priority Multiplier:
[priority: N] inline in the TODO item (e.g., [priority: 1.5])[priority: 2] — User considers this twice as important[priority: 0.5] — User considers this half as important[priority: 1.5] — User considers this 50% more importantIf Clarity is LOW, cap the Priority Score at 3/10 maximum (applied before multiplier).
Adjust score based on:
## {N}. {TODO Title}
**Priority Score:** {N}/10 {if multiplier != 1.0: "(base {base}/10 × {multiplier})"}
**Ranking Factors:**
- Requirements Clarity: {Medium|High} — {one sentence explanation}
- Ease of Implementation: {Low|Medium|High} — {one sentence explanation}
- Value to Project: {Low|Medium|High} — {one sentence explanation}
{if multiplier != 1.0: "- Personal Priority: ×{multiplier}"}
**Implementation Notes:**
{2-4 sentences on how to implement: key files to modify, approach, dependencies, estimated scope}
**Open Questions:**
- {Question that would improve requirements clarity}
- {Another question, if applicable}
**Suggested Next Action:** {See rules below}
The "Suggested Next Action" field must follow these rules:
[ready] tag in TODOS.md. Never infer readiness from clarity or detail alone. The user must explicitly mark items as ready.## {N}. {TODO Title}
**Priority Score:** {N}/10 (capped due to unclear requirements{if multiplier != 1.0: ", ×{multiplier} applied"})
**Ranking Factors:**
- Requirements Clarity: **Low** — {explain what's missing: no context, unclear intent, etc.}
- Ease of Implementation: Cannot assess
- Value to Project: Cannot assess
{if multiplier != 1.0: "- Personal Priority: ×{multiplier}"}
**What I understand:** {Brief statement of what little is clear, or "Only the title"}
**What I don't understand:**
- {Specific gap in understanding}
- {Another gap}
**Questions to clarify before proceeding:**
1. {Fundamental question about intent/purpose}
2. {Question about scope}
3. {Question about expected behavior}
**Suggested Next Action:** Clarify requirements first
# TODOS Analysis
**Generated:** {date}
**Items Analyzed:** {count}
**Project:** {project name from specs, or directory name}
---
{Individual item analyses, sorted by priority score}
---
## Summary
| Priority | Item | Score | Multiplier | Next Action |
|----------|------|-------|------------|-------------|
| 1 | {title} | {N}/10 | {×N or —} | {action} |
| 2 | {title} | {N}/10 | {×N or —} | {action} |
| ... | ... | ... | ... | ... |
**Ready to implement ([ready] tagged):** {count}
**Needs clarification:** {count}
**Consider deferring:** {count}
If TODOS.md doesn't exist:
/add-todo to add the first itemIf TODOS.md is empty or contains no TODO items:
/add-todo to add itemsIf TODOS.md uses non-standard format:
If context files (VISION.md, etc.) can't be read:
If priority tag has invalid value:
If Edit tool fails during Q&A updates:
After completing the analysis, verify:
After displaying the prioritized list and summary, use AskUserQuestion to offer the user an interactive session to clarify requirements. All user interactions in this phase MUST use the AskUserQuestion tool — never ask questions via plain text output.
See QA_WORKFLOW.md for the detailed Q&A workflow:
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer