Agent skill

Exec Report

by pnp in pnp/sharepoint-skills

Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description.

MITAuto-check passedDocuments & Office

Install Exec Report

skills CLI
$ npx skills add pnp/sharepoint-skills --skill exec-report -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install pnp/sharepoint-skills exec-report --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/pnp/sharepoint-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skills/exec-report/exec-report .claude/skills/exec-report && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
exec-report
GitHub stars
131
Token cost
~2k tokens
SKILL.md length
1,004 words
Files
4 (incl. references, assets)
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description.

  • Works in 5 steps: Determine the Data Source → Interview the User → Choose Components and Narrative Order → …
  • Asked to build an exec report
  • SKILL.md covers Step 1: Determine the Data…, Step 2: Interview the User, Step 3: Choose Components and… and Step 4: Build and Validate the…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Exec Report is an agent skill from pnp/sharepoint-skills. Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description. Use when asked to build an exec report, one-pager, summary page, status dashboard, project summary, business review, or any single-page visual summary of data. Interviews the user if data is incomplete, constructs a validated JSON document block by block, then renders it into a single sandbox-safe HTML file using the component library. No external dependencies —…

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files and assets (for example `references/components.md` and `references/design-system.md`).

It sits in Documents & Office, covering Cloud office suites, OKRs and executive reporting and Design systems. It works with Microsoft SharePoint. The repository describes itself as: Skills for Copilot in SharePoint. The licence is MIT.

When your agent uses it

  • Asked to build an exec report
  • Status dashboard
  • Project summary
  • Business review

Example prompts

  • “Use the exec-report skill to generate a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV…”
  • “/exec-report”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Determine the Data Source
  2. Interview the User
  3. Choose Components and Narrative Order
  4. Build and Validate the JSON Document
  5. Render the HTML

What it can do on your machine

Read from SKILL.md and the folder at commit aa9eb14. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Exec Report loads about 2k tokens when it runs, and up to ~8.4k if it reads all its reference files. Until then it costs about 144 tokens; SKILL.md has 1,004 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~144
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pnp/sharepoint-skills at commit aa9eb14, republished under its MIT licence (© pnp). 1,004 words, ~1,989 tokens.

Download SKILL.mdSave it as .claude/skills/exec-report/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
exec-report
description
Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description. Use when asked to build an exec report, one-pager, summary page, status dashboard, project summary, business review, or any single-page visual summary of data. Interviews the user if data is incomplete, constructs a validated JSON document block by block, then renders it into a single sandbox-safe HTML file using the component library. No external dependencies — output runs inside a SharePoint sandboxed iframe.
metadata.author
zrosenfield

Exec Report

Generates a complete, self-contained HTML report by (1) interviewing the user or parsing their data, (2) constructing and validating a JSON document, then (3) rendering that JSON into HTML using assets/report-template.html. The JSON is the authoritative source of truth; the HTML is fully determined by it.


Step 1: Determine the Data Source

Check what the user has already provided before asking anything:

  • SharePoint lists: Call list_items on the relevant lists. Read all needed columns before proceeding.
  • CSV or table pasted in chat: Parse all rows. Do not ask for data you already have.
  • Verbal description only: Proceed to Step 2.

Step 2: Interview the User

If the data or intent is not fully clear, ask these questions in a single message — not one at a time:

  1. Topic: What is this report about? (e.g., "Q2 pipeline health," "IT project status," "department spend overview")
  2. Audience: Who is reading it? Exec team, department head, all-hands? This determines detail level.
  3. Narrative intent: What is the shape of the story? Pick the closest match:
    • Achievement — "we hit a goal, here's how" (lead with the win: kpi-row + trend dominate)
    • Problem — "something needs attention, here's what" (lead with urgency: status-grid or table comes first)
    • Status — "here's where everything stands" (balanced overview: status-grid early, kpi-row supporting)
  4. Headline message: What should the reader walk away knowing? This becomes the hero sentence — one sentence.
  5. Sections wanted: Any specific sections — comparison to prior period, breakdown by category, status of open items, narrative highlights?
  6. Palette: Warm paper (cream/terra-cotta), deep ink (dark/gold), clean white (white/green), or slate (gray/blue)? Default to warm paper if no preference.

If the user's prompt already signals narrative intent (e.g., "the headline is the gap," "lead with urgency," "show the wins"), skip question 3 — you already have the answer.

Confirm your understanding before building the JSON.


Step 3: Choose Components and Narrative Order

The component sequence IS the story. Read references/components.md for the full component catalog, props schemas, and HTML patterns.

Always true:

  • Open with hero — sets the company, label, and hero sentence.
  • Close with highlights — narrative "so what" belongs last.
  • Maximum one trend, one table, and one highlights per report.
  • Keep total block count to 4–8.

