skill-stocktake

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

skill-stocktake

Slash command (

/skill-stocktake

) that audits all Claude skills and commands using a quality checklist + AI holistic judgment. Supports two modes: Quick Scan for recently changed skills, and Full Stocktake for a complete review.

斜杠命令 (

/skill-stocktake

)，通过质量检查表+AI整体判断来审计所有Claude技能和命令。支持两种模式：针对近期更改技能的快速扫描，以及全面审查的完整盘点。

Scope

适用范围

The command targets the following paths relative to the directory where it is invoked:

Path	Description
`~/.claude/skills/`	Global skills (all projects)
`{cwd}/.claude/skills/`	Project-level skills (if the directory exists)

At the start of Phase 1, the command explicitly lists which paths were found and scanned.

该命令针对以下相对于调用目录的路径：

路径	描述
`~/.claude/skills/`	全局技能（所有项目通用）
`{cwd}/.claude/skills/`	项目级技能（仅当目录存在时）

在第一阶段开始时，命令会明确列出已找到并扫描的路径。

Targeting a specific project

针对特定项目

To include project-level skills, run from that project's root directory:

bash

cd ~/path/to/my-project
/skill-stocktake

If the project has no

.claude/skills/

directory, only global skills and commands are evaluated.

如需包含项目级技能，请从该项目的根目录运行命令：

bash

cd ~/path/to/my-project
/skill-stocktake

如果项目没有

.claude/skills/

目录，则仅评估全局技能和命令。

Modes

运行模式

Mode	Trigger	Duration
Quick Scan	`results.json` exists (default)	5–10 min
Full Stocktake	`results.json` absent, or `/skill-stocktake full`	20–30 min

Results cache:

~/.claude/skills/skill-stocktake/results.json

模式	触发条件	耗时
快速扫描	存在 `results.json` （默认模式）	5–10分钟
完整盘点	不存在 `results.json` ，或执行 `/skill-stocktake full`	20–30分钟

结果缓存路径：

~/.claude/skills/skill-stocktake/results.json

Quick Scan Flow

快速扫描流程

Re-evaluate only skills that have changed since the last run (5–10 min).

Read

~/.claude/skills/skill-stocktake/results.json

Run:

bash ~/.claude/skills/skill-stocktake/scripts/quick-diff.sh \       ~/.claude/skills/skill-stocktake/results.json

(Project dir is auto-detected from

$PWD/.claude/skills

; pass it explicitly only if needed)

If output is
```
[]
```
: report "No changes since last run." and stop
Re-evaluate only those changed files using the same Phase 2 criteria
Carry forward unchanged skills from previous results
Output only the diff

Run:

bash ~/.claude/skills/skill-stocktake/scripts/save-results.sh \       ~/.claude/skills/skill-stocktake/results.json <<< "$EVAL_RESULTS"

仅重新评估自上次运行以来已更改的技能（耗时5–10分钟）。

读取

~/.claude/skills/skill-stocktake/results.json

执行：

bash ~/.claude/skills/skill-stocktake/scripts/quick-diff.sh \       ~/.claude/skills/skill-stocktake/results.json

（项目目录会从

$PWD/.claude/skills

自动检测；仅在需要时显式传入）

若输出为
```
[]
```
：报告“自上次运行以来无更改。”并终止流程
使用与第二阶段相同的标准仅重新评估已更改的文件
沿用上次结果中未更改的技能
仅输出差异内容

执行：

bash ~/.claude/skills/skill-stocktake/scripts/save-results.sh \       ~/.claude/skills/skill-stocktake/results.json <<< "$EVAL_RESULTS"

Full Stocktake Flow

完整盘点流程

Phase 1 — Inventory

第一阶段 — 盘点

Run:

bash ~/.claude/skills/skill-stocktake/scripts/scan.sh

The script enumerates skill files, extracts frontmatter, and collects UTC mtimes. Project dir is auto-detected from

$PWD/.claude/skills

; pass it explicitly only if needed. Present the scan summary and inventory table from the script output:

