Help us improve
Share bugs, ideas, or general feedback.
Displays all learned instincts grouped by domain with confidence scores, progress bars, triggers, actions, and sources. Supports --domain, --low-confidence, --high-confidence, --source, --json flags.
npx claudepluginhub codelably/harmony-claude-codeHow this command is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:instinct-statusFiles this command reads when invoked
The summary Claude sees in its command listing — used to decide when to auto-load this command
# 本能状态查询命令(Instinct Status Command) 显示所有已学习的本能(Instincts)及其置信度分数,并按领域(Domain)进行分组。 ## 实现方式 使用插件根路径运行本能 CLI: 如果未设置 `CLAUDE_PLUGIN_ROOT`(手动安装),请使用: ## 用法 ## 执行逻辑 1. 从 `~/.claude/homunculus/instincts/personal/` 读取所有个人本能文件。 2. 从 `~/.claude/homunculus/instincts/inherited/` 读取继承的本能。 3. 按领域分组显示,并附带置信度进度条。 ## 输出格式 ## 参数 (Flags) - `--domain <name>`: 按领域筛选(如 code-style, testing, git 等) - `--low-confidence`: 仅显示置信度 < 0.5 的本能 - `--high-confidence`: 仅显示置信度 >= 0.7 的本能 - `--source <type>`: 按来源筛选(session-observation, repo-analysis, inherited) - `--json`: 以 JSON 格式输出,便于程序化调用
/instinct-statusDisplays learned instincts (project-level and global) grouped by domain, with confidence bars and observation statistics.
/instinct-statusShows learned instincts for the current project and global ones, grouped by domain with confidence bars and observation stats.
/instinct-statusDisplays learned instincts from .claude/instincts.md as a sorted table with confidence scores, categories, status, sources, plus a summary of totals, averages, and conflicts.
/instinct-statusDisplays learned instincts with descriptions, confidence scores (0.0-1.0), last used dates, and contexts (e.g., compose, mvi). Supports --type filtering.
/instinct-statusShows learned instincts for the current project and global ones, grouped by domain with confidence bars and observation stats.
Share bugs, ideas, or general feedback.
显示所有已学习的本能(Instincts)及其置信度分数,并按领域(Domain)进行分组。
使用插件根路径运行本能 CLI:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/scripts/instinct-cli.py" status
如果未设置 CLAUDE_PLUGIN_ROOT(手动安装),请使用:
python3 ~/.claude/skills/continuous-learning-v2/scripts/instinct-cli.py status
/instinct-status
/instinct-status --domain code-style
/instinct-status --low-confidence
~/.claude/homunculus/instincts/personal/ 读取所有个人本能文件。~/.claude/homunculus/instincts/inherited/ 读取继承的本能。📊 本能状态 (Instinct Status)
==================
## 代码风格 (Code Style) (4 条本能)
### prefer-functional-style
触发器 (Trigger):编写新函数时
动作 (Action):优先使用函数式模式而非类
置信度 (Confidence):████████░░ 80%
来源 (Source):会话观察 (session-observation) | 最近更新:2025-01-22
### use-path-aliases
触发器 (Trigger):导入模块时
动作 (Action):使用 @/ 路径别名而非相对导入
置信度 (Confidence):██████░░░░ 60%
来源 (Source):仓库分析 (repo-analysis) (github.com/acme/webapp)
## 测试 (Testing) (2 条本能)
### test-first-workflow
触发器 (Trigger):添加新功能时
动作 (Action):先写测试,再写实现
置信度 (Confidence):█████████░ 90%
来源 (Source):会话观察 (session-observation)
## 工作流 (Workflow) (3 条本能)
### grep-before-edit
触发器 (Trigger):修改代码时
动作 (Action):先用 Grep 搜索,再用 Read 确认,最后 Edit 编辑
置信度 (Confidence):███████░░░ 70%
来源 (Source):会话观察 (session-observation)
---
总计:9 条本能 (4 条个人, 5 条继承)
观察器 (Observer):运行中 (最近分析:5 分钟前)
--domain <name>: 按领域筛选(如 code-style, testing, git 等)--low-confidence: 仅显示置信度 < 0.5 的本能--high-confidence: 仅显示置信度 >= 0.7 的本能--source <type>: 按来源筛选(session-observation, repo-analysis, inherited)--json: 以 JSON 格式输出,便于程序化调用