good-morning
Skill65 starsChanged 7 months agoMITView on GitHub
Present the daily operational briefing and start-of-day context. Use when the user says "good morning", "morning briefing", "what's today look like", "what do I have today", "morning rundown", "what's on my plate", "start of day", "weekly review", "weekly briefing", or "give me the weekly". Do NOT activate for casual mid-conversation "good morning" greetings when already deep in a task.
- Reads credentials
- Sends data out
- Commits and pushes
7 other projects use a version of this.
Adopted by
Most recently taken up by
- troia-51/claude-skillstheir own version, first seen Nov 16, 2026
- jsuchet/jonathan-skills-labtheir own version, first seen Nov 16, 2026
- jalmulla2/claude-plugin-second-brain-kittheir own version, first seen Oct 3, 2026
- risadams/ink-and-agencytheir own version, first seen Jul 7, 2026
- zenianielsen/founder-ostheir own version, first seen Jul 3, 2026
- debs-obrien/learn-agent-skillstheir own version, first seen Mar 24, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- debs-obrien/learn-agent-skills★ 46same name
- risadams/ink-and-agency★ 2same name
- zenianielsen/founder-os★ 2same name
- jsuchet/jonathan-skills-lab★ 1same name
- trifle-labs/skills★ 1same name
- jalmulla2/claude-plugin-second-brain-kit★ 0same name
- troia-51/claude-skills★ 0same name
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 repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-browserSkill
- buildSkill
- debugSkill
- financial-advisorSkill
- generate-image-openaiSkill
- pdfSkill
- planeSkill
- reply-xSkill
- researchSkill
- search-historySkill
- send-emailSkill
- simplify-julesSkill
- skill-creatorSkill
- stop-slopSkill
- thinkSkill
- watch-contactsSkill
- wrap-upSkill
- writeSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
29 rules. 0 are common, 20 are distinctive, and 9 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
20
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Read Briefing.md at the repo root.
- Very specific: line 16
If root copy is missing, try the dated archive: Documents/Field-Notes/$(date +%Y-%m-%d)-Briefing.md.
- Distinctive: line 19
If valid and fresh (or user accepts stale), present per the Presenting section.
- Distinctive: line 20
If invalid (empty, garbled, no header), treat as missing — fall through to Branch B.
- Distinctive: line 24
Check git log for overnight commit:
- Very specific: line 28
If a commit exists for today's date: run git pull origin main, then retry reading Briefing.md.
- Distinctive: line 29
If no overnight commit found: the Cloud task didn't run.
- Very specific: line 92
If QUIZ_DATA block is missing from the briefing, show: "Analytics not in today's briefing — will be live tomorrow."
- Distinctive: line 102
All entries in one table sorted by date, with a category column.
- Distinctive: line 114
After verdicts: act immediately — update Paperclip issue statuses, create issues, note manual follow-ups.
- Distinctive: line 150
If content is part of today's work, overlay a content-ops recommendation:
- Distinctive: line 161
If the packet is thin, ask one prompt from the packet before recommending content work.
- Distinctive: line 162
If [Your Name] wants engagement work, recommend:
- Distinctive: line 168
If [Your Name] wants to revisit a section, loop back — this is a dialogue, not a one-way presentation.
- Distinctive: line 174
If not in briefing, pull live from Gmail:
- Distinctive: line 181
When [Your Name] says "let's do decisions" mid-session or returns to decisions:
- Distinctive: line 191
When [Your Name] says "tell me more about [headline]" or asks about a specific item:
- Very specific: line 193
Search Gmail: python3 Scripts/gmail-read.py --hours 48 and grep for the newsletter name or sender.
- Distinctive: line 195
If Gmail unavailable: restate briefing excerpt with available context.
- Distinctive: line 199
When [Your Name] says "what's happening with [topic]?":
- Distinctive: line 201
Run 2-3 targeted WebSearch queries.
- Very specific: line 203
If sustained research warranted: "Want me to kick off a /research on this?"
- Distinctive: line 207
When [Your Name] says "show me the improvements":
- Very specific: line 209
Read today's improvement scan: Glob for Documents/Field-Notes/YYYY-MM-DD-Improvement-Scan.md.
- Distinctive: line 216
When [Your Name] gives editorial feedback ("I wanted to see X", "Y was noise", "more of this"):
- Distinctive: line 227
After walkthrough, commit any modified files:
- Distinctive: line 255
Ask one grounding prompt if the packet needs [Your Name]'s judgment.
