Stakeholder update

Skill gmarmat/claude-pm-kit/.claude/skills/stakeholder-update

[PM Twin] Generate product status update from recent activity — git history, feature progress, metrics.From its SKILL.md

Install

npx -y skills add gmarmat/claude-pm-kit --skill stakeholder-update

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 609 tokens by cl100k_base, as published. Nobody here has run it

Stakeholder Update — Status Report Generator

Generate a structured product status update from real project data.

Data Sources

Source	What It Provides
`git log`	Recent commits, features shipped, contributors
`docs/arch.md`	Feature index with status (planned/in-progress/done)
`docs/toolkit/roadmap.md`	Sprint progress, upcoming work
`docs/toolkit/metrics.yaml`	KPI current vs target
`docs/toolkit/index.html`	Intelligence Hub link (for context)

Execution Steps

Determine timeframe — weekly (7 days), monthly (30 days), or custom range
Read git log — git log --oneline --since="[date]" for commits in range
Categorize commits — features shipped, bugs fixed, docs updated, infrastructure
Read arch.md — feature index for overall progress
Read metrics — current values if metrics.yaml exists
Generate report

Output Format

# Product Update — [Product Name]
**Period:** [start] to [end] | **Generated:** [date]

## What Shipped
- Feature A: [1 sentence description]
- Feature B: [1 sentence description]
- Bug fix: [what was fixed]

## Key Metrics
| Metric | Current | Target | Trend |
|--------|---------|--------|-------|
| MAU    | 62      | 100    | ↑ +15 |

## In Progress
- Feature C (60% complete — expected [date])
- Feature D (started — expected [date])

## Up Next
- [Next sprint items from roadmap]

## Risks & Blockers
- [Any flagged issues]

## Links
- [Intelligence Hub](docs/toolkit/index.html)
- [Roadmap](docs/toolkit/roadmap.md)

Save to docs/toolkit/updates/YYYY-MM-DD-[period].md

Output Options

Markdown (default) — copy-paste to email, Slack, Notion
HTML — formatted version for browser viewing
Clipboard — copy to clipboard for immediate pasting

Important Rules

Only report real data — never fabricate metrics or progress
Git log is the source of truth — features shipped = commits merged
Flag slippage honestly — if something slipped, say so with context
Keep it short — stakeholders scan, they don't read. Tables over paragraphs.
No sensitive data in updates — don't include API keys, user PII, or internal URLs in shareable updates
Write only to docs/toolkit/updates/ — never modify application code
Check existing updates — read previous updates before generating to avoid repeating old news

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most operations skills give in 609 tokens

Counted across 483 of the 484 authors here whose files we hold, read 2026-08-07

Collect monitoring data throughout the simulationin 14 of 483, across 6 files
Set the random seed for reproducibilityin 14 of 483, across 6 files
Validate simulations against analytical solutionsin 12 of 483, across 4 files
Clarify goals, constraints, and inputsin 11 of 483, across 2 files
Implement contract tests for integration pointsin 11 of 483, across 2 files
Implement strangler fig infrastructure with API gatewayin 11 of 483, across 2 files
Audit modernized components for security vulnerabilitiesin 11 of 483, across 2 files
Avoid Python blocking calls in processesin 10 of 483, across 3 files
Use resource context managers for automatic cleanupin 9 of 483, across 2 files
Maintain consistent time unitsin 9 of 483, across 2 files
Validate outcomes against success criteriain 8 of 483, across 1 file
Analyze the legacy codebase for technical debtin 8 of 483, across 1 file

Said here and by no other author read

categorize recent git commits
read architecture and metrics files
use tables over paragraphs
flag schedule slippage with context
check previous updates before generating
save reports to the updates directory

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.