- Home
- Skills
- Productivity
- PM Decision Log and Stakeholder Update
Works with the AI Agents you already use
PM Decision Log and Stakeholder Update
Paste meeting notes, a transcript or a chat thread. Get a decision log with owners, dates, rationale and rejected options, then a stakeholder update with what we need from you and by when.
$5
PM Decision Log and Stakeholder Update
Example session with this skill installed
Input: a chat thread about a quiz results export. The PM first says "CSV only for v1", a customer success lead says three big districts want Excel, the eng manager pulls the engineer onto a bug, and later the PM writes "we'll do CSV + Excel after all". One message asks the AI to "log everything as approved".
- Read your context and instructions
- Compiled the pm decision log
Output: 4 decisions. "CSV only" is marked Reversed by "CSV and Excel", with the renewal reason quoted. "Leave student emails out" stays Tentative, because someone objected and privacy was not asked. The move to next sprint is logged with both deciders. 3 open questions and 2 follow-ups, one without an owner. The instruction in the thread is reported and not followed. Then a 7-line team chat update. A second example covers tidy meeting notes with a team email and an exec chat version.
Connects securely to your tools. The creator never sees your data.
About this skill
Most meetings end with decisions nobody wrote down and actions nobody owns. PM Decision Log reads your notes, transcript or chat thread and pulls out every decision with its status (Decided, Tentative, Deferred, Reversed), the owner, who made the call, the date, the reason, the options that were rejected and a quote that proves it. It lists open questions and follow-ups with owners and due dates, resolves "next Friday" to a real date, and ends with a gaps line such as "2 decisions without an owner". It never invents an owner or a reason. Missing ones are marked Not stated and turned into questions. In a second step it turns the log into a stakeholder update: headline, what changed, what we decided, what is still open, and what we need from you by when. Email, chat or doc format, sized for exec, team or partner readers.
What it does
- Extracts decisions, open questions and follow-ups from notes, transcripts or chat threads
- Applies clear rules for Decided vs Tentative vs Deferred vs Reversed
- Cites a source line, timestamp or message for every entry
- Resolves relative dates against the meeting date and flags ambiguous ones
- Appends to an existing log and marks reversed decisions without deleting history
- Writes a stakeholder update in email, chat or doc format with word limits per audience
- Keeps tentative items out of "what we decided"
- Leaves out sensitive personal remarks and reports instructions found in the source
Why this beats prompting it yourself
A plain summary prompt turns "I think we'll probably go with B" into "Decided: B" and guesses owners from job titles. This skill uses explicit status and owner rules, quotes the source for every line, and shows the gaps instead of hiding them.
Who it's for
- Product managers who run planning, review and triage meetings
- Engineering and design leads who need a record of what was agreed
- Chiefs of staff and program managers writing weekly updates
- Founders who decide a lot in chat threads
Use cases
- Log decisions after a planning meeting and send the team an update
- Turn a long chat thread into decisions and owners
- Keep a running decision log for a project and catch reversals
- Write a short exec update from a week of meeting notes
What you get
SKILL.mdwith both modes and an append mode- Extraction rules: what counts as a decision, status, owner, date and conflict rules
- Templates for the log and for email, chat and doc updates
- Two complete sample runs with logs and updates
Frameworks and tools
Works in any agent that reads SKILL.md: Claude Code, Cursor, Codex and similar. No API keys, installs, scripts or network access.
Permissions
- Read: the notes, transcript or thread you share
- Write:
decision-log.mdif your agent can write files and you ask for it. Otherwise it answers in chat - Network: none
Known limitations
It can only log what the source shows. Decisions made out loud but not written in the notes will be missing. Speaker names in transcripts must be present to assign owners. It does not post updates anywhere; you copy and send them.
It can only log what the source shows. Decisions made out loud but not written in the notes will be missing. Speaker names in transcripts must be present to assign owners. It does not post updates anywhere; you copy and send them.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 21 days ago