- Very specific: line 256
If useful, recommend the next drafting move in Documents/Content-Pipeline/Drafts/.
- Very specific: line 263
Read Documents/Field-Notes/$YESTERDAY-Briefing.md.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Good Morning Briefing
Interactive companion to the overnight batch. The briefing is pre-generated and saved to Briefing.md (root) and Documents/Field-Notes/YYYY-MM-DD-Briefing.md (archive). This skill reads, presents, and facilitates the interactive walkthrough. It never generates the briefing itself.
Decision Tree
Branch A — Briefing exists
- Read
Briefing.mdat the repo root. - If root copy is missing, try the dated archive:
Documents/Field-Notes/$(date +%Y-%m-%d)-Briefing.md. - Validate: must contain a
# Good Morningheader and be >200 characters. - Staleness check: Extract the date from the
# Good Morning — YYYY-MM-DDheader. If it doesn't match today, flag it: "Heads up — this briefing is from [date], not today. The overnight batch may not have run. Want me to pull a live summary instead?" - If valid and fresh (or user accepts stale), present per the Presenting section.
- If invalid (empty, garbled, no header), treat as missing — fall through to Branch B.
Branch B — Briefing missing or invalid
- Check git log for overnight commit:
git log --oneline -5 --grep="overnight: briefing" - If a commit exists for today's date: run
git pull origin main, then retry readingBriefing.md. If still missing after pull, fall through to fallback. - If no overnight commit found: the Cloud task didn't run. Inform [Your Name] and offer inline fallback.
Fallback (ephemeral, not saved)
Generate a lightweight briefing conversationally from live sources:
- Paperclip:
curl -sf "$PAPERCLIP_API_URL/api/companies/$PAPERCLIP_COMPANY_ID/issues?status=todo,in_progress" -H "Authorization: Bearer $PAPERCLIP_API_KEY"for active issues - Gmail:
Scripts/gmail-read.py --hours 24 - Git:
git log --oneline --since="yesterday"Note that this is ephemeral and won't persist. Recommend checking why the overnight batch didn't run.
Presenting
Structured walkthrough. Complete each step before moving to the next. Most mornings go straight through without looping — the iteration is there when needed, not forced.
Step 1 — Overview
Jules one-liner opener.
Pillars (every morning, always — one bullet each):
- Restate the pillar description first, then connect it to today's reality.
- Purpose: do work that visibly impacts real people, and be known for it
- Profit: build reputation that opens revenue paths
- People: be around people I enjoy, regularly
- Health: maintain and deepen — the foundation is solid
Project Overview — one bullet per tracked module, always. Modules are Product, Infrastructure, Content, Speaking, Personal. If nothing moved, say so explicitly. Keep it scannable and bullet-first, not paragraph-first. Source from briefing's activity section.
Example format:
- Product — Interest Finder launched. Partner invite polished and deployed.
- Infrastructure — 1Password TCC prompts eliminated. Morning batch wake time fixed.
- Speaking — Nothing moved yesterday.
Quiz Analytics — Parse the <!-- QUIZ_DATA --> JSON block from the briefing. If present, render:
- Metric cards (table format, one row):
- Starts: current value + day-over-day delta % (e.g., "385 starts (+12%)")
- Completion Rate: current + delta in pp (e.g., "33% completion (-2.1pp)")
- Email Signups: current + delta (e.g., "12 signups (+3)")
- Partner Invites: current value
- Interest Finder: started / completed / results viewed + ratings breakdown
- Funnel — render the
funnelarray as a bullet list with dropoff percentages between each step. If entries include agroupfield, present Quiz first and then any Interest Finder branch separately under the same funnel heading:
Flag the largest dropoff step.- Landing Page: 385 - Clicked Take Quiz: 167 (43% of landing) - Consent Given: 161 (96% of clicks) - Quiz Started: 159 (99% of consent) - Stage 2: 128 (81% of started) <- biggest dropoff - Results: 127 (99% of stage 2) - Survey Done: 108 (85% of results) - Email Signup: 12 (11% of survey) - Partner Invite: 1 (0.9% of survey) - Interest Finder CTA: 6 - Interest Finder Started: 6 (100% of CTA) - Interest Finder Completed: 6 (100% of started) - Interest Results Viewed: 6 (100% of completed) - Archetype distribution — top 3 from the
archetypesarray with percentages. - Survey highlights — top motivation, top challenge, and any notable
wish_existedfree-text responses, using bullets instead of prose wherever possible.
