What makes Kai Report Creator V1.23.3 Publish notable?

1.9K downloads. Trust evidence available

How should Kai Report Creator V1.23.3 Publish be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Kai Report Creator V1.23.3 Publish

Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and Eng... Skill: Kai Report Creator V1.23.3 Publish Owner: kaisersong Summary: Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and Eng... Tags: latest:1.23.3 Version history: v1.23.3 | 2026-05-17T09:51:54.143Z | user No-agent eval gate release: release verification now uses fixture skill evals by default, requires no Codex/Cla

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

1.23.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 1.23.3release · observed May 17, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17e36cy6y9drqxrb49xdqh05d83hqde:kai-report-creator

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-kaisersong-kai-report-creator/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: kai-report-creator
description: Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and English equally. Supports generating from raw notes, data, URLs, or an approved plan file. Use for --plan (structure first), --generate (render to HTML), --review (one-pass automatic refinement), --themes (preview styles), --from FILE, --bundle, --export-image flags. Does NOT apply to exporting finished HTML to PPTX/PNG (use kai-html-export) or creating slide decks (use kai-slide-creator).
version: 1.23.3
user-invocable: true
metadata: {"openclaw": {"emoji": "📊"}}
---

# kai-report-creator

Generate single-file HTML reports from source notes or `.report.md` IR. Keep this file as a thin router: load only the references needed for the current path.

## Core Principles

1. **Zero Dependencies** — generated reports are self-contained HTML, with CDN or bundled assets only when needed.
2. **User Provides Data, AI Provides Structure** — never fabricate facts or numbers; use `[数据待填写]` / `[INSERT VALUE]` when data is missing.
3. **Plan Before Generate** — complex reports should become `.report.md` IR first, then HTML.
4. **Progressive Disclosure for AI** — output keeps `report-summary`, section annotations, and component data machine-readable.
5. **Thin Routing Over Prompt Growth** — `SKILL.md` routes work; detailed rules live in references.
6. **Contracts and Gates Beat Prompt Soup** — prefer IR, guard validation, shell tests, and post-render review over adding more prose to this hot path.

## Command Routing

When invoked as `/report [flags] [content]`, parse flags first:

| Flag | Action |
|------|--------|
| `--plan "topic"` | Write `.report.md` IR only. Stop after saving it. |
| `--generate [file]` | Render one `.report.md` IR to HTML. With no file given, treat as IR from context: extract exactly one valid IR block from context. Never render the surrounding conversation. |
| `--review [file]` | Refine an existing HTML report with `references/review-checklist.md`. |
| `--themes` | Write the themes preview HTML. |
| `--from <file>` | If the file starts with frontmatter, treat as IR; otherwise create IR, then render. |
| `--theme <name>` | Override the theme. Built-ins: `corporate-blue`, `minimal`, `dark-tech`, `dark-board`, `data-story`, `newspaper`, `regular-lumen`, `fangsong`. |
| `--template <file>` | Use a custom HTML template. See `references/toc-and-template.md`. |
| `--output <file>` | Save to this path instead of the default. |
| `--bundle` | Inline CDN assets where supported. |
| `--export-image [mode]` | After HTML generation, run `scripts/export-image.py`; mode is `im`, `mobile`, `desktop`, or `all`. |
| no flags + text | Create IR internally, then render HTML. |
| no flags + IR in context | Treat as `--generate` from context. |

Default output filename: `report-<YYYY-MM-DD>-<slug>.html`. Slug: lowercase ASCII, non-alphanumeric to hyphens, collapse

README.md

# kai-report-creator

> You have data, decisions, and deadlines — but decision makers don't have time to read everything. AI can generate reports, but they often look instantly AI-made: template headings, primary color flooding every element, 3-column KPI grids regardless of count. kai-report-creator gives you polished, async-friendly reports in one command: drop a document or URL, pick a theme, and get a single HTML file that survives first-contact reading. Downstream AI agents can also parse it — the output embeds a 3-layer machine-readable structure.
>
> **[See the guide as a report →](https://kaisersong.github.io/kai-report-creator/examples/zh/kai-report-creator-guide.html)** — this document was generated by kai-report-creator itself.

A skill for [Claude Code](https://claude.ai/claude-code) and [OpenClaw](https://openclaw.ai) that turns plain text or structured outlines into polished HTML reports.

