daily-review
Skill509 starsChanged 3 months agoMITView on GitHub
Close out the day: what got done vs planned, meeting follow-ups, learnings, and tomorrow's focus. Use when the user says 'review my day', 'wrap up', 'end of day', or it's evening. Also use proactively when the day's work is clearly done. Not for setting up the morning; use `daily-plan`.
18 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- gutohuida/AgentWeavetheir own version, first seen Nov 15, 2026
- mrosano1987/git-daily-reviewtheir own version, first seen Nov 4, 2026
- AN0099/toothpaste-kittheir own version, first seen Oct 24, 2026
- RumbleJack56/skillstheir own version, first seen Oct 20, 2026
- razbakov/skillstheir own version, first seen Oct 17, 2026
- bradautomates/second-braintheir own version, first seen Oct 9, 2026
Used with
Projects with it also use weekly-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- heyitsnoah/claudesidian★ 2.6k13% same
Wrote their own version · 17
- qusong0627/QuantMind★ 1.9ksame name
- zephyrwang6/myskill★ 339same name
- bradautomates/second-brain★ 217same name
- SpaceZephyr/allSkills★ 14same name
- timominkus/obsidian-para-gtd-ai★ 9same name
- razbakov/skills★ 5same name
- gutohuida/AgentWeave★ 4same name
- finger88/my-claude-skills★ 3same name
- RumbleJack56/skills★ 2same name
- AN0099/toothpaste-kit★ 1same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository153 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .claude/plugins/compound-engineering/CLAUDE.mdCLAUDE.md
- .cursor/rules/search-routing.mdcCursor rule
- anthropic-algorithmic-artSkill
- anthropic-brand-guidelinesSkill
- anthropic-doc-coauthoringSkill
- anthropic-docxSkill
- anthropic-frontend-designSkill
- anthropic-internal-commsSkill
- anthropic-mcp-builderSkill
- anthropic-pptxSkill
- anthropic-slack-gif-creatorSkill
- anthropic-theme-factorySkill
- anthropic-webapp-testingSkill
- anthropic-web-artifacts-builderSkill
- anthropic-xlsxSkill
- atlassian-setupSkill
- backup-nowSkill
- backup-restoreSkill
- backup-setupSkill
- calendar-setupSkill
- commitmentsSkill
- create-mcpSkill
- daily-planSkill
- decision-logSkill
- delegate-checkSkill
- dex-backlogSkill
- dex-doctorSkill
- dex-improveSkill
- dex-obsidian-setupSkill
- dex-rollbackSkill
- dex-updateSkill
- dex-whats-newSkill
- diff-profileSkill
- enable-semantic-searchSkill
- getting-startedSkill
- goal-backlogSkill
- google-workspace-setupSkill
- granola-setupSkill
- identity-snapshotSkill
- industry-truthsSkill
- initiative-kickoffSkill
- integrate-mcpSkill
- journalSkill
- manage-capabilitiesSkill
- meeting-closeoutSkill
- meeting-prepSkill
- ms-teams-setupSkill
- pipedrive-setupSkill
- pipeline-syncSkill
- process-meetingsSkill
- product-briefSkill
- project-healthSkill
- prompt-improverSkill
- relationship-radarSkill
- reviewSkill
- save-insightSkill
- scrapeSkill
- skill-scoreSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
45 rules. 0 are common, 29 are distinctive, and 16 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
29
Distinctive
This author's own choices. Worth a look.
16
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run inline in the current conversation by default.
- Distinctive: line 19
Before authoring anything, check for existing day state: today's archived plan, today's completion metrics, and any review or closeout …
- Distinctive: line 23
Do not create a competing review or overwrite the existing author.
- Very specific: line 41
Call the Agent tool with subagent_type: "general-purpose", model: "sonnet", that prompt, and a short description.
- Very specific: line 45
Verify it wrote the draft to 07-Archives/Reviews/Daily_Review_YYYY-MM-DD.md, then run the interactive steps from its findings and complete …
- Very specific: line 52
Use
AGENT_INSTRUCTIONS.mdverbatim: Read the file and pass its content as the subagent prompt, substituting only the placeholders. - Very specific: line 67
Always fall back: If the subagent fails, times out, or returns nothing usable, say so plainly and run the gathering inline from the same …
- Very specific: line 78
Read System/user-profile.yaml → communication section and adapt accordingly.
