status-update
Skill2 starsChanged 3 months agoMITView on GitHub
Use when the user says "write my standup", "weekly update for my manager", "end of day wrap", "what did I get done this week", "status update", "update for my boss". Turns rough notes or a pasted activity list into a standup (done, next, blocked by account), a weekly update (highlights, lowlights, asks, renewals, commitments) or an end-of-day wrap. Not for a team lead rolling up several CSMs (use team-rollup) or a note to a customer (use customer-update).
11 other projects use a version of this.
Adopted by
Most recently taken up by
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Robinnnnn/skillstheir own version, first seen Nov 1, 2026
- lost-rob0t/skillstheir own version, first seen Oct 30, 2026
- The-AI-Thinker/claude-code-pm-startertheir own version, first seen Oct 15, 2026
- Baba01hacker666/dummyskillstheir own version, first seen Oct 13, 2026
- tmusser/context-to-action-skillstheir own version, first seen Sep 16, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- etrebels/claude-code-growth-os★ 21same name
- arezous/pm-pilot★ 20same name
- The-AI-Thinker/claude-code-pm-starter★ 13same name
- caidanw/skills★ 11same name
- Robinnnnn/skills★ 4same name
- tmusser/context-to-action-skills★ 2same name
- tines/skills★ 1same name
- Baba01hacker666/dummyskills★ 0same name
- lost-rob0t/skills★ 0same name
- nbirkner/digital-brain★ 0same name
1 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 repository54 other files it gives its agents.
- account-contextSkill
- account-planSkill
- account-reviewSkill
- adoption-planSkill
- advocacy-askSkill
- book-reviewSkill
- book-triageSkill
- business-reviewSkill
- call-prepSkill
- call-recapSkill
- champion-lossSkill
- churn-postmortemSkill
- coachingSkill
- commitmentsSkill
- coverage-modelSkill
- csm-hiringSkill
- csm-rampSkill
- csql-motionSkill
- cs-scorecardSkill
- cs-startSkill
- customer-updateSkill
- day-planSkill
- email-criticSkill
- escalationSkill
- exec-conversationSkill
- expansion-caseSkill
- expansion-scanSkill
- handoffSkill
- hard-conversationSkill
- health-scoreSkill
- internal-askSkill
- invoice-chaseSkill
- mutual-action-planSkill
- nrr-narrativeSkill
- offboardingSkill
- onboarding-planSkill
- one-pagerSkill
- playbook-builderSkill
- portfolio-reviewSkill
- price-increaseSkill
- renewal-forecastSkill
- renewal-negotiationSkill
- renewal-riskSkill
- renewal-runwaySkill
- sales-handoffSkill
- save-planSkill
- stakeholder-mapSkill
- survey-follow-upSkill
- team-rollupSkill
- usage-emailSkill
- value-ledgerSkill
- voice-of-customerSkill
- what-do-i-oweSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
If the user pasted notes or an activity list and said which update (standup, weekly, wrap), go straight to "Do this".
- Distinctive: line 21
If an "Account context" block exists in the conversation, use it.
“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
Status Update
Paste rough notes. Get the update you owe someone, led by outcomes, with the bad news stated plainly and the asks specific.
Start here
If the user pasted notes or an activity list and said which update (standup, weekly, wrap), go straight to "Do this". If the kind is not stated, pick by the day (Friday means weekly, late afternoon means wrap) and say which you chose.
Otherwise ask for these in ONE message, then proceed with whatever comes back:
- Which update, and who reads it
- The notes, in any state: bullets, a task list, call summaries
- Anything that went wrong this period that the reader does not know yet
If an "Account context" block exists in the conversation, use it. If a CRM or mailbox is connected, you may read it. Otherwise use the paste only.
Do this
- Turn activity into outcomes. "Had calls with Orrin" becomes "Orrin sponsor agreed to bring the VP of Ops to the next review". If there was no outcome, say "no movement" rather than dress it up.
- Sort facts from hope. Mark each claim
said(a customer told us, name who),seen(we observed it) orinferred(our read). Hope goes in a line called "My read", never in the outcome. - Put the lowlights in, plainly, each with a plan and a date. Do not bury them under the wins or soften them into "areas of focus".
- Make every ask specific: a named person or team, the action, and a date. If the user cannot name a person, write "[who]" and list it under What I could not check.
- Name the measure on every count (accounts touched, commitments made, renewals with a date inside 90 days). A bare number is dropped.
- Cut to length. Standup and weekly: about 200 words. Wrap: ten lines. Group standup items by account.
- Close with the sources: what was read, and what was not (CRM, usage, tickets, calendar).
Output
Pick the one that matches. Verdict line first, always.
WEEKLY UPDATE: week of [Mon date] to [Fri date] | [n accounts, ARR] (the user's figure)
Bottom line: [one sentence: the state of the book and the one thing needing help]
Highlights (outcomes): 3 to 5, each [account, $, what changed, said/seen]
Lowlights: 3 to 5, each [account, $, what went wrong, plan, date]
Asks: [who], [action], by [date]
Renewals: [n] with a date inside 90 days, $[x]. [account, $, date, fact | my read]
Commitments to customers: [n] made, [n] on time, [n] late, [n] open, next due [date]
Sources: read [..]. Not checked [..].
STANDUP: Done / Doing next / Blocked (name who unblocks), grouped by account
WRAP: Closed today | Slipped (and why) | Carry over | Tomorrow's first threeA filled weekly example is in examples/sample.md. Match its length and tone.
Rules
- Lead with outcomes, not activity. A manager cannot act on "had 11 calls", and activity read as effort invites more activity instead of results.
- Bad news now is cheaper than bad news later. A lowlight that surfaces in the forecast call costs the reader their own credibility upward, so put it in this update with a plan.
- Asks are a name, an action and a date. "Need help with Kestrel" gets sympathy, and "Director, 20 minutes with their practice owner by Fri 13 Nov" gets done.
- Separate what is true from what is hoped. A champion's optimism is a
said, and a renewal "looking good" is a read. Mixing them is how a forecast goes wrong quietly. - Every count names its measure. "6 commitments" is ambiguous, while "6 made, 4 on time, 1 a day late, 1 open" can be checked.
- Say what was not read. An update written from memory looks identical to one written from the CRM, so state the sources and let the reader weigh it.
- Do not pad a quiet week. Short and true beats long and padded, and the reader learns to trust "no movement".
- Credit others by name. A win that depended on support or sales is reported with their name, because the reader checks and the credit is cheap.
Related (only if installed)
what-do-i-owe for the commitments count. team-rollup if the user leads a team. renewal-risk for the read behind a renewal line. internal-ask when an ask needs a fuller case.
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.

