agentleFS
chrisblattmanchrisblattman/claudeblattman/skills/todo-review/SKILL.md

todo-review

Skill479 starsChanged 23 days agoMITView on GitHub

Review and consolidate tasks across configured to-do files.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No argument = quick summary (High Priority only)

    line 12
  2. Distinctive:

    Read each file listed in the "File Locations" section below.

    line 19
  3. Distinctive:

    If empty or not "full" → Quick mode

    line 33
  4. Distinctive:

    If "full" → Full mode

    line 34
  5. Distinctive:

    If any changes made, update "Last reviewed" or "Last updated" in affected files.

    line 124
  6. Distinctive:

    If your todo files use different section names, map them here:

    line 128
  7. Distinctive:

    Add more lists as needed:

    line 142
  8. Distinctive:

    Keep output concise — this is for quick status checks

    line 148
  9. Distinctive:

    Don't modify files unless explicitly asked

    line 149
  10. Distinctive:

    Priority section names: If your todo files use section headers like "## Active" instead of "## High Priority", update the Priority Mapping …

    line 162
  11. Distinctive:

    Special sections: If any of your lists have unique sections (e.g., "Decisions Needed", "Waiting On Others"), add them to the Full Mode …

    line 166

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

To-Do Review

v1.1 — Adapted for public use

Review and consolidate to-do items across all your todo files.

Argument: $ARGUMENTS

  • No argument = quick summary (High Priority only)
  • full = comprehensive view (all priority levels)

Instructions

1. Read all TODO files

Read each file listed in the "File Locations" section below.

2. Check for duplicates

Scan all files for potential duplicates by looking for:

  • Same keywords in item titles
  • Items that reference the same tools or systems
  • Tasks that could be consolidated

3. Display consolidated view

Mode Detection

Check $ARGUMENTS:

  • If empty or not "full" → Quick mode
  • If "full" → Full mode

Quick Mode Output (default)

## TO-DO REVIEW — [DATE]

### Summary

| List | High | Medium | Low | **Total** |
|------|------|--------|-----|-----------|
| Main | X | Y | Z | X |
| Work | X | Y | Z | X |
| **TOTAL** | **X** | **Y** | **Z** | **X** |

### Duplicates/Overlaps (N found)

1. **[Topic]**
   - Main: "[Item text]"
   - Work: "[Item text]"
   → Recommend: [Action]

[Or if none: "### Duplicates/Overlaps (None)"]

### High Priority

**Main**
- [ ] Item 1
- [ ] Item 2

**Work**
- [ ] Item 1

### Recently Completed (Last 7 days)
- [date]: Item (List)
- [date]: Item (List)

---
*Quick view. Run `/todo-review full` for Medium/Low priority items.*

Full Mode Output

Show everything from Quick Mode, PLUS add these sections after "Recently Completed":

### Medium Priority

**Main**
- [ ] Item 1
- [ ] Item 2

**Work**
- [ ] Item 1
- [ ] Item 2

### Low Priority

**Main**
- [ ] Item 1

**Work**
- [ ] Item 1
- [ ] Item 2

---
*Full view showing all priorities.*

4. Prompt for action

Options:
1. Reprioritize an item
2. Mark something complete
3. Add a new item (runs /todo-add)
4. Remove a duplicate
5. Done

What would you like to do?

5. Update timestamps

If any changes made, update "Last reviewed" or "Last updated" in affected files.

Priority Mapping

If your todo files use different section names, map them here:

StandardAlternative Names
HighActive, Urgent, Now
MediumUp Next, Soon, Normal
LowSomeday, Later, Backlog

File Locations

Configure your todo files here:

  • Main: ~/Documents/todo.md

Add more lists as needed:

  • Work: ~/Documents/todo-work.md
  • Personal: ~/Documents/todo-personal.md

Notes

  • Keep output concise — this is for quick status checks
  • Don't modify files unless explicitly asked
  • Duplicates section must show count in header and number each duplicate

Customization Points

To set up this skill for your workflow:

  1. File locations: Edit the "File Locations" section to list all your todo files. Each file becomes a named list in the review output. You can have as many as you need.
  2. List display names: The bold label before each path (e.g., "Main", "Work") is what appears in the summary table and section headers. Name them whatever makes sense for you.
  3. Priority section names: If your todo files use section headers like "## Active" instead of "## High Priority", update the Priority Mapping table so the skill knows how to categorize items.
  4. Quick vs. Full mode: By default, quick mode shows only High Priority items. If you want quick mode to also include Medium, move that section up into the Quick Mode Output template.
  5. Special sections: If any of your lists have unique sections (e.g., "Decisions Needed", "Waiting On Others"), add them to the Full Mode Output template so they get surfaced during review.
  6. Summary table columns: The default table shows High/Medium/Low counts. If you use different priority tiers (e.g., P0/P1/P2/P3), adjust the column headers to match.
  7. Action prompt: The action menu references /todo-add for adding new items. If you renamed that skill, update the reference in Step 4.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.