lesson-memory
Maintains relevance-ranked lessons and repair memory so agents do not repeat mistakes across tasks or sessions.
- License 许可
- Apache-2.0
- 最近更新
- 2026-07-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- lesson-memory
- description
- Maintains relevance-ranked lessons and repair memory so agents do not repeat mistakes across tasks or sessions.
03 SKILL.md 正文
Lesson Memory
Purpose
Convert repeated defects into durable prevention rules without bloating global prompts.
Read policy
Before implementation, repair, or review, load lessons relevant to touched components. Prefer component/domain/tag matches over recency. Cap loaded lessons to avoid context bloat.
Write policy
Create or update a lesson when:
- the same finding appears more than once;
- a repair was non-obvious;
- a hidden assumption caused failure;
- a domain invariant was missed;
- an environment/tooling issue changed the correct command.
Lesson format
Each lesson should include:
- id;
- domain/component/tags;
- symptom;
- root cause;
- prevention rule;
- example task;
- date observed.
04 同仓库更多 Skills
invoice-domain-review
Domain review for contractor invoice governance, ingestion, reconciliation, attendance attribution and billing evidence.
python-domain-review
Reviews generic Python implementation against task intent, API expectations, simplicity and maintainability.
verified-commit
Creates a task-scoped commit only after validator and exact-tree postflight pass.
using-agent-skills
Selects and applies the smallest relevant set of skills for a task, preventing generic prompting and unused specialist guidance. Use at the start of every command, task, review, or repair cycle.
testing-patterns
Designs focused, hierarchical, regression, boundary, integration, and end-to-end tests for vertical-slice implementation. Use before and after implementation, and during test review.
test-hierarchy
Classifies and enforces the required unit, integration, local E2E, and cloud E2E test tier for a task or run.