Narrative intent drives the block order:

IntentTypical sequenceHero sentence shape
Achievementhero → kpi-row → trend → bar-list → compare → status-grid → highlights"We closed $X, up Y% from last quarter."
Problemhero → status-grid → compare → table → bar-list → highlights"We enter Q3 with X open roles and a gap in Y."
Statushero → status-grid → kpi-row → compare → bar-list → highlights"Here's where all six workstreams stand heading into Q3."

The hero sentence signals intent to the reader. Achievement heroes lead with a number and a direction. Problem heroes lead with a situation. Status heroes lead with a scope statement.

Component selection guide:

Data shapeComponent
2–4 headline numbers worth celebrating or trackingkpi-row
Values over time (3+ periods)trend
Category breakdown with relative sizesbar-list
Structured numeric comparison (QoQ, YoY, plan vs. actual)compare
Detailed row data (5+ items with 3+ fields)table
Health or urgency status of multiple itemsstatus-grid
Narrative insights: bright spots, risks, actionshighlights

Hard rules:

  • Never put a headline number in prose when kpi-row can show it larger.
  • Never use table for 2–4 numbers — use kpi-row.
  • kpi-row is not mandatory — omit it when the story is problem- or urgency-forward and metrics are supporting context, not the lead.

Step 4: Build and Validate the JSON Document

Construct the JSON object. Top-level structure:

report object (document metadata):

FieldRequiredDescription
paletteyeswarm-paper, deep-ink, clean-white, or slate
footer_lnoLeft footer text, e.g. "Generated May 28, 2026"
footer_rnoRight footer text, e.g. "47 deals analyzed"

blocks array — ordered list of content blocks. Each block: type string + props object. See references/components.md for every component's full props schema.

Show full SKILL.md (374 more words)Show less
Validation Checklist

Run every check before rendering. Fix any failure before proceeding.

Document level:

  • report.palette is one of: warm-paper, deep-ink, clean-white, slate
  • blocks array has at least one entry
  • First block type is hero
  • Last block type is highlights
  • Block order reflects the declared narrative intent (achievement / problem / status)

Per block:

  • type is one of: hero, kpi-row, trend, bar-list, compare, table, status-grid, highlights
  • All required props are present (see components.md)
  • Numeric values are numbers, not strings with embedded units
  • No block exceeds its item count limits (see components.md limits table)

Data integrity:

  • kpi-row items count is 2–4
  • bar-list shares: largest item = 1.0, all others ≤ 1.0
  • trend data and labels arrays have the same length (3–12)
  • trend prior_data (if present) same length as data
  • compare rows have dir set to "up" or "down" on every row
  • table headers count matches every row's cell count
  • highlights items count is 3–5

Step 5: Render the HTML

  1. Read assets/report-template.html.
  2. Replace {{REPORT_TITLE}} in <title> with a concise page title (company + report label).
  3. Replace {{PALETTE_CLASS}} on <body> with palette- + the palette name (e.g. palette-warm-paper).
  4. Generate the hero block HTML (.rpt-header + .hero) and replace {{HERO}}.
  5. Generate all remaining blocks in order and replace {{BLOCKS}}.
  6. Replace {{FOOTER_L}} and {{FOOTER_R}} with footer text (or empty strings).
  7. Generate the {{INLINE_SCRIPT}} content. Include:
    • Segment bar fill-in code (if any bar-list blocks are present)
    • Trend tooltip JS with embedded TREND_DATA array (if a trend block is present)
    • See the template's script comment block for the exact code patterns to use.
  8. Deliver the complete file as the response. No prose outside the file.

If the site context specifies a folder for report output, save the file there after delivering it.


Hard Constraints

  • No external URLs, CDN links, or web fonts in the output HTML.
  • No <script src> tags. All JavaScript must be inline.
  • All data values must be pre-rendered into the HTML — the page must be fully correct with JavaScript disabled. JS adds animations and tooltips but must never be required for correctness.
  • Do not generate Python, PowerShell, or any other scripts — output is always the HTML file.
  • Do not render until the validation checklist passes.
  • Follow the no-Person-column-type rule for any accompanying SharePoint schema: use text columns only.

© pnp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references, assets) in Skills/exec-report/exec-report of pnp/sharepoint-skills.

  • SKILL.md
  • assets/report-template.html
  • references/components.md
  • references/design-system.md

Open the folder on GitHubat commit aa9eb14

Compare with similar skills

Exec Report next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Exec Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Exec Report this skillpnp/sharepoint-skills131—~2kAutomated safety check: PassMIT
SVG DashboardSCStelz/security-investigator249—~5.7kAutomated safety check: PassMIT
Data ReportZJU-REAL/Easel3.2k—~479Automated safety check: PassApache-2.0
Flowai Live Dashboard Templatenexu-io/open-design100k—~865Automated safety check: PassApache-2.0
HTML DesignNimaChu/html-design101—~2.7kAutomated safety check: PassNone
Colleague DistillationZhixiangLuo/10xProductivity478—~2.1kAutomated safety check: NotesMIT

Similar skills

  • SVG Dashboard

    SCStelz/security-investigator

    A skill your agent uses when asked to generate SVG data visualization dashboards from investigation data or skill reports.