Scanning:
  ✓ ~/.claude/skills/         (17 files)
  ✗ {cwd}/.claude/skills/    (not found — global skills only)

Skill	7d use	30d use	Description

执行：

bash ~/.claude/skills/skill-stocktake/scripts/scan.sh

该脚本会枚举技能文件、提取前置元数据并收集UTC修改时间。项目目录会从

$PWD/.claude/skills

自动检测；仅在需要时显式传入。展示脚本输出中的扫描摘要和盘点表格：

Scanning:
  ✓ ~/.claude/skills/         (17 files)
  ✗ {cwd}/.claude/skills/    (not found — global skills only)

Skill	7d use	30d use	Description

Phase 2 — Quality Evaluation

第二阶段 — 质量评估

Launch an Agent tool subagent (general-purpose agent) with the full inventory and checklist:

text

Agent(
  subagent_type="general-purpose",
  prompt="
Evaluate the following skill inventory against the checklist.

[INVENTORY]

[CHECKLIST]

Return JSON for each skill:
{ \"verdict\": \"Keep\"|\"Improve\"|\"Update\"|\"Retire\"|\"Merge into [X]\", \"reason\": \"...\" }
"
)

The subagent reads each skill, applies the checklist, and returns per-skill JSON:

{ "verdict": "Keep"|"Improve"|"Update"|"Retire"|"Merge into [X]", "reason": "..." }

Chunk guidance: Process ~20 skills per subagent invocation to keep context manageable. Save intermediate results to

results.json

(

status: "in_progress"

) after each chunk.

After all skills are evaluated: set

status: "completed"

, proceed to Phase 3.

Resume detection: If

status: "in_progress"

is found on startup, resume from the first unevaluated skill.

Each skill is evaluated against this checklist:

- [ ] Content overlap with other skills checked
- [ ] Overlap with MEMORY.md / CLAUDE.md checked
- [ ] Freshness of technical references verified (use WebSearch if tool names / CLI flags / APIs are present)
- [ ] Usage frequency considered

Verdict criteria:

Verdict	Meaning
Keep	Useful and current
Improve	Worth keeping, but specific improvements needed
Update	Referenced technology is outdated (verify with WebSearch)
Retire	Low quality, stale, or cost-asymmetric
Merge into [X]	Substantial overlap with another skill; name the merge target

Evaluation is holistic AI judgment — not a numeric rubric. Guiding dimensions:

Actionability: code examples, commands, or steps that let you act immediately
Scope fit: name, trigger, and content are aligned; not too broad or narrow
Uniqueness: value not replaceable by MEMORY.md / CLAUDE.md / another skill
Currency: technical references work in the current environment

Reason quality requirements — the

reason

field must be self-contained and decision-enabling:

Do NOT write "unchanged" alone — always restate the core evidence

For Retire: state (1) what specific defect was found, (2) what covers the same need instead

Bad:
```
"Superseded"
```

Good:

"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains."

For Merge: name the target and describe what content to integrate

Bad:
```
"Overlaps with X"
```

Good:

"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill."

For Improve: describe the specific change needed (what section, what action, target size if relevant)

Bad:
```
"Too long"
```

Good:

"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines."

For Keep (mtime-only change in Quick Scan): restate the original verdict rationale, do not write "unchanged"

Bad:
```
"Unchanged"
```

Good:

"mtime updated but content unchanged. Unique Python reference explicitly imported by rules/python/; no overlap found."

传入完整盘点清单和检查表，启动一个Agent工具子代理（通用代理）：

text

Agent(
  subagent_type="general-purpose",
  prompt="
Evaluate the following skill inventory against the checklist.