- Distinctive: line 92
No truncation — list all modified files
- Distinctive: line 94
Verify with user — "These are the files I found.
- Distinctive: line 106
Read the helper's "Meetings processed in catch-up" line and carry the count into the review summary
- Distinctive: line 108
If the helper reported meetings left unstamped or an older backlog, surface those lines.
- Distinctive: line 110
Only if the helper failed and the inline fallback is running does this conversation process meetings itself, following the same brief
- Very specific: line 127
Check 00-Inbox/Meetings/ for meeting notes from today (should now include anything just pulled from the meeting source).
- Distinctive: line 141
Look for connections to quarterly goals or weekly priorities that keyword matching would miss.
- Distinctive: line 159
Add to the Weekly Priorities Progress section if semantic search reveals hidden progress
- Distinctive: line 160
If QMD is not available, skip this step silently — the review works fine without it
- Distinctive: line 166
Check for tasks added from phone during the day that weren't triaged in the morning plan:
- Distinctive: line 176
Run the same triage flow as daily-plan Step 5.10a: infer pillar, confirm with user, create task, mark Reminder complete
- Distinctive: line 177
If user wants to defer: leave in Dex Inbox for tomorrow's daily-plan
- Distinctive: line 181
Setup: If the user hasn't created a "Dex Inbox" Reminders list yet, mention it: "You can capture tasks from your phone by adding them to a …
- Distinctive: line 187
Check if tasks were completed on phone since the morning plan:
- Very specific: line 197
Update task status via Work MCP: update_task_status(task_title="...", status="d")
- Very specific: line 225
Look for today's plan in the resolved daily-plan folder: System/folder-paths.yaml daily_plans if set, otherwise the folder that already …
- Distinctive: line 234
Check if it was completed (look in Tasks.md for completion timestamps)
- Distinctive: line 235
Check if it was started but not finished
- Distinctive: line 236
Check if it was blocked or deferred
- Distinctive: line 254
If tracking completion rates:
- Very specific: line 255
Update System/metrics/daily-completion.md with today's rate
- Very specific: line 330
Read System/Session_Learnings/YYYY-MM-DD.md first.
- Very specific: line 341
Write new entries to System/Session_Learnings/YYYY-MM-DD.md.
- Distinctive: line 349
Check if any learnings should be elevated to pattern files:
- Very specific: line 383
Call list_ideas(status="active", min_score=70) from Improvements MCP
- Distinctive: line 384
Look for ideas that connect to today's work or learnings:
- Distinctive: line 388
If a relevant match exists, surface it briefly:
- Distinctive: line 394
Only show if genuinely connected to today's work (not random)
- Distinctive: line 396
If no connection, skip entirely
- Distinctive: line 397
Keep it to 1-2 lines max
- Very specific: line 407
Call track_event with event_name daily_review_completed and properties:
- Very specific: line 423
Check if today's evening journal exists in 00-Inbox/Journals/
- Distinctive: line 424
If yes: acknowledge it ("You already journaled this evening") and skip to Step 12
- Distinctive: line 425
If no: create it from the template
- Very specific: line 551
After generating the review, call get_skill_ratings(skill_name="daily-review") from Work MCP.
- Distinctive: line 554
Add one line at the end of the review output:
- Very specific: line 559
Then: Run /identity-snapshot silently in the background if System/identity-model.md is older than 7 days (check file mtime).
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Generated from `.claude/skills/daily-review/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->Purpose
Conduct an end-of-day review to capture progress, track what you actually accomplished vs. planned, surface meeting follow-ups, and set up tomorrow.
Execution mode
Run inline in the current conversation by default. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background review or the host has already obtained a specific background-work approval for this review.
Before authoring anything, check for existing day state: today's archived plan, today's completion metrics, and any review or closeout already written for today. If existing day state is present, enter verifier mode. Read it, compare it with the current tasks and meeting evidence, and surface omissions or proposed corrections. Do not create a competing review or overwrite the existing author. Any proposed write still follows the confirmation and write-guard rules below.
Delegated gathering (large-vault scaling)
This skill stays inline as described above: it keeps session awareness, it asks the user the questions, and it owns every interactive step. What it does NOT do inline is the bulk read-gathering, which on a mature vault (hundreds of notes, thousands of indexed messages, a live calendar and multiple integrations) can be large enough to exhaust the main conversation before the useful work starts.