English | [简体中文](README.zh-CN.md)

---

## Live Demo

Click any screenshot to open the live demo:

<table>
<tr>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/corporate-blue.html"><img src="templates/screenshots/corporate-blue.png" width="360" alt="corporate-blue"/><br/><b>corporate-blue</b></a><br/><sub>Warm Premium · Business</sub></td>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/minimal.html"><img src="templates/screenshots/minimal.png" width="360" alt="minimal"/><br/><b>minimal</b></a><br/><sub>Research · Academic</sub></td>
</tr>
<tr>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/dark-tech.html"><img src="templates/screenshots/dark-tech.png" width="360" alt="dark-tech"/><br/><b>dark-tech</b></a><br/><sub>Engineering · Ops</sub></td>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/dark-board.html"><img src="templates/screenshots/dark-board.png" width="360" alt="dark-board"/><br/><b>dark-board</b></a><br/><sub>Dashboards · Architecture</sub></td>
</tr>
<tr>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/data-story.html"><img src="templates/screenshots/data-story.png" width="360" alt="data-story"/><br/><b>data-story</b></a><br/><sub>Annual Reports · Growth</sub></td>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/newspaper.html"><img src="templates/screenshots/newspaper.png" width="360" alt="newspaper"/><br/><b>newspaper</b></a><br/><sub>Editorial · Industry Analysis</sub></td>
</tr>
<tr>
<td align="center"><a href="https://kaisersong.github.io/kai-report-creator/templates/en/regular-lumen.html"><img src="templates/screenshots/regular-lumen.png" width="360" alt="regular-lumen"/><br/><b>regular-lumen</b></a><br/><sub>Periodic Reports · Weekly/Daily/Monthly</sub></td>
</tr>
</table>

Preview the theme gallery: `/report --themes` → opens `report-themes-preview.html`

---

## Design Philosophy: Skil

tests/fixtures/skill-evals/README.md

# Captured Runner Trace Fixtures

These fixtures document the real Codex JSONL shape used by
`scripts/run-skill-evals.py`. Parser support must be based on captured traces
like these, not guessed runner event names.

Observed Codex JSONL shape:

- Top-level events include `thread.started`, `turn.started`, `item.started`,
  `item.completed`, and `turn.completed`.
- Tool calls appear under `item` objects. Shell commands use
  `item.type == "command_execution"` with `command`, `exit_code`, and `status`.
- File reads and writes are not guaranteed to appear in the captured trace; the
  current adapter only consumes explicit `file_read` and `file_write` items if a
  future Codex trace includes them.
- Token usage appears on `turn.completed` as `usage.input_tokens` and
  `usage.output_tokens`.
- Runner warnings can come from `item.type == "error"` events or from a nonzero
  return code in a manually captured `codex exec` trace.

Normalized fixture files use the runner-agnostic `normalized-v1` schema. Unit
tests should score these normalized metrics directly so ordinary pytest never
invokes a live agent or network-backed runner.

themes/README.md

# Custom Themes

Place folders here to add your own themes to kai-report-creator.

## Directory Structure

```
themes/
  your-theme-name/
    reference.md   ← Style description (AI reads and generates CSS variables)
    theme.css      ← Direct CSS definitions (optional, takes priority over reference.md)
```

Both files are optional and can be used independently or together:

| Case | Behavior |
|------|----------|
| Only `reference.md` | AI reads style description and derives `:root` CSS variables |
| Only `theme.css` | CSS variables used directly, fully predictable output |
| Both present | `theme.css` takes priority; `reference.md` serves as style documentation |

## Usage

```bash
/report --theme your-theme-name "Report topic"
```

Or specify in `.report.md` frontmatter:

```yaml
theme: your-theme-name
```

## reference.md Format

```markdown
# Theme Name — Style Reference

One sentence description. Inspiration / aesthetic / mood.

---

## Colors

```css
:root {
  --primary:      #...;   /* Main color: headings, links, accents */
  --bg:           #...;   /* Page background */
  --surface:      #...;   /* Card background */
  --text:         #...;   /* Body text */
  --text-muted:   #...;   /* Secondary text */
  --border:       #...;   /* Borders / dividers */
}
```

## Typography

Font choices. Serif or sans-serif? Geometric or humanist? Google Fonts links.

## Layout

Whitespace style, card border-radius, max-width preferences.

## Best For

Brand reports, research docs, internal newsletters...
```

## theme.css Format

Define `:root` CSS variables to override the base theme defaults.

```css
:root {
  --primary:      #C2410C;
  --primary-light:#FFF7ED;
  --accent:       #EA580C;
  --bg:           #FFFBF7;
  --surface:      #FFFFFF;
  --text:         #1C1917;
  --text-muted:   #78716C;
  --border:       #E7E5E4;
  --font-sans:    'Inter', system-ui, sans-serif;
  --font-mono:    'JetBrains Mono', monospace;
  --radius:       6px;
}
```

See `templates/themes/corporate-blue.css` for all available variables.

## Notes

- Directories starting with `_` (e.g. `_example-warm-editorial`) are ignored and won't appear in theme lists
- Theme names support only letters, numbers, and hyphens: `my-brand`, `warm-editorial`
- Custom themes take priority over built-in themes with the same name

## Sharing Themes

Publish your theme folder as a git repo — others clone it into their `themes/` directory:

```bash
git clone https://github.com/yourname/report-theme-mybrand \
  ~/.claude/skills/report-creator/themes/mybrand
```

_meta.json

{
  "ownerId": "kn7bjv9d2ccsjqk1m4edthgtgx82fem8",
  "slug": "kai-report-creator",
  "version": "1.23.3",
  "publishedAt": 1779011514143
}

Github ReposUpdated 11h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.