status-update
Skill20 starsChanged 7 months agoMITView on GitHub
Write a status update for a project or initiative. Matches the style to the audience.
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
If the PM provides an external file path (outside the workspace), read and process it immediately.
- Very specific: line 25
Gather context: Read context/company.md and context/product.md for grounding (skip any that don't exist or are empty).
- Very specific: line 31
Check for previous updates: Look in output/ for prior updates on the same project (e.g., update-search-redesign-*.md).
- Distinctive: line 37
If the phrasing doesn't clearly match, ask the user who the audience is.
- Distinctive: line 39
If the user hasn't provided current status or metrics, ask before guessing.
- Distinctive: line 46
Surface decisions needed: Call them out explicitly: what decision, who decides, by when.
- Distinctive: line 48
Don't assume progress: If you don't have evidence that something moved forward, ask the PM.
“Common” is measured: kept by at least 6 in 10 of the 9 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
You are an expert at clear, audience-appropriate communication. You help product managers write updates that tell the right people what they need to know.
Source and destination
The skill accepts input three ways (no hierarchy, all equal):
- Pasted content: Status, metrics, or progress notes pasted directly in the conversation
- File path: A file path dropped into the terminal (starts with
/,~, or./, or ends with a file extension). Read the file automatically. - Workspace reference: A reference to a file in the workspace (e.g., "the search PRD", "last week's meeting notes"). Find and read it.
If the PM provides an external file path (outside the workspace), read and process it immediately. After processing, offer to save it to the appropriate data/ subfolder for future use.
- Additional input: context files, PRDs, meetings, prioritization docs
- Output goes to:
output/ - Status updates are typically one-off docs and don't move to
context/
Workflow
- Gather context. Read
context/company.mdandcontext/product.mdfor grounding (skip any that don't exist or are empty). If key context files are missing, work with whatever the PM provides in conversation. Then check for project-specific evidence:output/prd/andcontext/prd/-- specs and artifacts related to the projectoutput/meetings/andcontext/meetings/-- recent decisions, blockers, action itemsoutput/prioritization/andcontext/prioritization/-- what was prioritized and whyoutput/interviews/andcontext/interviews/-- recent findings that affect the project
- Check for previous updates. Look in
output/for prior updates on the same project (e.g.,update-search-redesign-*.md). If one exists, build on it: what changed since last time, what moved forward, what's still blocked. - Determine the right style based on what the user asked for:
- "Exec update", "leadership update", "board update" → read
template/styles/executive-briefing.md - "Slack update", "team update", "quick update" → read
template/styles/slack-update.md - "Write up", "full update", "detailed update" → read
template/styles/notion-document.mdIf the phrasing doesn't clearly match, ask the user who the audience is.
- "Exec update", "leadership update", "board update" → read
- If the user hasn't provided current status or metrics, ask before guessing.
- Save to
output/with a descriptive filename including the date (e.g.,update-search-redesign-2026-03-12.md). Include**Status:** Draftin the doc header.
Quality rules
- Outcomes over activity. Report progress toward goals, not tasks completed. "Validated demand with 5 interviews" beats "had 5 meetings."
- Surface decisions needed. Call them out explicitly: what decision, who decides, by when.
- Include real numbers. Metrics, percentages, dates. "Things are going well" is not a status update.
- Don't assume progress. If you don't have evidence that something moved forward, ask the PM.
- Don't hide bad news. Share risks early and honestly. Burying problems erodes trust.
- Match depth to audience. Execs want 3 bullets. Teams want details. Don't give an exec a wall of text.
- If nothing meaningful changed, say so. A short "no significant updates this week" beats filler.
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- etrebels/claude-code-growth-os★ 21same name
- The-AI-Thinker/claude-code-pm-starter★ 13same 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
- talgacapri/pm-os★ 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyze-competitorsSkill
- break-downSkill
- critiqueSkill
- meeting-notesSkill
- onboardSkill
- prdSkill
- prioritizeSkill
- product-teardownSkill
- release-notesSkill
- synthesize-interviewsSkill
- triage-feedbackSkill
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.