So the gathering phase is delegated to one general-purpose subagent via the
Agent tool, using the self-contained prompt in this skill's
AGENT_INSTRUCTIONS.md:
- Read
.agents/skills/daily-review/AGENT_INSTRUCTIONS.md. - Substitute its placeholders (
{{TARGET_DATE}},{{TOMORROW_DATE}},{{TOMORROW_DATE_PLUS_1}},{{DAY_NAME}},{{MONTH}},{{DD}},{{YYYY}}). - Call the Agent tool with
subagent_type: "general-purpose",model: "sonnet", that prompt, and a short description. The brief is mechanical gathering, so it runs on the fast tier; the judgement calls stay in this conversation on the default model. - Verify it wrote the draft to
07-Archives/Reviews/Daily_Review_YYYY-MM-DD.md, then run the interactive steps from its findings and complete the placeholder sections.
The subagent inherits MCP connections, runs in its own context, and that context is freed when it completes, so only its findings reach this conversation.
Use AGENT_INSTRUCTIONS.md verbatim. Read the file and pass its content as
the subagent prompt, substituting only the placeholders. Do NOT hand-write a
replacement brief from what you already know about the day: that is how steps get
silently dropped, and the omission looks complete because nothing errors. If
context from this conversation is worth adding, APPEND it to the file's content;
never substitute for it.
Two caveats that are load-bearing:
- Do not count on hooks for the subagent's writes. The hooks declared in
this skill's own frontmatter belong to this skill's run, not the subagent's,
and whether the repository-wide hooks in
the host's lifecycle settingsreach a subagent's tool calls is not something a skill should assume either way. Nothing in this skill's gathering depends on a hook; the subagent's writes must stand on their own. - Always fall back. If the subagent fails, times out, or returns nothing
usable, say so plainly and run the gathering inline from the same
AGENT_INSTRUCTIONS.md. A missing subagent must never mean a missing result.
Stays inline: verifier mode, meeting follow-up surfacing, learning capture and categorisation, tomorrow's focus confirmation, the Dex Inbox check (Step 2.55), the retrospective insight (Step 9.5), the evening journal, and the rating prompt. These need the user, so they must not be delegated.
Tone Calibration
Read System/user-profile.yaml → communication section and adapt accordingly.
Step 1: File Discovery
Find files modified TODAY:
TODAY=$(date +%Y-%m-%d)
find . -type f -name "*.md" -newermt "$TODAY 00:00:00" ! -newermt "$TODAY 23:59:59" 2>/dev/nullCritical rules:
- No truncation — list all modified files
- Today only — use date-based filtering
- Verify with user — "These are the files I found. What did you actually work on?"
Step 1.5: Today's Meetings Are Already Processed
Meeting catch-up happens once, inside the gathering helper (its Step 0 processes
every unprocessed meeting since the last one that was, following
process-meetings/AGENT_INSTRUCTIONS.md). Do NOT also run /process-meetings
from this conversation: that ran the whole meeting pass twice per evening, and
the second pass found nothing new.
- Read the helper's "Meetings processed in catch-up" line and carry the count into the review summary
- If the helper reported meetings left unstamped or an older backlog, surface those lines; do not re-run the pass to check them
- Only if the helper failed and the inline fallback is running does this conversation process meetings itself, following the same brief
Step 2: Gather Context
From 03-Tasks/Tasks.md
- Tasks completed today (look for
✅ YYYY-MM-DDmatching today) - Tasks started but not finished
From Weekly Priorities
Read 02-Week_Priorities/Week_Priorities.md for:
- This week's strategic focus
- How today's work connects to weekly priorities
From Recent Meetings
Check 00-Inbox/Meetings/ for meeting notes from today (should now include anything just pulled from the meeting source).
Step 2.5: Semantic Context Enrichment (if QMD available)
Check if semantic search is available by looking for qmd in PATH. If available, use it to map today's work to priorities and goals more intelligently.
