- Home
- Skills
- Prompt & Skill Engineering
- Experience Extraction Expert
Experience Extraction Expert
Extracts tacit expert knowledge into actionable checklists and operational manuals through interviews or text analysis.
Free
Works with the AI Agents you already use
Experience Extraction Expert
Example session with this skill installed
I have a transcript from our lead architect explaining how she handled the database migration last month. Can you extract the methodology from this text? [Text attached]
- Read your context and instructions
- Compiled the experience extraction expert
I have analyzed the transcript regarding the database migration. I identified three critical "hidden" decision points: the pre-sync heartbeat check, the manual schema locking sequence, and the rollback trigger threshold. Before I generate the full manual, I have structured the methodology into the "Zero-Downtime Shift" framework.
Analysis Framework: Zero-Downtime Shift
| Extraction Layer | Findings from Transcript |
|---|---|
| Context | High-concurrency environment, legacy SQL cluster, 2-hour maintenance window. |
| Hidden Judgment | "The Pulse Check": The architect didn't trust the automated logs; she manually verified latency on the secondary node. |
| Actionable Step | Sequence Locking: Instead of global locks, she implemented a tiered table-level lock to prevent application timeout. |
| Evidence | Mentioned "Transaction Log Wrap-around" as the primary risk factor. |
Missing Details for Documentation:
- What specific latency threshold (in ms) triggered the "Pulse Check" failure?
- Who was the specific point of contact for the application layer during the tiered locking?
Next steps
- Confirm if the "Sequence Locking" label accurately describes the process.
- Provide the specific latency thresholds if known.
- I will then generate the Operation Manual and Behavioral Checklist.
Connects securely to your tools. The creator never sees your data.
About this skill
Most high-performers possess "tacit knowledge" that they cannot easily explain. When they try to teach, they offer vague principles like "just be proactive" rather than actionable steps. This skill solves the expertise gap by systematically extracting the specific decision points, hidden triggers, and exact behaviors that lead to success.
What it does
- Multi-modal extraction identifies expertise through either structured live interviews or by analyzing existing artifacts like meeting transcripts and chat logs.
- Hidden logic identification spots the "counter-factual" moments where an expert made a specific choice that others would miss.
- Actionable naming converts vague intuition into named methodologies, such as "Decision Point Probes," to make them teachable.
- Gap analysis generates a "missing evidence list" when analyzing source materials to highlight exactly what information is still needed from the expert.
- Document generation produces a three-part deliverable including an operations manual, a behavioral checklist, and a narrative case study.
How it works
- Mode selection: The user provides a raw source (text/audio) for analysis or requests a live interview session.
- Framework alignment: The agent presents a "Mirror Outline" summarizing the core logic it detected for user verification before writing.
- Structured probing: For interviews, the agent follows a 5-round protocol moving from context to deep implementation details.
- Final delivery: The agent generates Markdown or Word documents containing the behavioral checklists and case summaries.
Frameworks & tools
This skill utilizes specialized interview protocols and transcript rubrics. It includes Python scripts for source loading and Word document rendering with specific typography controls.
Why this beats prompting it yourself
Generic prompts usually result in high-level summaries or "fluff" like "stay focused." This skill uses a rigorous 5-round interrogation protocol designed to prevent the expert from speaking in platitudes, forcing out the specific details that make the method actually replicable by others.
Use cases
- Converting a top salesperson's intuitive pitch into a training manual for new hires.
- Extracting the "war stories" and recovery steps from a senior engineer after a complex system migration.
- Analyzing months of project Slack logs to document a team's unique problem-solving workflow.
Known limitations
Cannot directly transcribe audio without an external ASR key. Does not support visual-only sources like screenshots without text. Word export requires local python-docx installation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
Requires text transcripts for audio if no ASR key is present. Word output depends on local python-docx environment. Logic is limited to extraction, not performance management or creative writing.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
- Software
Python