agentleFS
mpaaratingmpaarating/ai-workflow-kit/skills/eod-review/SKILL.md

eod-review

Skill2 starsChanged 8 months agoMITView on GitHub

Review your day, compare plan to outcomes, identify carry-forwards, and prep tomorrow

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    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:

    If no daily page exists, tell the user and offer to create a quick recap from scratch instead.

    line 23
  2. Distinctive:

    If the user worked on things not in the morning plan, note those as Unplanned Work.

    line 38
  3. Distinctive:

    Ask the user to confirm or add anything missing from each category.

    line 51
  4. Distinctive:

    Write a concise end-of-day recap.

    line 55
  5. Distinctive:

    Write the recap into the "End-of-Day Recap" section of today's daily page in {{notes}}.

    line 77
  6. Distinctive:

    Do not overwrite existing content in other sections.

    line 79
  7. Distinctive:

    If the Carry-Forward section has items, merge them into the Tomorrow list (avoid duplicates).

    line 80
  8. Distinctive:

    If the user confirmed that tasks were completed or blocked, offer to update their statuses in {{tasks}}.

    line 84
  9. Distinctive:

    Only update statuses the user explicitly confirmed.

    line 86
  10. Distinctive:

    Don't auto-close anything without confirmation.

    line 87
  11. Distinctive:

    If {{tasks}} is not configured, skip task activity gathering and rely on the user's input.

    line 100
  12. Distinctive:

    Keep the recap concise. Bullet points, not paragraphs.

    line 101

≈ “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

End-of-Day Review

Trigger Phrases

  • "eod review"
  • "end of day"
  • "wrapping up"
  • "done for today"
  • "signing off"
  • "goodnight"

Workflow

Step 1: Read Today's Daily Page

Fetch today's daily page from {{notes}}.

  • If no daily page exists, tell the user and offer to create a quick recap from scratch instead.
  • Extract the Focus Areas section (the morning plan) for comparison.
  • Extract the Working Notes section for context on what actually happened.

Step 2: Gather Task Activity

Query {{tasks}} for tasks that changed status today (completed, moved to in-progress, or newly created).

  • Include: task ID, title, old status, new status.
  • This gives an objective view of what moved, independent of what the user wrote down.

Step 3: Compare Plan to Outcomes

For each item in the morning Focus Areas:

  • Mark as: Done, In Progress, or Not Started.
  • If the user worked on things not in the morning plan, note those as Unplanned Work.

Present this as a simple table or checklist so the user can confirm or correct.

Step 4: Categorize the Day

Organize the day's work into four categories:

  • Shipped: Work that is complete and delivered (merged PRs, closed tickets, sent deliverables).
  • Moved Forward: Work that progressed but isn't done yet (open PRs, in-progress tickets, drafts).
  • Blocked: Work that couldn't progress and needs something from someone else.
  • Carry Forward: Items to pick up tomorrow, with brief context on where they left off.

Ask the user to confirm or add anything missing from each category.

Step 5: Draft the Recap

Write a concise end-of-day recap. Format:

## End-of-Day Recap

### Shipped
- [item] ([task ID if applicable])

### Moved Forward
- [item] — [current state / next step]

### Blocked
- [item] — blocked on [who/what]

### Tomorrow
- [carry-forward item 1]
- [carry-forward item 2]
- [any new priority for tomorrow]

Step 6: Update the Daily Page

Write the recap into the "End-of-Day Recap" section of today's daily page in {{notes}}.

  • Do not overwrite existing content in other sections.
  • If the Carry-Forward section has items, merge them into the Tomorrow list (avoid duplicates).

Step 7: Update Task Statuses (Optional)

If the user confirmed that tasks were completed or blocked, offer to update their statuses in {{tasks}}.

  • Only update statuses the user explicitly confirmed.
  • Don't auto-close anything without confirmation.

Step 8: Closing Summary

Print a brief summary:

  • Count of items shipped vs. carried forward
  • Any blockers that need attention tomorrow morning
  • A one-line note if the day had significant unplanned work (useful for spotting patterns over time)

Notes

  • This skill fills in the "End-of-Day Recap" section created by morning-kickoff.
  • Carry-forward items are picked up by tomorrow's morning-kickoff run.
  • If {{tasks}} is not configured, skip task activity gathering and rely on the user's input.
  • Keep the recap concise. Bullet points, not paragraphs.

Examples

User: "wrapping up"

Assistant: Let me review your day.

Morning plan vs. actual:

  • Auth migration: Done (PR merged)
  • PR #482 review: Done
  • 1:1 prep with Taylor: Not Started (meeting got cancelled)

Unplanned work:

  • Hotfix for login timeout bug (2h)

Here's the recap I'll add to your daily page:

Shipped: Auth migration (ENG-312), PR #482 review Moved Forward: Login timeout hotfix (PR open, needs review) Blocked: Nothing Tomorrow: Taylor 1:1 prep (rescheduled to Thursday), continue hotfix review

Want me to update ENG-312 to Done in your task tracker?

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.