- Home
- Skills
- Technical Documentation
- knowledge gap detection
Works with the AI Agents you already use
knowledge gap detection
Analyzes search logs to detect topics users query but cannot find content for. Produces prioritized gap register with query coverage metrics. Privacy-sensitive search data requires appropriate handling.
$1.99
knowledge gap detection
Example session with this skill installed
Analyze these search logs and articles to find documentation gaps. Use a 0.3 relevance threshold and a min query count of 2. [search_logs.csv, articles_list.json]
- Read your context and instructions
- Compiled the knowledge gap detection
I have analyzed the search logs against your current article database. The calculation script processed 450 total queries with a coverage rate of 62%. # Knowledge Gap Analysis — Documentation Team, 2023-10-24 ## 1. Query Coverage - Total Queries: 450 - Distinct Queries: 82 - Coverage Rate: 62.0% - Zero-result Rate: 18.5% - Low-relevance Rate: 19.5% ## 2. Gap Summary - High Severity: 3 - Medium Severity: 5 - Low Severity: 12 - Types: 8 missing_content, 12 low_quality_content ## 3. Knowledge Gap Register | Topic | Type | Severity | Score | Queries | Users | Zero-result % | Status | | :--- | :--- | :--- | :--- | :--- | :--- | :--- | :--- | | MFA Setup | missing_content | High | 24.5 | 32 | 14 | 85% | draft | | API Rate Limits | low_quality_content | High | 18.2 | 22 | 8 | 10% | draft | | SSO Debugging | missing_content | Medium | 9.0 | 12 | 5 | 60% | draft | ## 4. Recommended Actions - **Priority 1**: Create "MFA Setup Guide" (Management decision required). - **Priority 2**: Update "API Reference" with explicit rate limit tables. ## 5. Warnings - `W001`: Privacy warning. Search logs contain raw user queries. Handle as PII. - `W004`: Low relevance threshold adjusted to 0.3 per user request. ## 6. Interpretation and items for human review - MFA queries have the highest zero-result rate, indicating a total lack of content. - API Rate Limit queries return results, but relevance scores are consistently below 0.3. - User demand for SSO topics is growing, with 5 unique users searching this week. This analysis supports, and does not replace, professional judgment and management's decision. **Next steps** - Validate the "MFA Setup" gap with the security team. - Run a follow-up analysis in 30 days to measure the impact of new articles. - Review raw search strings for "API Rate Limits" to understand specific user pain points.
Connects securely to your tools. The creator never sees your data.
About this skill
Documentation teams often struggle to prioritize what to write, relying on guesswork rather than user needs. This skill identifies exactly where your documentation fails by analyzing search logs against existing knowledge articles. It moves beyond simple "zero-result" counts to calculate a weighted gap score based on relevance thresholds and user demand.
What it does
- Search log analysis processes query frequency, result counts, and relevance scores from provided logs.
- Content mapping compares user queries against existing article titles and topics to identify coverage.
- Gap prioritization calculates a weighted
gap_scoreusing zero-result weightings and unique user factors. - Severity classification categorizes missing content into High, Medium, or Low severity based on demand and failure rates.
- Automated reporting generates a structured knowledge gap register with precise metrics.
How it works
- Prepare a
request.jsonfile containing your search logs and current article metadata. - Execute the included
run.pyscript to perform the deterministic gap calculation. - Review the generated gap register to see which topics lack satisfactory content.
- Export the findings into the standardized Markdown report for stakeholder review.
Frameworks & tools
The skill utilizes a self-contained Python analysis engine for deterministic calculations. It relies on standard JSON schemas for search log data and article metadata ingestion.
Why this beats prompting it yourself
Generic prompts often hallucinate missing topics or fail to weigh the importance of a gap correctly. This skill uses a specific mathematical formula to calculate gap scores, ensuring that high-volume, low-relevance queries are prioritized over outliers.
Use cases
- Identify missing documentation topics that lead to high support ticket volume.
- Prioritize the content creation backlog based on actual user search failure rates.
- Audit search engine performance by identifying queries with consistently low relevance scores.
- Generate data-driven reports for management to justify documentation resource allocation.
Known limitations
Search log quality directly affects detection accuracy. The skill does not analyze user intent beyond text matching and cannot assess content quality beyond relevance scores.
Requires search logs with result counts or relevance scores. Does not analyze query intent. Results are draft status and require management validation. Privacy sensitivity for query data.
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 any payment.
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