- Home
- Skills
- Agents & Orchestration
- learn from my corrections
Works with the AI Agents you already use
learn from my corrections
Extracts and consolidates reusable instructions from your past corrections and feedback episodes.
$5
learn from my corrections
Example session with this skill installed
Review our last three chats about the API documentation. I've had to correct how you handle error codes and your tone several times. Give me a consolidated instruction block to prevent this.
- Read your context and instructions
- Compiled the learn from my
I have analyzed the three provided transcripts focusing on API documentation tasks. I identified two recurring correction patterns regarding HTTP error formatting and technical persona.
Correction Analysis & Proposed Instructions
| Proposed Rule | Evidence | Scope | Confidence |
|---|---|---|---|
| Error Code Mapping | 3 instances of correcting 400 vs 422 usage in validation docs. | API Documentation | High |
| Direct Technical Tone | Rejection of "Here is the..." intros in 4 separate drafts. | Global | High |
| Schema Nesting | 1 correction regarding depth of JSON examples. | Project-specific | Medium |
Proposed Instruction Draft
# Documentation Style Rules
- When documenting validation errors, always use HTTP 422 (Unprocessable Entity) for business logic failures and 400 for malformed syntax.
- Omit conversational filler and introductory sentences (e.g., "Certainly," "Here is the..."). Start directly with the technical content or heading.
- For JSON schema examples, limit nesting to 3 levels unless explicitly asked for a full object tree.
Next steps
- Review the Error Code Mapping rule to ensure 422 is your standard across all services.
- Copy the draft into your
PROJECT_CONTEXT.mdor System Instructions. - Provide a counter-example for the Schema Nesting rule if you require deep nesting by default in specific modules.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Users waste time repeating the same corrections, stylistic preferences, and project requirements across multiple chat sessions. AI assistants often fail to internalize specific feedback, leading to a cycle of repetitive editing and frustration.
What it does
- Analyzes conversation history and rejected drafts to identify recurring patterns in user feedback.
- Extracts concrete, observable instructions from explicit corrections and positive examples.
- Classifies findings into global preferences, project-specific rules, or one-off factual fixes.
- Generates a ready-to-use instruction block with evidence-based confidence ratings for each rule.
- Maps instructions to their ideal destination, such as system prompts, project files, or custom skills.
Why this beats prompting it yourself
Manually distilling feedback often leads to over-generalization or "prompt bloat" where conflicting instructions confuse the model. This tool uses a structured evidence ledger to ensure new rules don't break existing workflows or ignore legitimate exceptions. It prevents the common mistake of turning a single correction into a blanket ban.
Use cases
- Consolidating feedback from a long project thread into a permanent project README or system prompt.
- Converting a series of stylistic critiques on marketing copy into a reusable brand voice guide.
- Auditng why an assistant keeps failing a specific task by comparing corrections against current instructions.
Known limitations
Cannot access history from other conversations unless the user provides the transcripts or the environment explicitly supports cross-thread retrieval. Does not "train" the underlying model.
Requires manual input of transcripts if cross-thread history is not natively accessible. Does not perform actual model training or fine-tuning.
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 2 months ago
Permissions
No special permissions declared or detected