Skill85 estrellas del repoactualizado 25d ago

memory

The memory skill persists project state and user preferences across sessions by automatically saving compressed configurations to local files when sessions end or before compaction occurs. Use this when you need to maintain project settings, preferences, and context between separate Claude interactions while ensuring sensitive data like API keys and passwords are never stored.

Ver fuente Repositorio: autocode

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/memory && cp -r /tmp/memory/skills/memory ~/.claude/skills/memory

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

::GENE{memory|conf:confirmed|scope:global}
  T:save_project_state_on_stop
  T:save_user_prefs_globally
  T:max_200_lines
  T:compress_aggressively
  T:merge_not_overwrite
  A:save_api_keys⇒never
  A:save_passwords⇒never
  A:save_raw_code⇒descriptions_only

::ACTIVATE{memory}
  ON:session_end
  ON:before_compact

::FACT{path:project|value:.autocode/memory.md}
::FACT{path:global|value:~/.autocode/user.md}

Powered by I-Lang v4.0 | ilang.ai

Del mismo repositorio

ask-smartSkill

Before coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.

auto-qualitySkill

Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.

best-choiceSkill

When multiple solutions exist, pick the best one. Explain why in one sentence.

build-featureSkill

Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.

build-scaffoldSkill

Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.

build-uiSkill

Build user-facing interface. Clean, functional, mobile-friendly by default.

celebrateSkill

Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.

clarify-scopeSkill

Classify request as small/medium/large. Adjust workflow depth accordingly.