Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.
.claude/skills/brianrwagner-daily-briefing-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 97% | 0% |
Generates a morning brief from your Obsidian vault. Reads today's action file, scans for unposted content, and fetches weather — all inside a Claude Code session.
No APIs. No paid services. No agent autonomy required. You run it, you get your brief.
Open Claude Code in your vault directory and say:
Run the Daily Briefing Builder skill.Or with context upfront:
Run the Daily Briefing Builder skill. My vault is at /path/to/vault and my city is Ann+Arbor.When this skill is invoked, follow these phases exactly.
Check whether the user has provided:
vault_path — absolute path to their Obsidian vaultcity — city name for weather (wttr.in format, spaces as +)If either is missing, ask before proceeding:
To run your morning brief, I need two things:
1. Your vault path (e.g. /root/obsidian-vault)
2. Your city for weather (e.g. Ann+Arbor or London)Do not proceed to PHASE 2 until both values are confirmed.
Run these shell commands in sequence. Capture all output before formatting.
Step 1 — Today's actions:
bashTODAY=$(date +%Y-%m-%d) VAULT="VAULT_PATH_HERE" ACTIONS_FILE="$VAULT/bambf/tracking/daily-actions/${TODAY}.md" if [ -f "$ACTIONS_FILE" ]; then echo "FILE_FOUND" awk '/## Today.s 3 Actions/{found=1; next} found && /^[0-9]/{print} found && /^##/{exit}' "$ACTIONS_FILE" else echo "FILE_MISSING:$ACTIONS_FILE" fi
Step 2 — Unposted content scan:
bashVAULT="VAULT_PATH_HERE" READY_DIR="$VAULT/content/ready-to-post" if [ -d "$READY_DIR" ]; then find "$READY_DIR" -name "*.md" -printf "%T@ %p\n" 2>/dev/null \ | sort -rn | awk '{print $2}' \ | while read f; do if grep -q '\*\*Posted:\*\* ❌' "$f" 2>/dev/null; then platform=$(echo "$f" | sed "s|.*/ready-to-post/||" | cut -d'/' -f1) title=$(grep -m1 '^[^#\-\*>|` ]' "$f" 2>/dev/null | head -c 100) rel="${f##$VAULT/}" echo "ITEM|$platform|$rel|$title" fi done else echo "DIR_MISSING:$READY_DIR" fi
Step 3 — Weather:
bashcurl -s --max-time 5 "wttr.in/CITY_HERE?format=3" || echo "WEATHER_UNAVAILABLE"
Format and print the brief to the terminal:
☀️ Morning Brief — [Weekday, Month Day]
TODAY'S 3 ACTIONS
[numbered actions, or fallback message if file missing]
READY TO POST ([shown] of [total])
[platform] [title] — [relative file path]
...and X more in the pipeline ← only if total > 5
WEATHER
[wttr.in output or fallback]Formatting rules:
content/ready-to-post/ doesn't exist: No ready-to-post folder foundContent queue is emptyNo actions file for today — create one at bambf/tracking/daily-actions/YYYY-MM-DD.mdWeather unavailable (offline) — do not abort the briefBefore delivering, run this internal check. Fix anything that fails — do not deliver until all 4 pass.
ITEM| lines in Step 2 output. Does the number shown in the brief match? Were any files skipped?☀️ Morning Brief — Friday, February 28
TODAY'S 3 ACTIONS
1. Finish Q1 content calendar
2. Send invoice to BAMBF client
3. Publish LinkedIn post on AI ops
READY TO POST (5 of 9)
[linkedin] Nobody talks about what happens when your AI system fails... — content/ready-to-post/linkedin/ai-ops-failure.md
[twitter] The overnight ops shift is real. We run Scribe at 2am... — content/ready-to-post/twitter/async-ops.md
[newsletter] AI marketing systems that actually work — content/ready-to-post/newsletter/systems-post.md
[linkedin] Three things I stopped doing after deploying agents — content/ready-to-post/linkedin/stopped-doing.md
[twitter] Founders who ignore async AI ops are about to find out why — content/ready-to-post/twitter/ignore-ops.md
...and 4 more in the pipeline
WEATHER
Ann Arbor: ☀️ +42°FExpected path: <vault>/bambf/tracking/daily-actions/YYYY-MM-DD.md
Expected structure:
markdown# Daily Actions — 2026-03-01 ## Today's 3 Actions 1. First priority 2. Second priority 3. Third priority
If you use a different path or heading, tell Claude Code when invoking the skill.
