Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/session-intelligence-harvester
This skill should be used after productive sessions to extract learnings and route them to appropriate Reusable Intelligence Infrastructure (RII) components.
4 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
During our debugging session, we realized that component tests were failing because the mock database helper was initialized with stale schema assumptions. We want to extract this session learning into our system guidance. Make sure your process explicitly documents the three analytical questions before modifying any files, then execute the edits and summary.
| Checked | Without skill | With skill |
|---|---|---|
| Includes an explicit analysis step covering Corrections Made, Patterns Identified, and Learning Classification. | Missed | Passed |
| Identifies why the error occurred under the corrections analysis. | Missed | Passed |
| Specifies canonical sources referenced during pattern identification. | Missed | Passed |
The instructions your model reads when the skill loads.
Transform session learnings into permanent organizational intelligence by implementing updates across RII components. After productive sessions involving corrections, discoveries, or pattern identification, systematically extract what was learned, route it to the correct component, and apply the changes.
Why this matters: One-time fixes that aren't encoded into RII components will recur. The Chapter N skill format drift happened because no check existed to prevent it. After harvesting, that failure mode is encoded in 4 files—future sessions automatically benefit.
Automatic Triggers (proactively suggest harvesting):
Manual Triggers (user requests):
Default to action: Implement all updates rather than only proposing them. Read target files, make edits, and commit changes. Only propose without implementing if explicitly asked.
Analyze the session by answering these questions. Write your analysis to track progress:
1. CORRECTIONS MADE
- What errors/drift were corrected?
- What was wrong vs what is now correct?
- Why did the error occur? (missing check, format drift, etc.)
WHY THIS MATTERS: Understanding root cause determines which RII
component prevents recurrence. Format drift → agent convergence
pattern. Missing context → CLAUDE.md protocol step.
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.