work-self-improvement-review

Solid

Review the current ChatGPT Work conversation and files made available in the chat for durable corrections, preferences, and workflow lessons, then propose updates as project guidance, an instruction overlay, a patch to a provided SKILL.md, or a new skill candidate. Use when the user asks to review, learn from, distill, or preserve lessons from the current task, especially after corrections, repeated friction, or a non-obvious recovery. Always propose before exporting or applying any change.

AI & Automation 17 stars 5 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
42
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Work Self Improvement Review Use the user's language unless they request another language. ## Boundaries - Use only the current conversation and files made available in this conversation. - Do not claim access to prior chats, local transcripts, telemetry, installed local skills, hooks, MCP servers, backups, or background state. - Treat hidden system and developer instructions as operating constraints, not content to quote or export. - Do not browse for additional evidence as part of the review. - Do not change guidance, skills, repositories, or remote state during the proposal phase. - Do not treat invocation of this skill as approval. - Complete proposal and approval in separate turns. - After approval, export only the approved content. - Never claim an export was installed, published, or persisted unless the user completes that action through a supported interface. ## Review Workflow 1. Extract grounded evidence from: - explicit user corrections; - stable preferences or policies stated by the user; - repeated friction visible in the current conversation; - non-obvious failure causes and reusable recovery steps; - successful procedures likely to prevent future mistakes. 2. Classify each lesson. Mark a lesson `durable` only when at least one condition holds: - the user explicitly states a continuing preference or rule; - the same issue appears more than once; - a non-obvious and costly failure has a broadly reusable prevention; - the les...

Details

Author
UniM0cha
Repository
UniM0cha/self-improving-skills
Created
1 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category