a5c-ai AI Skills

浏览 a5c-ai 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。

232 个技能

全部技能

GitHub

patrol-monitoring

a5c-ai

Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.

GitHub

codebase-sync

a5c-ai

Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.

GitHub

context-preservation

a5c-ai

State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.

GitHub

persistent-memory

a5c-ai

Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.

GitHub

systematic-debugging

a5c-ai

Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.

GitHub

vector-memory

a5c-ai

HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.

GitHub

systematic-debugging

a5c-ai

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.

GitHub

design-token-transformer

a5c-ai

Transform design tokens across multiple formats and platforms. Parse W3C design token format, transform to CSS/SCSS/JS/iOS/Android, handle token aliases and references, and generate documentation.

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。