Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pnp/sharepoint-skills --skill metadata-completeness-auditorgit clone --depth 1 https://github.com/pnp/sharepoint-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pnp/sharepoint-skills/metadata-completeness-auditor)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/metadata-completeness-auditor"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/metadata-completeness-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/metadata-completeness-auditor"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/metadata-completeness-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00154 | $0.02172 |
| Opus 5 | $0.00077 | $0.01086 |
| Sonnet 5 | $0.00031 | $0.00434 |
| Haiku 4.5 | $0.00015 | $0.00217 |
Grade A, and why
metadata-completeness-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata Completeness Auditor
Purpose
Missing or inconsistent metadata is the single most common reason SharePoint search, filtering, views, and retention stop working. This skill measures the metadata quality of a library (or list), flags every item with gaps, and produces a color-coded HTML dashboard the team can act on. It is strictly read-only: it inspects the schema and reads items, but never creates columns, writes to items, or changes the list in any way.
Trigger Phrases
Activate this skill when the user says any of the following (or close variations):
- "metadata audit" / "audit metadata"
- "metadata completeness" / "metadata health" / "metadata quality"
- "missing metadata" / "which items are missing metadata"
- "check metadata" / "metadata gap report"
- "find blank columns" / "find empty fields"
Inputs & Scope
Determine the reporting scope from the user's request and the current context, in this order:
- Selected items — if the user has items selected or says "these/this", audit the library that contains the selection.
- Named library or list — if the user names one (e.g., "audit the Contracts library"), resolve it on the current site.
- Current library — if the user is in a library and gives no other scope, audit it.
- If no scope can be resolved, ask the user which library or list to audit. Do not guess.
Only audit content the current user can already see. Never invent items or values.
Steps
Step 1 — Resolve the target list and read its schema
Use get_list_schema on the resolved library/list to enumerate its columns. Record for each
column: internal name, display name, type (text, choice, number, date, person, managed
metadata, multi-value, etc.), and whether it is marked required.
Step 2 — Decide the "required set" of columns to audit
Choose which columns count toward completeness, in this order of preference:
- Explicit user request — if the user names specific columns (e.g., "check Owner and Review Date"), audit exactly those.
- Columns marked required in the schema — if any exist, default to auditing those.
- All user-created content columns — if nothing is marked required, audit every non-system content column.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 175 lines · 154 tokens per session scan A dfd3c2e80089
metadata-completeness-auditor is a skill published in the GitHub repository pnp/sharepoint-skills (112 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 2,172 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-obsidian-claude-gradient
OpenDesign's enterprise AI-adoption brief: local-first agents at work, the risk controls, the ROI, and the rollout plan. Built as a decision-grade AI literacy deck for leadership, IT, security.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
skill-deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries.
speech-to-text
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
msgraph-files
Read OneDrive and SharePoint files via the Microsoft 365 MCP server — list folder contents, fetch item metadata, inspect versions and sharing permissions. Use when locating a document in OneDrive/SharePoint, checking who a file is shared with, or reviewing file version history.
managedcode-markitdown
Use ManagedCode.MarkItDown when a .NET application needs deterministic document-to-Markdown conversion for ingestion, indexing, summarization, or content-processing workflows. USE FOR: ManagedCode.MarkItDown integration; document ingestion flows; Office or rich-text conversion to Markdown; indexing and summarization…