Daily Review

<!-- 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:

1. Read .agents/skills/daily-review/AGENT_INSTRUCTIONS.md.
2. Substitute its placeholders ({{TARGET_DATE}}, {{TOMORROW_DATE}}, {{TOMORROW_DATE_PLUS_1}}, {{DAY_NAME}}, {{MONTH}}, {{DD}}, {{YYYY}}).
3. 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.
4. 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 settings reach 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/null

Critical rules:

1. No truncation — list all modified files
2. Today only — use date-based filtering
3. 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-DD matching 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:

1. Map completed tasks to goals: For each task completed today, search semantically:

   qmd query "task description here" --limit 3

   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.

2. Enrich meeting follow-ups: For each meeting today, search for related past discussions:

   qmd query "meeting topic" --limit 5

   Surface any commitments, decisions, or context from previous meetings on the same theme.

3. Priority alignment check: For each weekly priority, search for today's work that advanced it:

   qmd query "priority title/description" --limit 5

   Catch work that moved the needle but wasn't explicitly tagged to the priority.

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. Note: Reminders access never works when Claude Code runs inside the VS Code extension (macOS never shows the permission dialog to that process) — see the known limitation in 06-Resources/Dex_System/Calendar_Setup.md. Do not advise reinstalling or reconfiguring; skip silently.

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. Note: Reminders access never works when Claude Code runs inside the VS Code extension (macOS never shows the permission dialog to that process) — see the known limitation in 06-Resources/Dex_System/Calendar_Setup.md. Do not advise reinstalling or reconfiguring; skip silently.

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:

1. ✅ Prep for Acme meeting — Complete
2. 🔄 Write pricing proposal — In progress (about 60% done)
3. ❌ Reply to Mike — Didn't get to it

Completion rate today: 1 of 3 (33%)

What happened with #3? Should it carry to tomorrow?"