agentleFS
Sign inStart free
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/daily-recap/SKILL.md

daily-recap

Skill9 starsChanged 6 months agoMITView on GitHub

End-of-day consolidation — summarize daily log, track belief changes and customer conversations, promote durable facts to MEMORY.md

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If weekly count < 4 by Wednesday or < 6 by Friday — add warning: "Below target.

    line 42
  2. Very specific:

    If daily_minimum.done == false at recap time and no waiver → note neutrally: "GTM не стартовал сегодня.

    line 48
  3. Distinctive:

    If yes — update MEMORY.md.

    line 56
  4. Distinctive:

    If the day was empty AND GTM missed: "Тихий день.

    line 86
  5. Distinctive:

    Follow output preferences from USER.md (language, format, platform constraints).

    line 88
  6. Distinctive:

    Don't fabricate — only from today's entries

    line 93
  7. Distinctive:

    If MEMORY.md was updated — mention: "MEMORY.md updated: [what exactly]"

    line 95
  8. Distinctive:

    If 0 conversations AND 0 belief changes — note factually, offer lower threshold for tomorrow

    line 96

≈ “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

Daily Recap

End-of-day consolidation. Triggered by heartbeat at 21:00-22:00 or manually ("recap the day").

Algorithm

1. Read today's log

Open memory/YYYY-MM-DD.md. If empty or no entries — ask: "Quiet day. Any customer conversations or belief changes to log before we close?" If still nothing → HEARTBEAT_OK.

2. Extract key items

From all entries of the day, compile:

## Daily Recap

**Customer conversations:** X today (Y this week, target 8-12/week)
- [who]: [key insight or outcome]

**Belief changes:** (what shifted in understanding)
- [was] -> [became] (evidence: [what showed it])

**Decisions:** (decisions made today)
- [decision]: [why] -> [what changes]

**Open threads:** (started but not finished)
- [topic]: [what remains to be done]

**Constraint check:** [current constraint] — today [exploit/subordinate/ignore]?

3. Conversation count + Focus status

Count customer conversations from today's log entries. Update memory/heartbeat-state.json field weeklyConversations (increment). If it's Monday — reset to 0.

If weekly count < 4 by Wednesday or < 6 by Friday — add warning: "Below target. What's blocking customer contact?"

Read memory/focus-state.json:

  • GTM minimum today: done/waived/missed
  • Streak: N days
  • Waivers this week: N (list reasons if any)
  • If daily_minimum.done == false at recap time and no waiver → note neutrally: "GTM не стартовал сегодня. Завтра снизим порог."

4. Check for promotion to MEMORY.md

For each belief change, ask:

  • Does this change something in MEMORY.md? (Company, Wedge, PMF Stage, Metrics, Constraint)
  • Is it sufficiently confirmed? (not a single data point)

If yes — update MEMORY.md. Keep MEMORY.md < 3KB.

5. Write recap to daily log

Append the ## Daily Recap block to memory/YYYY-MM-DD.md.

6. Update heartbeat state

Set "lastRecapDate": "YYYY-MM-DD" in memory/heartbeat-state.json.

Telegram Output Format

Day recap:

GTM: [done ✓ / waived (reason) / missed ✗]
Streak: N дн | Waivers: N/week

Conversations: X today (Y/week, target 8-12)
[list if any]

Belief changes: Z
[list — most important]

Decisions: N
[list if any]

Constraint: [exploit/subordinate/ignore today]

If the day was empty AND GTM missed: "Тихий день. GTM не стартовал — завтра снизим порог. Что-нибудь запомнить перед закрытием?"

Follow output preferences from USER.md (language, format, platform constraints).

Rules

  • Max 15 lines for Telegram
  • Don't fabricate — only from today's entries
  • Belief changes > conversations > decisions > threads by importance
  • If MEMORY.md was updated — mention: "MEMORY.md updated: [what exactly]"
  • If 0 conversations AND 0 belief changes — note factually, offer lower threshold for tomorrow

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.

Check your setup, free