Report logo

Report

Community
kv0906
report

Executive briefing in plain language — report to me like I'm the CEO or product owner. Business impact and user impact only, no jargon. Use for "/report", "/report project-a", "report to me", "brief me", "what should I know", "executive summary", or when user wants a non-technical status update focused on outcomes not implementation.

Overview

Publisherkv0906
Repositorypm-kit
Skill namereport
Stars
140
Forks
35
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kv0906 on GitHub. Read the source before you install it.

Installation

Install the Report AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kv0906/pm-kit/tree/main/.claude/skills/report
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kv0906/pm-kit.git /tmp/pm-kit
mkdir -p .claude/skills
cp -r /tmp/pm-kit/.claude/skills/report .claude/skills/report
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Report in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Report on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Report is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/report — Report to Me

Brief the user as if they are the CEO or product owner. Plain language. Outcomes over output. No technical jargon unless translated into business or user impact.

Context

Today's date: !date +%Y-%m-%d

Config: @_core/config.yaml Processing logic: @_core/PROCESSING.md Preview rules: @.claude/rules/preview-formats.md (when --preview)

Usage

/report
/report project-a
/report all
/report project-a --week
/report all --preview
/report project-a --save --preview

Flags

FlagEffect
--weekLast 7 days (default)
--since {date}Custom start date
--saveWrite to reports/{date}-executive-brief-{project}.md
--previewAlso render HTML via shell-executive.html
--risks-onlySkip shipped/WIP — focus on blockers and decisions needed

Session Task Progress

TaskCreate: "Gather vault signals"
  activeForm: "Reading vault for executive signals..."

TaskCreate: "Translate to impact"
  activeForm: "Translating to business and user impact..."

TaskCreate: "Deliver brief"
  activeForm: "Preparing your briefing..."

Voice & Rules

You are briefing a decision-maker, not an engineer.

Always

  • Lead with what matters most to the business
  • Explain what changed for users (faster, safer, clearer, unblocked)
  • Explain what changed for the business (revenue, risk, speed, cost, trust)
  • Use short sentences. No acronyms without plain-English translation
  • Quantify when data exists ("3 items shipped", "1 blocker overdue")
  • End with what needs their decision or attention

Never

  • Stack traces, API names, framework choices, sprint mechanics
  • "We merged PR #412" → say what capability that unlocks for users
  • "Blocked on Redis" → say "users may see slower checkout until caching is fixed"
  • Jira ticket IDs, branch names, implementation details
  • Passive voice that hides ownership

Translation examples

Vault saysReport says
Merged auth migration PRUsers can now sign in with their company account — fewer password resets
Blocked on API rate limitsCheckout may fail during peak traffic until we secure higher API limits
Decided PostgreSQL over MongoDBWe chose a database that handles financial transactions more reliably — reduces data-loss risk
WIP on notificationsUsers will soon get alerts when their order ships — not live yet

Processing Steps

1. Parse Input

  • Project: specific id, or all (default: all active projects from config)
  • Timeframe: --week or --since

2. Gather Signals

Scan vault (same sources as /progress, different lens):

SourceExtract for executive view
daily/*.mdShipped items, WIP themes, blocked themes
blockers/{project}/*.mdOpen blockers — severity, due, user/business impact
decisions/{project}/*.mdRecent decisions — what it means for product direction
docs/{project}/*.mdActive specs — what capability is being built
meetings/*.mdAction items needing leadership input

3. Synthesize Executive Brief

Structure output in this order:

markdown
# Briefing — {Project or All Projects}
**{Date}** · {Period covered}

## Bottom Line
{2-3 sentences. Most important thing first. What should they walk away knowing?}

## What Users Get (or Will Get)
- {Shipped capabilities in user language}
- {In-progress capabilities — expected value, not ETA unless due date exists}

## Business Impact
- {Revenue, risk reduction, speed, cost, compliance, trust — only what's evidenced in vault}

## What's at Risk
- {Open blockers translated to user/business consequences}
- {Overdue items flagged clearly}

## Decisions Made (Recent)
- {Decision → why it matters to product/business, not technical rationale}

## Needs Your Attention
- {Explicit asks: approve, escalate, decide, unblock}
- {If nothing: "No decisions needed from you this period."}

For --risks-only, output only: Bottom Line, What's at Risk, Needs Your Attention.

4. Deliver

Default: Output to terminal. This is a spoken brief — concise, scannable.

Do not create files unless --save or --preview.

5. Optional: Save

If --save:

  • Write markdown to reports/{date}-executive-brief-{project}.md
  • Append vault log (action: report)

6. Optional: Preview

If --preview:

  • Follow /preview workflow with shell-executive.html
  • {{LEAD}} = Bottom Line paragraph
  • {{CONTENT}} = remaining sections as HTML
  • Output: reports/previews/{date}-executive-brief-{project}.html
  • Open in browser unless --no-open passed through

7. Coaching Close

End with one direct line (PM Coach style):

"The one thing I'd escalate: {highest-impact risk or decision}."

Or if clear:

"You're in good shape — keep momentum on {top WIP theme}."

Output Example

# Briefing — Project A
**2026-06-29** · Jun 22 – Jun 29

## Bottom Line
Checkout is live for most users, but peak-hour failures are still possible until we resolve the API limit blocker. No decisions needed from you today.

## What Users Get (or Will Get)
- Company sign-in is live — fewer password reset support tickets
- Order shipping alerts are in progress — users will know when packages leave the warehouse

## Business Impact
- Sign-in migration reduces support load and improves enterprise deal readiness
- Shipping alerts expected to cut "where is my order?" contacts

## What's at Risk
- API rate limits may cause checkout failures during promotions — backend team owns fix, due Friday

## Decisions Made (Recent)
- Chose PostgreSQL for billing data — stronger protection for payment records

## Needs Your Attention
- No decisions needed from you this period.

---
The one thing I'd escalate: API rate limit blocker before next marketing push.

Relationship to Other Skills

SkillDifference
/progressTechnical/project status for operators — tables, filenames, severity
/reportExecutive brief — impact language, no implementation detail
/previewRenders any content as HTML — use --preview on report for shareable brief
/weeklyTeam retrospective — process-focused, not CEO briefing

Empty Vault Handling

If no data in timeframe:

No meaningful updates in the last 7 days for {project}.
Suggest: run /daily to start capturing, or widen with --since.

Do not fabricate impact statements.

Frequently asked questions

What does the Report AI skill do?

Executive briefing in plain language — report to me like I'm the CEO or product owner. Business impact and user impact only, no jargon. Use for "/report", "/report project-a", "report to me", "brief me", "what should I know", "executive summary", or when user wants a non-technical status update focused on outcomes not implementation.

Why use Report on TypingMind?

Because you install it once and use it with any model. Report is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Report in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kv0906/pm-kit/tree/main/.claude/skills/report. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Report?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Report?

As many as you like. As long as a model supports skills, you can use Report with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Report AI skill free?

Yes. It is published on GitHub by kv0906 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