What to search:
- Map completed tasks to goals: For each task completed today, search semantically:
Look for connections to quarterly goals or weekly priorities that keyword matching would miss. Example: completing "finalize stakeholder deck" might connect to a goal about "executive engagement strategy" — same concept, different words.qmd query "task description here" --limit 3 - Enrich meeting follow-ups: For each meeting today, search for related past discussions:
Surface any commitments, decisions, or context from previous meetings on the same theme.qmd query "meeting topic" --limit 5 - Priority alignment check: For each weekly priority, search for today's work that advanced it:
Catch work that moved the needle but wasn't explicitly tagged to the priority.qmd query "priority title/description" --limit 5
How to use results:
- Only surface genuinely new connections — if a task was already linked to a goal, don't repeat it
- Merge insights into the Plan vs. Reality section: "Task X also advanced Goal Y (semantic match)"
- Add to the Weekly Priorities Progress section if semantic search reveals hidden progress
- If QMD is not available, skip this step silently — the review works fine without it
Step 2.55: Dex Inbox Check (Phone Captures)
Check for tasks added from phone during the day that weren't triaged in the morning plan:
Use: reminders_list_items(list_name="Dex Inbox")If the tool is unavailable or errors (Apple Reminders phone-capture is optional and may not be set up on this machine): skip this step silently — do not surface an error for a feature the user never enabled. Exception: if the tool says Reminders can't be switched on from inside VS Code, tell the user that one calm line (use the Claude app or Terminal for Reminders). Do not skip that case silently, do not advise reinstalling, and do not raise it again this session.
If items found:
- Surface them: "📱 Phone captures not yet triaged (X items in Dex Inbox)"
- Run the same triage flow as daily-plan Step 5.10a: infer pillar, confirm with user, create task, mark Reminder complete
- If user wants to defer: leave in Dex Inbox for tomorrow's daily-plan
If empty: Skip silently.
Setup: If the user hasn't created a "Dex Inbox" Reminders list yet, mention it: "You can capture tasks from your phone by adding them to a 'Dex Inbox' list in Apple Reminders. They'll show up here automatically."
Step 2.6: Reminders Completion Sync (Dex Today → Dex)
Check if tasks were completed on phone since the morning plan:
Use: reminders_list_completed(list_name="Dex Today")If the tool is unavailable or errors (Apple Reminders sync is optional and may not be set up on this machine): skip this step silently — do not surface an error for a feature the user never enabled. Exception: if the tool says Reminders can't be switched on from inside VS Code, tell the user that one calm line (use the Claude app or Terminal for Reminders). Do not skip that case silently, do not advise reinstalling, and do not raise it again this session.
For each completed item:
- Match to a Dex task by title
- Update task status via Work MCP:
update_task_status(task_title="...", status="d") - Surface what was synced:
"📱 Synced from phone:
- ✅ "Follow up with Hero Coders" — marked done in Dex"
Also check for tasks completed in Dex today that still have active Reminders:
# For each task completed today in Dex, check if a matching Reminder exists
Use: reminders_find_and_complete(list_name="Dex Today", title_query="task title")Clean up completed items:
Use: reminders_clear_completed(list_name="Dex Today")If nothing to sync: Skip silently.
Step 3: Daily Plan Completion Tracking (NEW)
Compare what you planned vs. what you did.
3.1 Find Today's Plan
Look for today's plan in the resolved daily-plan folder: System/folder-paths.yaml daily_plans if set, otherwise the folder that already holds dated daily plans, otherwise 00-Inbox/Daily_Plans/YYYY-MM-DD.md. Do not treat a leftover next_action_date as overdue; only i_owe_date can be overdue.
3.2 Extract Planned Focus
From the "Today's Focus" section, extract the 3 items you planned to focus on.
3.3 Track Completion
For each planned focus item:
- Check if it was completed (look in Tasks.md for completion timestamps)
- Check if it was started but not finished
- Check if it was blocked or deferred
Surface this:
"📊 Daily Plan Completion:
You planned 3 focus items this morning:
- ✅ Prep for Acme meeting — Complete
- 🔄 Write pricing proposal — In progress (about 60% done)
- ❌ Reply to Mike — Didn't get to it
Completion rate today: 1 of 3 (33%)
What happened with #3? Should it carry to tomorrow?"
3.4 Track Over Time (Optional)
If tracking completion rates:
- Update
System/metrics/daily-completion.mdwith today's rate - Surface patterns: "Your average completion rate this week is 67%"
Step 4: Meeting Follow-Up Surfacing (NEW)
For each meeting you had today, surface follow-ups.
