Works with the AI Agents you already use
knowledge inventory mapping
This skill processes asset metadata to build a structured inventory that identifies governance gaps without manual auditing.
$1.99
knowledge inventory mapping
Example session with this skill installed
Inventory these assets from the Marketing and Engineering repositories. Check for staleness using a 180-day threshold and map them to our internal taxonomy. [Attachment: metadata_export.json]
- Read your context and instructions
- Compiled the knowledge inventory mapping
I have processed the metadata for the provided assets across two repositories. The analysis is complete with three items flagged for human review.
Knowledge Asset Inventory — Corporate Library, 2024-05-20
1. Scope, sources and assumptions
- Sources: E1 (Marketing-SharePoint), E2 (Eng-GitHub-Wiki).
- Taxonomy: Corporate Taxonomy v2.1.
- Parameters:
staleness_threshold_days: 180. - Assumptions: Assets without a
last_modifieddate are treated as stale (Origin: Default logic).
2. Coverage metrics
| Metric | Value |
|---|---|
| Total Assets | 142 |
| Taxonomy Coverage | 82.4% |
| Stale Ratio | 12.7% |
| Orphan Ratio | 4.2% |
| Duplicate Ratio | 3.5% |
| Content Health Score | 78/100 |
3. Findings summary
- Critical (2): 6 assets missing owners in protected repositories.
- High (5): 18 stale assets in "Security" taxonomy node.
- Medium (3): 5 duplicate groups identified across Marketing and Engineering.
4. Prioritized actions
| Priority | Action | Issue Code | Count |
|---|---|---|---|
| 1 | Assign owners to orphaned assets | MISSING_OWNER | 6 |
| 2 | Review stale content for archival | STALE_CONTENT | 18 |
| 3 | Consolidate cross-repo duplicates | DUPLICATE_ENTRY | 5 |
5. Distribution
- By Repository: Marketing (88), Engineering (54).
- By Type: PDF (60), Markdown (45), DOCX (37).
6. Duplicate groups
- Group 1:
mkt-ref-001,eng-ref-099(Title: "Brand_Guidelines_2023.pdf") - Group 2:
eng-spec-v1,eng-spec-final(Title: "API_v2_Specification")
7. Warnings and items for human review
Information gap — organizational validation required: Assets mkt-990 through mkt-995 lack access level metadata.
- Analytical estimate — validation required: 4 assets classified into "Uncategorized" due to ambiguous titles.
Next steps
- Assign owners to the 6 critical orphan assets identified in Section 4.
- Verify the 18 stale assets before initiating the archival workflow.
- Consolidate the 5 duplicate groups to reduce storage redundancy.
Connects securely to your tools. The creator never sees your data.
About this skill
Organizations struggle to maintain visibility over fragmented document libraries, leading to stale content and knowledge silos. This skill processes asset metadata to build a structured inventory that identifies governance gaps without manual auditing.
What it does
- Taxonomy classification maps assets to hierarchical structures using titles and tags.
- Staleness detection flags outdated documents based on configurable time thresholds.
- Duplicate identification finds identical or redundant assets across different repositories.
- Health scoring calculates coverage metrics and orphan ratios to assess library integrity.
- Remediation planning generates a prioritized list of actions to fix missing owners or metadata gaps.
How it works
- Metadata collection where you provide a list of asset records including titles, dates, and repositories.
- Schema validation checks your input against the required JSON structure to ensure data integrity.
- Automated analysis runs a deterministic script to classify assets and compute metrics.
- Report generation delivers a structured inventory with prioritized governance actions.
Frameworks & tools
This tool uses a Python-based execution environment to process JSON metadata. It relies on standard ISO date formats for temporal analysis and hierarchical taxonomy schemas for classification logic.
Why this beats prompting it yourself
Standard prompts often hallucinate document counts or miss subtle duplicates in large datasets. This skill uses a deterministic script to ensure every metric, from staleness ratios to orphan counts, is calculated with mathematical precision rather than LLM estimation.
Use cases
- Audit repositories to find documents without owners or clear classifications.
- Clean up libraries by identifying exact duplicates and stale content for archiving.
- Map knowledge gaps by visualizing which taxonomy nodes lack supporting documentation.
- Standardize governance across multiple storage platforms using a single taxonomy.
Known limitations
This skill only processes metadata and does not read or summarize actual document content. It cannot access live repositories directly; you must supply the metadata in the request.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Only processes metadata, not full text. No live repository access. Requires human validation for all remediation actions. Does not modify taxonomy structures.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago