Skip to content
Agentmart
Submit a tool

cqi-analytical-documentation

Create or review evidence-bound analytical narrative for EDA documentation, plot explanations, rule analyses, executive reports, stakeholder questions…

Skill by negritaos

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cheetah-alo-cqi-analytical-documentation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create or review evidence-bound analytical narrative for EDA documentation, plot explanations, rule analyses, executive reports, stakeholder questions, DOCX/PDF/Markdown outputs, and analytical presentations. Use when the work must explain what the evidence shows, how to read it, what it means, what it cannot prove, and which decision it supports.

Use cases: documents, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cqi-analytical-documentation

What's inside

Skill name
cqi-analytical-documentation
Description
Create or review evidence-bound analytical narrative for EDA documentation, plot explanations, rule analyses, executive reports, stakeholder questions, DOCX/PDF/Markdown outputs, and analytical presentations. Use when the work must explain what the evidence shows, how to read it, what it means, what it cannot prove, and which decision it supports.
License
Apache-2.0
Metadata
author: negritaos · version: 1.0
Instructions
116 lines in SKILL.md · view on GitHub

Files (7)

  • SKILL.md
  • openai.yaml · agents/
  • anti_patterns.md · references/
  • arik_questions.md · references/
  • evidence_boundaries.md · references/
  • plot_discussion.md · references/
  • voice_and_tone.md · references/

SKILL.md (first lines)

# CQI Analytical Documentation

Use this skill for the analytical narrative. It does not replace the visual
template, the data contract, or the domain profile.

Combine it with:

- `evidence-first-plot-analysis` for plot interpretation;
- `rule-model-documentation` for deterministic rule systems;
- `cqi-analytical-docx-pdf` for Word/PDF production and QA;
- `analytics-storytelling-deck` and `cqi-analytical-pptx` for presentations;
- the active project profile for domain-specific semantics.

## Required Narrative

Every analytical section, finding, stakeholder answer, or plot discussion must
follow this order:

```text
Question
-> Executive answer
-> Evidence
-> How to read the plot or table
-> Observation
-> Interpretation
-> Evidence boundary
-> Operational implication or next analysis
```

Do not start with implementation detail when the audience first needs the
answer. Do not end at a metric or a caption. The narrative must explain why the
result matters and how far the evidence supports the conclusion.

## Plot Contract

For every plot, declare:

1. the question it answers;
2. population, grain, window, filters, denominator, and comparison baseline;
3. how to read axes, units, scales, marks, colors, groups, and direction;
4. the material pattern with `n`, percentages, rates, deltas, or support;
5. the evidence-supported interpretation;
6. what the plot cannot establish;
7. the operational decision, risk, or next check it enables.

Load [plot_discussion.md](references/plot_discussion.md) whenever a deliverable
contains a chart, table, heatmap, funnel, flow, or diagram.

## Presentation Notes Contract

The visible slide carries the concise message. The speaker notes carry the
complete discourse guide. Every new or materially changed slide must contain
this block:

```text
[Talk track]
Question:
Executive answer:
How to read:
What stands out:
Interpretation:
Evidence boundary:
Operational implication:
Transition:
[/Talk track]
```

For a slide without a plot, table, diagram, or other visual evidence, use
`How to read: N/A - no visual` and keep the remaining fields substantive. For
plot-backed slides, the talk track must point the speaker to the relevant
visual feature and quantified pattern.

For CQI/CQISense decks, keep the separate `[Evidence]` block required by
`cqi-analytical-pptx`. The talk track explains the story; the evidence block
records provenance and allowed conclusions. Neither replaces the other.

The talk track must be fluent, natural, presentation-ready prose in the output
language. Do not write stage directions, jargon-heavy fragments, or text that
merely repeats the slide.

## Stakeholder Questions

When the request is organized around stakeholder or Arik questions, load
[arik_questions.md](references/arik_questions.md). Answer each question as a
self-contained decision record. Do not bury the evidence status at the end.

## Project Boundaries

This skill is provider-neutral and project-neutral. It must not import HOT,
ELAL, IBC, BigQuery, churn, telecom, or aviation semantics unless the active
project profile supplies them.

For ELAL work, load the active ELAL governance skills and the ELAL section in
[arik_questions.md](references/arik_questions.md). Keep customer-facing and
internal/auditable routes distinct.

## Required References

- Load [voice_and_tone.md](references/voice_and_tone.md) for any full report,
  document, or deck narrative.
- Load [plot_discussion.md](references/plot_discussion.md) for visual evidence.
- Load [arik_questions.md](references/arik_questions.md) only for stakeholder
  question packs or ELAL/Arik review.
- Load [evidence_boundaries.md](references/evidence_boundaries.md) whenever a
  claim, status, comparison, or recommendation is written.
- Use [anti_patterns.md](references/anti_patterns.md) as the final narrative QA
  gate.

## Calibration Boundary

The HOTMobile PDFs named in `references/voice_and_tone.md` are read-only style
calibration. They are not factual authority for another project. Do not copy
their claims, thresholds, tables, wording, colors, layouts, grammar defects,
or unresolved placeholders.

From cheetah-alo/NegritaOS, Apache-2.0.

More from cheetah-alo/NegritaOS

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 31, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from negritaos

Cite this page

cqi-analytical-documentation skill. Agent Mart. https://agentmart.dev/skills/cheetah-alo-cqi-analytical-documentation (last updated 2026-10-24)