4.1 Identify Today's Meetings
From calendar or meeting notes, list meetings that happened today.
4.2 For Each Meeting, Ask:
Use: get_meeting_context(meeting_title="...", attendees=[...])Then prompt:
"📍 You met with Sarah Chen today (Acme Quarterly Review)
Any follow-ups to capture?
- Action items you committed to?
- Things they owe you?
- Decisions that need documentation?
(Type your follow-ups or 'none')"
4.3 Create Follow-Up Tasks
For any follow-ups mentioned, create each one via Work MCP create_task — never by
writing checkboxes into Tasks.md directly (hand-written tasks get no task ID, so
completion sync, dedup, and goal rollups can't track them). Pass:
pillar(inferred per the Task Creation flow, confirmed with the user) andprioritypeople: the page path(s) of who you met (e.g.05-Areas/People/External/Sarah_Chen.md) — this keeps the person page's Related Tasks table in sync automaticallyaccountif the meeting was with a company you trackdue(YYYY-MM-DD) if a date was mentionedweekly_priority_id/goalif the follow-up clearly serves one
Step 5: Progress Assessment
With user-verified information:
- What was accomplished?
- What progress was made against weekly priorities?
- What got stuck or blocked?
- What unexpected things came up?
Step 6: Week Progress Check (Midweek Context)
Use: get_week_progress()Show how today's work moved weekly priorities:
"Week Progress Update:
After today, you're at:
- Priority 1: ✅ Complete (finished today!)
- Priority 2: 🔄 60% (moved from 40%)
- Priority 3: ⚠️ Still not started
You have 2 days left. Tomorrow should focus on Priority 3."
Step 7: Auto-Extract Session Learnings
Read System/Session_Learnings/YYYY-MM-DD.md first. Corrections said during
the day, and obvious corrections/preferences spotted when a session closed,
may already be there as pending entries. Do not write a second copy.
Then scan today's conversation for anything those passes missed:
- Mistakes or corrections — Did something not work as expected?
- Preferences mentioned — Did you express how you like to work?
- Documentation gaps — Were there questions about how the system works?
- Workflow inefficiencies — Did any task take longer than it should?
Write new entries to System/Session_Learnings/YYYY-MM-DD.md.
Then ask: "I captured [N] learnings from today's session (including any already waiting). Anything else you'd like to add?"
Step 8: Categorize Learnings (If Applicable)
Check if any learnings should be elevated to pattern files:
- Recurring mistakes →
06-Resources/Learnings/Mistake_Patterns.md - Workflow preferences →
06-Resources/Learnings/Working_Preferences.md
Get user confirmation before adding.
Step 9: Tomorrow's Setup
Based on:
- Incomplete items from today
- Weekly priorities (especially lagging ones)
- Commitments due tomorrow
- Tomorrow's calendar shape
Suggest 3 focus items for tomorrow:
"Suggested focus for tomorrow (Thursday):
- Priority 3 — It's been untouched all week and you have 2 days left
- Finish pricing proposal — 40% left, should be quick to complete
- Reply to Mike — Carried from today
Tomorrow's shape: Moderate (4 meetings). You have a 2-hour block in the afternoon.
Does this feel right?"
Step 9.5: Retrospective Insight (Innovation Concierge)
At the end of the review, check if there's a relevant backlog idea to surface:
- Call
list_ideas(status="active", min_score=70)from Improvements MCP - Look for ideas that connect to today's work or learnings:
- Did the user work on tasks related to a backlog idea?
- Did learnings captured today strengthen an existing idea?
- Is there a "Why Now?" idea with fresh evidence?
- If a relevant match exists, surface it briefly:
Retrospective Insight: Today's meeting processing struggles connect to idea-027 (RAG-Powered Vault Search) — semantic search could make finding meeting context much faster. Worth exploring? Run
/dex-improve idea-027.
Rules:
- Show at most 1 insight per review
- Only show if genuinely connected to today's work (not random)
- Frame as retrospective — "based on what you just did, here's what could help"
- If no connection, skip entirely
- Keep it to 1-2 lines max
Step 10: Track Usage (Silent)
Call the mark_feature_used tool on the dex-analytics MCP server with daily-review. This ticks the feature's box in System/usage_log.md, which is what /dex-level-up reads to recommend features that have not been tried. It writes locally and sends nothing, so it runs whether or not analytics is enabled.