content/ready-to-post/ folder (files must contain **Posted:** ❌ to register as unposted)curl installed (weather fails gracefully without it)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,167 | 12,400 | +2% | 1 | 1 | 0% | 2,059 | 2,235 | +9% | 0 | 0 | — |
case-02 | fail→fail | 17,497 | 12,193 | -30% | 1 | 1 | 0% | 2,494 | 2,565 | +3% | 0 | 0 | — |
case-03 | fail→fail | 6,936 | 10,792 | +56% | 1 | 1 | 0% | 239 | 2,200 | +821% | 0 | 0 | — |
case-04 | fail→pass | 6,636 | 2,249 | -66% | 1 | 1 | 0% | 1,002 | 1,837 | +83% | 0 | 0 | — |
case-05 | pass→pass | 8,605 | 1,929 | -78% | 1 | 1 | 0% | 748 | 1,809 | +142% | 0 | 0 | — |
case-06 | fail→pass | 9,610 | 2,590 | -73% | 1 | 1 | 0% | 1,270 | 1,884 | +48% | 0 | 0 | — |
case-07 | fail→fail | 12,057 | 12,289 | +2% | 1 | 1 | 0% | 1,868 | 2,540 | +36% | 0 | 0 | — |
case-08 | fail→pass | 9,915 | 2,563 | -74% | 1 | 1 | 0% | 1,576 | 1,937 | +23% | 0 | 0 | — |
case-09 | pass→pass | 10,840 | 4,993 | -54% | 1 | 1 | 0% | 1,780 | 2,423 | +36% | 0 | 0 | — |
case-10 | fail→pass | 8,154 | 2,390 | -71% | 1 | 1 | 0% | 1,134 | 1,889 | +67% | 0 | 0 | — |
case-11 | fail→pass | 6,459 | 2,016 | -69% | 1 | 1 | 0% | 950 | 1,867 | +97% | 0 | 0 | — |
case-12 | fail→pass | 11,067 | 2,959 | -73% | 1 | 1 | 0% | 1,637 | 2,021 | +23% | 0 | 0 | — |
case-13 | fail→pass | 10,632 | 1,851 | -83% | 1 | 1 | 0% | 1,738 | 1,746 | +0% | 0 | 0 | — |
case-14 | fail→pass | 5,457 | 1,871 | -66% | 1 | 1 | 0% | 849 | 1,770 | +108% | 0 | 0 | — |
case-15 | pass→pass | 5,342 | 2,069 | -61% | 1 | 1 | 0% | 798 | 1,770 | +122% | 0 | 0 | — |
case-16 | pass→pass | 6,656 | 3,562 | -46% | 1 | 1 | 0% | 1,062 | 2,226 | +110% | 0 | 0 | — |
case-17 | fail→pass | 10,464 | 2,752 | -74% | 1 | 1 | 0% | 1,616 | 1,969 | +22% | 0 | 0 | — |
case-18 | fail→pass | 10,347 | 3,433 | -67% | 1 | 1 | 0% | 1,553 | 1,992 | +28% | 0 | 0 | — |
case-19 | pass→pass | 6,919 | 3,653 | -47% | 1 | 1 | 0% | 1,273 | 2,155 | +69% | 0 | 0 | — |
case-20 | pass→pass | 10,020 | 2,258 | -77% | 1 | 1 | 0% | 1,667 | 1,941 | +16% | 0 | 0 | — |
case-21 | pass→pass | 6,797 | 5,848 | -14% | 1 | 1 | 0% | 1,129 | 2,500 | +121% | 0 | 0 | — |
case-22 | pass→pass | 11,098 | 9,689 | -13% | 1 | 1 | 0% | 2,102 | 3,471 | +65% | 0 | 0 | — |
case-23 | pass→pass | 8,211 | 10,705 | +30% | 1 | 1 | 0% | 1,599 | 2,501 | +56% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +43 percentage points is the difference between those two pass rates over the 19 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.