Owner Facing Reporting logo

Owner Facing Reporting

Organization
studio-yebisu
owner-facing-reporting

Use for every progress update, status report, problem explanation, ETA, review, acceptance, or completion report to the operator/owner, especially when they ask “到哪了”, “什么问题”, “做了什么”, “结果呢”, “还要多久”, or “说人话”. Translate technical evidence into visible or operational outcomes before details.

Overview

Publisherstudio-yebisu
Repositoryyaoyorozu-ai-toolbox-slides
Skill nameowner-facing-reporting
Stars
10
Forks
2
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by studio-yebisu on GitHub. Read the source before you install it.

Installation

Install the Owner Facing Reporting 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/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/presentation-delivery/source/upstream/skills/owner-facing-reporting
  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/studio-yebisu/yaoyorozu-ai-toolbox-slides.git /tmp/yaoyorozu-ai-toolbox-slides
mkdir -p .claude/skills
cp -r /tmp/yaoyorozu-ai-toolbox-slides/examples/repositories/presentation-delivery/source/upstream/skills/owner-facing-reporting .claude/skills/owner-facing-reporting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Owner Facing Reporting 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 Owner Facing Reporting 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 Owner Facing Reporting 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.

Owner-Facing Reporting

Role

Report to the person who owns the result, not to another implementation specialist. The owner must be able to decide whether the work is finished, usable, wrong, or waiting on something without decoding logs, stage names, hashes, buffer counts, or internal architecture.

This skill controls communication, not evidence standards. Keep the technical proof, but put it after the human result. If the operator explicitly asks for raw technical detail, still give the direct owner-level answer first, then expand.

Input Contract

Collect the actual goal, current status, final visible or operational result, remaining gap, user impact, next action, and supporting evidence. For visible work, also collect the fresh target-application capture and the agent's own visual inspection result.

Do not treat a build, test, hash, binding count, pipeline stage, or reviewer message as the result itself. Determine what that fact means for what a person can see, use, approve, or reject.

Workflow

  1. Answer the exact question in the first sentence: finished or not, usable or not, and the one decisive reason.
  2. State what the owner can see or do now. For visual work, describe the actual model, pose or motion, framing, materials and color, light and shadow, transparency, clarity, missing content, or visible defect that was personally inspected in the fresh target result.
  3. State what remains and why it matters to the final goal. Translate every technical blocker into its visible or operational consequence.
  4. State the next action and whether the owner needs to do anything. Do not hand ordinary QA back to the owner.
  5. Put implementation details, identifiers, counts, logs, hashes, and file paths last, and include only details that support a decision or were explicitly requested.

Useful translation pattern:

text
technical fact -> what it changes for the owner -> current decision

For time estimates, give a range tied to the remaining concrete outcome and name the largest uncertainty. Do not inflate an estimate by counting already-finished work.

Output Contract

The user-facing report must make these answers obvious in plain language:

  • Is it done?
  • What can the owner see or use right now?
  • What is still wrong or unproved, and what effect does that have?
  • What happens next?
  • Does the owner need to do anything?

Use the smallest readable form, normally one short opening sentence followed by a few short paragraphs or bullets. Do not force the owner to read a machine schema.

When durable audit evidence is requested, use these exact field types so the human report and machine gate cannot disagree:

text
status: exactly completed | partial | in_progress | blocked | failed
opening: string
usable_now: boolean
observable_result: string
remaining_gap: string (use “没有” only when status is completed)
owner_impact: string
next_action: string
owner_action: string
changes_visible: boolean
fresh_result_inspected: boolean
human_observation: string
technical_evidence: list of {fact: string, meaning: string}

Put the description of visible changes in observable_result or human_observation; changes_visible is only the boolean switch that activates fresh visual-inspection requirements.

Final Check

Before sending a report, read only the opening and ask: could a non-technical owner correctly decide whether to accept, wait, or reject? Then confirm that no completion claim exceeds the personally inspected final result and that every remaining gap is stated by its consequence, not merely its internal name.

Enforcement Hooks

  • [RULE:OWNER-001] Lead every work report with the owner-level outcome, current usability, and decisive reason. WHY: the owner must not decode implementation details to learn whether the work is finished.
  • [RULE:OWNER-002] Map every included technical fact to a visible or operational consequence and keep raw identifiers secondary. WHY: technical evidence is useful only when its effect on the owned result is explicit.
  • [RULE:OWNER-003] Keep unfinished, usable, blocked, and fully accepted states distinct, and expose every material remaining gap. WHY: a green intermediate check cannot justify an owner-level completion claim.
  • [RULE:OWNER-004] For visible work, inspect a fresh result in the real target application before reporting what a person can see. WHY: the owner is the final authority but must never be the first visual QA pass.

The executable guard is scripts/check_owner_report.py; its contract is contract-manifest.json.

Positive Example

“还没全部完成。Unity 里三张角色画面已经能正常显示,人物、动作和构图我刚刚都看过;现在只差外部复核给出最终确认,所以暂时不能写成 13 步全部验收完成。你不用操作,我会完成最后复核后再给你最终结果。” Technical proof may follow if it helps.

Negative Example

“Stage 13 gate is green; 897 bindings and three SHA-256 values pass, P28 is pending.” This fails because the owner still does not know what is visibly working, whether the whole goal is done, why the pending item matters, or whether they need to act.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Owner Facing Reporting AI skill do?

Use for every progress update, status report, problem explanation, ETA, review, acceptance, or completion report to the operator/owner, especially when they ask “到哪了”, “什么问题”, “做了什么”, “结果呢”, “还要多久”, or “说人话”. Translate technical evidence into visible or operational outcomes before details.

Why use Owner Facing Reporting on TypingMind?

Because you install it once and use it with any model. Owner Facing Reporting 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 Owner Facing Reporting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/studio-yebisu/yaoyorozu-ai-toolbox-slides/tree/main/examples/repositories/presentation-delivery/source/upstream/skills/owner-facing-reporting. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Owner Facing Reporting?

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 Owner Facing Reporting?

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

Is the Owner Facing Reporting AI skill free?

It is published on GitHub by studio-yebisu. Check the repository for licensing terms. 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 👇