Analytics (Silent):
Call track_event with event_name daily_review_completed and properties:
wins_countlearnings_count
This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".
Step 11: Evening Journal (If Enabled)
Check System/user-profile.yaml → journaling.evening.
If journaling.evening: true, run the actual /journal evening flow from
.agents/skills/journal/SKILL.md — do not just mention reflection and move on, and do
not substitute a single ad-hoc question. The real flow:
- Check if today's evening journal exists in
00-Inbox/Journals/- If yes: acknowledge it ("You already journaled this evening") and skip to Step 12
- If no: create it from the template
- Pull in this morning's journal intention (if one exists) for reflection
- Guide the user through the evening prompts conversationally — one question at a time, per the journal skill's Prompting Style
- Save the entry, then continue the review
Offer it plainly: "You have evening journaling enabled — want to do a quick reflection before we close the day?" If the user declines, skip without pushing back and continue to Step 12.
If journaling.evening is false or missing: Skip this step silently.
Output Format
Create 07-Archives/Reviews/Daily_Review_YYYY-MM-DD.md:
---
date: YYYY-MM-DD
type: daily-review
plan_completion_rate: X%
---
# Daily Review — [Day], [Month] [DD], [YYYY]
## 📊 Plan vs. Reality
**Planned focus:**
1. [x] [Planned item 1] — ✅ Complete
2. [ ] [Planned item 2] — 🔄 In progress (X%)
3. [ ] [Planned item 3] — ❌ Didn't start
**Completion rate:** X of 3 (X%)
**What happened:** [Brief explanation of deviations]
---
## ✅ Accomplished
- ✓ [Completed item 1]
- ✓ [Completed item 2]
---
## 🔄 Progress Made
| Area | Movement |
|------|----------|
| [Priority 1] | [What moved forward] |
| [Priority 2] | [What moved forward] |
---
## 📊 Weekly Priorities Progress
After today:
- **Priority 1:** [Status/progress] — [emoji]
- **Priority 2:** [Status/progress] — [emoji]
- **Priority 3:** [Status/progress] — [emoji]
**Days remaining this week:** [X]
---
## 📍 Meeting Follow-Ups
### From [Meeting Name]
- [ ] [Follow-up action] — due [date]
- [ ] [Follow-up action]
---
## 💡 Insights
- [Key realization or connection]
- [Important learning]
---
## 🚫 Blocked/Stuck
| Item | Blocker | Status |
|------|---------|--------|
| [Item] | [What's blocking] | [Status] |
---
## ❓ Discovered Questions
1. [New question that emerged]
2. [Thing to research]
---
## 📅 Tomorrow's Focus
Based on weekly priorities and today's carryover:
1. [Priority 1 — tied to weekly focus]
2. [Priority 2]
3. [Priority 3]
**Tomorrow's shape:** [stacked/moderate/open]
---
## 🔄 Open Loops
- [ ] [Thing to remember]
- [ ] [Person to follow up with]
- [ ] **Awaiting:** [What you're waiting on from others]
---
*Generated: [timestamp]*
*Daily completion rate: X%*
*Week progress: X/3 priorities on track*Step 12: Skill Quality Check (Gentle)
After generating the review, call get_skill_ratings(skill_name="daily-review") from Work MCP.
If 3+ ratings exist and average has dropped below 3.0 over the last 5 entries: Add one line at the end of the review output:
"Your daily reviews have been averaging [X]/5 lately. Common note: '[most recent note]'. Want to adjust the format?"
If no ratings exist or average is 3.0+: Say nothing. Don't mention ratings at all.
Then: Run /identity-snapshot silently in the background if System/identity-model.md is older than 7 days (check file mtime). Don't announce this.
MCP Dependencies
| Integration | MCP Server | Tools Used |
| Meetings | Local meeting notes (helper Step 0 catch-up, following process-meetings/AGENT_INSTRUCTIONS.md) | Processes unprocessed meetings once per review |
| Work | work-mcp | list_tasks, get_week_progress, get_commitments_due, analyze_calendar_capacity |
| Calendar | calendar-mcp | calendar_get_today |
| Reminders | calendar-mcp | reminders_list_completed, reminders_find_and_complete, reminders_clear_completed, reminders_list_items |
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
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.

