kb-admin-report
Skill96 starsChanged 3 months agoMITView on GitHub
Generates a comprehensive knowledge base health report covering corpus overview, knowledge decay, gap status, ingestion activity, expert coverage, and recommended next actions. Triggers when an admin asks for a knowledge base report, status update, or health check.
In this repository27 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- authoring-sharepoint-markdownSkill
- autoresearchSkill
- brainstorming-design-docsSkill
- copy-editingSkill
- decision-logSkill
- deck-assemblySkill
- design-directionSkill
- executive-summarySkill
- faq-buildingSkill
- find-expertSkill
- forest-styleSkill
- gap-analysisSkill
- hiring-pipeline-reportSkill
- improve-skillsSkill
- ingest-knowledgeSkill
- linkedin-post-writingSkill
- list-formattingSkill
- log-knowledge-gapSkill
- meeting-notesSkill
- project-briefSkill
- quarterly-expense-reportSkill
- ralph-loopSkill
- site-analyzerSkill
- style-guidelinesSkill
- uppababy-brand-reviewSkill
- youtube-descriptionSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
When an admin asks for a knowledge base report, status update, or health check, generate a comprehensive report.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
When an admin asks for a knowledge base report, status update, or health check, generate a comprehensive report. Read all files in the Knowledge Base library, all items in the Knowledge Gaps list, and all items in the Expert Directory list.
1. Corpus Overview
- Total number of KB files and list of topic names
- For each file: count of sections, count of distinct sources cited, and the date range of entries (oldest Added date to newest Added date)
- Total knowledge entries across all files
2. Decay Report
- List every KB entry where Last Verified is older than 90 days
- Group stale entries by topic file
- For each stale entry: show the subtopic name, Last Verified date, days since verification, and the original source person
- Count: total entries, verified within 90 days, stale (90+ days), critical (180+ days)
- Highlight any topic files where more than half of entries are stale
3. Gap Status
- Count of Knowledge Gaps by Status (Open, Assigned, Resolved, Verify)
- List all Open and Assigned gaps with their Topic, Asked By, and date
- List all Verify items (decay-triggered re-verification requests)
- Average time from Open to Resolved for completed gaps (if dates allow)
- Topics with the most open gaps — these are the weakest coverage areas
4. Ingestion Activity
- Count of resolved gaps by Source Type (Transcript, Email, Document, Slack, Typed, Verification)
- This shows how knowledge is entering the system — are people typing it in, or is it coming from meeting transcripts, emails, etc.
- Identify which source types are most and least used
5. Expert Coverage
- List all experts and their expertise areas
- Cross-reference against open gap topics: which gap topics have a matching expert? Which don't?
- Identify expertise areas with no KB file yet (expert registered but no knowledge captured)
- Identify KB topics with no matching expert (knowledge exists but no one owns it)
6. Recommendations
Based on the data above, provide 3–5 specific next actions. Prioritize:
- Stale entries that need re-verification (especially in frequently-asked topics)
- Open gaps that have been unassigned the longest
- Topic areas with no expert coverage
- Source type gaps (e.g., if no transcripts have been processed, suggest recording and submitting meeting notes)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.