/daily-review

name: daily-review
description: "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`."

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 `.claude/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 `.claude/settings.json` 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 goa