    249 GitHub stars~5.7k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Data Report

    ZJU-REAL/Easel

    把 CSV、Excel 或 JSON 数据生成包含 KPI、图表和洞察的完整可视化报告页。当用户说“数据报告、CSV/Excel 转报告、做 KPI 看板、生成可视化报告页”时使用。单张图表用 chart-visualization;信息图或 GIF 动画图表用 infographic。

    3.2k GitHub stars~479 tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity…

    100k GitHub stars~865 tokensUpdated today
    Frontend & DesignAuto-check passed
  • HTML Design

    NimaChu/html-design

    Create, redesign, repair, validate, preview, and package lightweight standalone HTML deliverables.

    101 GitHub stars~2.7k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Colleague Distillation

    ZhixiangLuo/10xProductivity

    Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and…

    478 GitHub stars~2.1k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check: notes
  • CLI Microsoft365

    pnp/cli-microsoft365-mcp-server

    Use CLI for Microsoft 365 to manage Microsoft 365 tenants from the terminal.

    131 GitHub stars~3.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed

More from pnp/sharepoint-skills

All 51 skills in this repo
  • Scorecard Matrix

    pnp/sharepoint-skills

    Generates a polished, self-contained HTML heatmap scorecard — a weighted comparison matrix where entities (rows) are scored across dimensions (columns), with computed totals, rank badges, and a…

    131 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Analyze Document Library

    pnp/sharepoint-skills

    Analyze the current SharePoint document library in read-only mode and produce a structured summary of files, folders, file types, recent activity, naming issues, and organization recommendations.

    131 GitHub stars~899 tokensUpdated yesterday
    Auto-check passed
  • Broken Link Auditor

    pnp/sharepoint-skills

    Audits SharePoint pages, news posts, and hyperlink fields for broken or risky links and saves a self-contained HTML link-health report to the site.

    131 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Custom Image Tagger

    pnp/sharepoint-skills

    Analyze selected construction images, create missing object metadata columns, and write concise visual metadata back to SharePoint columns using explicit image-analysis, list-schema, list-update…

    131 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Dossier

    pnp/sharepoint-skills

    Renders a polished, self-contained HTML briefing from any data source — SharePoint lists, uploaded documents, or a verbal description.

    131 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • File Classifier

    pnp/sharepoint-skills

    Classifies files in a SharePoint document library by reading their content and matching them to known content types (Contracts, Invoices, Purchase Orders).

    131 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

Questions about Exec Report

What does Exec Report do?

Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description. Exec Report is an agent skill from pnp/sharepoint-skills. Generates a polished, self-contained HTML executive report or dashboard from any data source — SharePoint lists, CSV exports, or a user description.

When should I use Exec Report?

Exec Report fits situations like: asked to build an exec report; status dashboard; project summary; business review.

How do I install Exec Report in Claude Code?

Run `npx skills add pnp/sharepoint-skills --skill exec-report -a claude-code`. Or copy the skill folder (Skills/exec-report/exec-report in pnp/sharepoint-skills) into .claude/skills/exec-report in your project. Claude Code loads it when a task matches its description.

How do I install Exec Report in Codex?

Run `npx skills add pnp/sharepoint-skills --skill exec-report -a codex`. Or copy the skill folder (Skills/exec-report/exec-report in pnp/sharepoint-skills) into .agents/skills/exec-report in your project. Codex loads it when a task matches its description.

Can I use Exec Report in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pnp/sharepoint-skills --skill exec-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/exec-report, .gemini/skills/exec-report, .github/skills/exec-report and .opencode/skills/exec-report in your project.

What does Exec Report need to run?

SKILL.md names no scripts, command-line tools or credentials: Exec Report is instructions for the agent only.

Does Exec Report access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Exec Report safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Exec Report use?

Exec Report is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Exec Report use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.4k tokens, read only when the agent opens those files.

What are the alternatives to Exec Report?

Skills that share tags, products or a category with Exec Report: SVG Dashboard (SCStelz/security-investigator, 249 stars), Data Report (ZJU-REAL/Easel, 3.2k stars), Flowai Live Dashboard Template (nexu-io/open-design, 100k stars) and HTML Design (NimaChu/html-design, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Exec Report?

pnp (a GitHub organization) maintains it in pnp/sharepoint-skills, which has 131 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on October 6, 2026.

Source: pnp/sharepoint-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.