If QUIZ_DATA block is missing from the briefing, show: "Analytics not in today's briefing — will be live tomorrow."
Step 2 — Timeline
Consolidates deadlines, waiting-on items, and actions needed into one date-sorted view. Three categories in a single table:
Deadlines — items due within 7 days. Flag today/overdue with warning emoji. Waiting On — external blockers with expected resolution dates (ball not in [Your Name]'s court). Actions Needed — things only [Your Name] can do (reviews, approvals, manual tasks).
All entries in one table sorted by date, with a category column. Link: "Full details in today's briefing."
Step 3 — Decisions
Present ALL decisions from the briefing's Decisions Pending section as a single batched AskUserQuestion. Each decision must be fully self-contained:
- What triggered it
- What changes if approved vs rejected
- Recommended option labeled "(Recommended)"
- Risk + reversibility
Link: "Full context in today's briefing."
After verdicts: act immediately — update Paperclip issue statuses, create issues, note manual follow-ups.
Step 4 — Proposals
Separate batched AskUserQuestion — different register from strategic decisions. Two sources combined:
Retro proposals — Read Documents/Field-Notes/YYYY-MM-DD-Retro-Proposals.md (today, fall back to most recent). Each proposal: what it changes, why, config delta if applicable, recommendation. Options: Approve / Reject / Defer.
Improvement radar proposed changes — from the briefing's Improvement Radar section, surface items that recommend adoption or have actionable config changes. Each item: what it changes, why, recommendation. Options: Adopt / Defer / Dismiss.
- Adopt → create Paperclip issue
- Dismiss → append to
Documents/Field-Notes/Logs/improvement-scan-seen.jsonlwith"dismissed": true
Links: "Full retro detail in today's briefing. Full improvement scores in today's briefing."
On Approve (retro): queue for implementation (not done during morning).
Skip this step silently if no retro file exists and no improvement items have proposed changes.
Step 5 — Pending Review
Items with status in_review in Paperclip. Show each with enough context to decide. This step reviews existing issues only; do not create new Paperclip issues from session-report open items during the morning flow.
- Cancel — PATCH status to
cancelled - Done — PATCH status to
done - Schedule — assign to project + set priority + move to
todo
Link: "Full list in today's briefing."
Skip if empty.
Step 6 — Day Plan + Content Ops + Iterate
Synthesize everything above into a concrete recommendation for today:
- 2-3 priorities in order
- First action for each (specific enough to start immediately)
- Flag any conflicts or tradeoffs
If content is part of today's work, overlay a content-ops recommendation:
- Generate or refresh the daily content packet:
python3 .claude/scripts/generate-content-packet.py --stdout - Surface:
- one recommended anchor article
- one LinkedIn post topic
- one X original topic
- recent source highlights from actual work
- If the packet is thin, ask one prompt from the packet before recommending content work.
- If [Your Name] wants engagement work, recommend:
watch-contactsfor X reply scouting- manual-first LinkedIn engagement based on tracked accounts and current priorities
Then: "Does this feel right, or do you want to adjust anything?"
If [Your Name] wants to revisit a section, loop back — this is a dialogue, not a one-way presentation. Most days this step closes the morning. Occasionally it surfaces something that needs another pass at decisions or priorities. Follow the thread.
Step 7 — Newsletters & AI Headlines
Show only Must-Read items (1-3 max) with one-liner + link each. Then: "Full newsletter list in today's briefing."
If not in briefing, pull live from Gmail:
python3 Scripts/gmail-read.py --newsletters --hours 24Decisions Walkthrough
When [Your Name] says "let's do decisions" mid-session or returns to decisions:
- Parse briefing Decisions Pending section for each item.
- Batch all decisions into a single AskUserQuestion with full context per decision.
- On Approve/Reject: search Paperclip (
curl -sf "$PAPERCLIP_API_URL/api/companies/$PAPERCLIP_COMPANY_ID/issues?q=<keyword>" -H "Authorization: Bearer $PAPERCLIP_API_KEY"), update status viacurl -sf -X PATCH "$PAPERCLIP_API_URL/api/issues/<issueId>" -H "Authorization: Bearer $PAPERCLIP_API_KEY" -H "Content-Type: application/json" -d '{"status":"<new-status>"}'. If no issue found, note it. - On Defer: note reason, move on.
