Agent skill · microsoft

feedback-learning

Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.

What it needs

About 2k tokens when loaded.

What this skill does

Feedback learning Use this skill when a user explicitly corrects an implementation or design approach, rejects a pattern, or asks the agent to learn from feedback, except when the user invokes the literal learn! trigger. Literal learn! requests are governed exclusively by .github/instructions/learnings.instructions.md and are outside this skill's scope. Do not replace or reinterpret that instruction. Goal Preserve reusable knowledge in the smallest authoritative artifact. A correction is not automatically a permanent rule. Workflow 1. Identify the correction What was wrong? Why was it wrong? What approach did the user prefer? Which paths or subsystem does it affect? 2. Search before writing Check applicable instructions, skills, design documents, tests, and scoped learning files. Update an existing rule instead of adding a duplicate. 3. Classify the feedback Feedback kind Destination --------------- ------------- Task-specific preference or one-off adjustment Do not persist Concrete behavior that must not regress Regression test Stable subsystem architecture or product invariant Relevant design/specification document Universal repository rule Applicable instruction file Reusable but not yet mature or proven guidance .github/learnings/<area>.md Tool-driven workflow Relevant skill 4. Generalize carefully Preserve the principle, not the incident chronology. Do not include temporary symbol names, line numbers, or implementation details unless they define the durable contract. Do not turn a single rejected implementation into a universal prohibition without broader evidence. 5. Record once Design documents and tests are authoritative. A learning inbox entry is temporary. When promoted, remove the inbox entry in the same change. Never copy the same rule into a skill, instruction, and design document. Before adding an inbox entry, compact the target file using the maintenance rules below. 6. Validate Confirm the destination applies to the affected path. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills microsoft/feedback-learning

View the source on GitHub

Browse the @skills marketplace