القائمة
Use when repeated project mistakes, review feedback, failed commands, onboarding friction, or team workflow lessons should become reusable AI development behavior for this repo.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | repo-self-improvement |
| description | Use when repeated project mistakes, review feedback, failed commands, onboarding friction, or team workflow lessons should become reusable AI development behavior for this repo. |
Turn repeated development lessons into reviewed, reusable project skills without letting agents rewrite shared behavior blindly.
Use this skill after tasks that reveal:
AGENTS.md, .cursorrules, docs, or .agents/skills/.Do not use it for one-off mistakes, personal preferences, or rules that can be enforced mechanically by lint, tests, or CI.
Agents may propose repo behavior improvements, but they must not silently overwrite shared team behavior. Proposals go through .agents/skill-proposals/ first unless the user explicitly asks to edit an existing skill.
Identify the lesson.
Classify the destination.
AGENTS.md: strict repo-wide operating rule..cursorrules: guard rail for all AI assistants..agents/skills/<name>/SKILL.md: reusable workflow or judgment pattern.docs/: human-facing setup, architecture, or contribution guidance.Draft a proposal under .agents/skill-proposals/.
YYYY-MM-DD-short-topic.md.Validate before promotion.
AGENTS.md, .cursorrules, and existing matching skills.Promote only after approval.
# Skill Proposal: <topic>
Date: YYYY-MM-DD
Target: <AGENTS.md | .cursorrules | .agents/skills/name/SKILL.md | docs/path.md | CI>
## Trigger
What happened, with concrete evidence.
## Proposed Behavior
What future agents or developers should do.
## Why It Belongs Here
Why this should be remembered instead of handled as a one-off.
## Validation
How to confirm the proposal is correct and non-conflicting.
Automatically generates and updates the CONTRIBUTORS.md file by analyzing git merge history, identifying authors who have merged at least 2 branches, and formatting the output beautifully.
Use when asking for a team report, assigning tasks, updating task status, or managing the sprint board for HealthBytes. Triggers on "reporte del equipo", "asignar tarea", "dame un resumen del sprint", "qué están haciendo los chicos", "nueva tarea para", or any team/task management request.
Use when updating HealthBytes docs, README files, roadmap, setup/env docs, architecture docs, AI inspections, agent prompts, weekly reports, or documentation structure.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when the user needs to change, update, or bump the app version of HealthBytes — mentions "versión", "version bump", "subir versión", "cambiar versión", "release", "nueva versión", or asks what version the app is on.
Mobile-first design and engineering doctrine for iOS and Android apps. Covers touch interaction, performance, platform conventions, offline behavior, and mobile-specific decision-making. Teaches principles and constraints, not fixed layouts. Use for React Native, Flutter, or native mobile apps.