- On Discuss: advisory register, think it through, return for verdict.
Newsletter Drill-Down
When [Your Name] says "tell me more about [headline]" or asks about a specific item:
- Search Gmail:
python3 Scripts/gmail-read.py --hours 48and grep for the newsletter name or sender. - Expand the relevant section — full context, links, implications for our work.
- If Gmail unavailable: restate briefing excerpt with available context.
AI News Deep Dive
When [Your Name] says "what's happening with [topic]?":
- Run 2-3 targeted WebSearch queries.
- Synthesize: what happened, why it matters, implications for our work.
- If sustained research warranted: "Want me to kick off a
/researchon this?"
Improvement Radar Review
When [Your Name] says "show me the improvements":
- Read today's improvement scan: Glob for
Documents/Field-Notes/YYYY-MM-DD-Improvement-Scan.md. - Fall back to most recent if today's missing.
- Walk through Top 5. For each: Action / Defer / Dismiss.
- Summarize: "Actioned N, deferred N, dismissed N."
Taste Calibration
When [Your Name] gives editorial feedback ("I wanted to see X", "Y was noise", "more of this"):
- Append to
Documents/Field-Notes/Logs/AI-Section-Calibration.md:## YYYY-MM-DD - [feedback note] - Acknowledge: "Noted. That'll shape future briefings."
Morning Actions
After walkthrough, commit any modified files:
git add Documents/Field-Notes/Logs/AI-Section-Calibration.md
git add Documents/Field-Notes/Logs/improvement-scan-seen.jsonl
git commit -m "morning: walkthrough actions $(date +%Y-%m-%d)"
git push origin mainStage specific files only. Only commit files that were actually modified.
Follow-Up Handling
Focus synthesis
"What should I focus on?" — Synthesize Day Plan output from Step 6 into 2-3 crisp priorities with concrete next actions.
Content packet
"What should I write?" / "Give me the content plan for today":
- Run:
python3 .claude/scripts/generate-content-packet.py --stdout - Present:
- recommended anchor article
- recommended LinkedIn post
- recommended X post
- recent proof points and source highlights
- Ask one grounding prompt if the packet needs [Your Name]'s judgment.
- If useful, recommend the next drafting move in
Documents/Content-Pipeline/Drafts/.
Yesterday's briefing
"What happened yesterday?":
YESTERDAY=$(date -v-1d +%Y-%m-%d)Read Documents/Field-Notes/$YESTERDAY-Briefing.md. Fall back to git log.
Retro proposals
"Show me the retro" — Read Documents/Field-Notes/YYYY-MM-DD-Retro-Proposals.md (today, fall back to most recent).
Quiz drill-down
"How's the quiz doing?" / "Tell me more about the analytics":
- Parse the
<!-- QUIZ_DATA -->JSON block from the briefing. - Render full metric cards with day-over-day deltas (starts, completion rate, email signups, partner invites).
- Render complete funnel with dropoff analysis — flag the biggest dropoff and any anomalies vs baseline (76.6% completion, 4.6% email rate).
- Show full archetype distribution (all archetypes, not just top 3) with percentages and counts.
- Show survey data: experience level breakdown, motivation breakdown, biggest challenge breakdown, and
wish_existedfree-text responses. - Compare to prior day if
priorvalues exist in QUIZ_DATA. - Link to HTML report if it exists:
open ~/Active-Work/Documents/Field-Notes/$(date +%Y-%m-%d)-Analytics-Report.html - Offer: "Want me to pull live data? I can run
make quiz-report-latestfor a fresh snapshot."
Error Cases
- Briefing.md missing + no overnight commit — Offer ephemeral fallback. Don't save to disk.
- Gmail unavailable — Newsletter step: note "(Gmail unavailable)", use briefing AI section only. Drill-down degrades to briefing excerpt.
- Paperclip unavailable — Record verdicts, list what needs manual Paperclip update.
- Improvement scan missing — Skip Step 4 improvement items, note it.
- Analytics missing from briefing — Show placeholder, note it'll be live when overnight batch includes it.
- Empty briefing file — Treat as missing (Branch B).
- Retro file missing — Skip retro portion of Step 4 silently.
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.