[INVENTORY]

[CHECKLIST]

Return JSON for each skill:
{ \"verdict\": \"Keep\"|\"Improve\"|\"Update\"|\"Retire\"|\"Merge into [X]\", \"reason\": \"...\" }
"
)

子代理会读取每个技能，应用检查表，并返回每个技能的JSON结果：

{ "verdict": "Keep"|"Improve"|"Update"|"Retire"|"Merge into [X]", "reason": "..." }

分块处理指南： 每次调用子代理时处理约20个技能，以确保上下文可控。每处理完一个分块后，将中间结果保存到

results.json

（

status: "in_progress"

）。

所有技能评估完成后：将

status

设为

"completed"

，进入第三阶段。

续处理检测： 启动时如果发现

status: "in_progress"

，则从第一个未评估的技能开始续处理。

每个技能将根据以下检查表进行评估：

- [ ] Content overlap with other skills checked
- [ ] Overlap with MEMORY.md / CLAUDE.md checked
- [ ] Freshness of technical references verified (use WebSearch if tool names / CLI flags / APIs are present)
- [ ] Usage frequency considered

判定标准：

判定结果	含义
Keep	有用且内容最新
Improve	值得保留，但需要特定改进
Update	引用的技术已过时（需通过WebSearch验证）
Retire	质量低下、内容陈旧或投入产出比失衡
Merge into [X]	与另一技能存在大量重叠；请指定合并目标

评估采用AI整体判断——而非量化评分。评估维度包括：

可操作性：提供可直接执行的代码示例、命令或步骤
范围匹配度：技能名称、触发条件和内容一致；既不过宽也不过窄
独特性：具备MEMORY.md / CLAUDE.md / 其他技能无法替代的价值
时效性：技术参考在当前环境中仍有效

理由质量要求——

reason

字段必须完整且可支撑决策：

不得仅写"unchanged"——必须重述核心依据

对于淘汰：说明(1) 发现的具体问题，(2) 可替代的方案

错误示例：
```
"Superseded"
```

正确示例：

"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains."

对于合并：指定目标技能并说明需整合的内容

错误示例：
```
"Overlaps with X"
```

正确示例：

"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill."

对于优化：说明具体的修改需求（哪部分内容、修改动作、目标篇幅等）

错误示例：
```
"Too long"
```

正确示例：

"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines."

对于保留（快速扫描中仅修改时间变化）：重述原判定理由，不得仅写"unchanged"
- 错误示例：
```
"Unchanged"
```
- 正确示例：
```
"mtime updated but content unchanged. Unique Python reference explicitly imported by rules/python/; no overlap found."
```

Phase 3 — Summary Table

第三阶段 — 汇总表

Skill	7d use	Verdict	Reason

Skill	7d use	判定结果	理由

Phase 4 — Consolidation

第四阶段 — 整合

Retire / Merge: present detailed justification per file before confirming with user:
- What specific problem was found (overlap, staleness, broken references, etc.)
- What alternative covers the same functionality (for Retire: which existing skill/rule; for Merge: the target file and what content to integrate)
- Impact of removal (any dependent skills, MEMORY.md references, or workflows affected)
Improve: present specific improvement suggestions with rationale:
- What to change and why (e.g., "trim 430→200 lines because sections X/Y duplicate python-patterns")
- User decides whether to act
Update: present updated content with sources checked
Check MEMORY.md line count; propose compression if >100 lines

淘汰/合并: 在获得用户确认前，为每个文件提供详细理由：
- 发现的具体问题（重叠、陈旧、无效引用等）
- 可替代的功能方案（淘汰：现有技能/规则；合并：目标文件及需整合的内容）
- 删除的影响（是否有依赖技能、MEMORY.md引用或工作流受影响）
优化: 提供具体的改进建议及理由：
- 需修改的内容及原因（例如：“从430行精简至200行，因为X/Y章节与python-patterns重复”）
- 由用户决定是否执行
更新: 提供经来源验证的更新内容
检查MEMORY.md的行数；如果超过100行，建议压缩

Results File Schema

结果文件结构

~/.claude/skills/skill-stocktake/results.json

evaluated_at
: Must be set to the actual UTC time of evaluation completion. Obtain via Bash:

date -u +%Y-%m-%dT%H:%M:%SZ

. Never use a date-only approximation like

T00:00:00Z

json

{
  "evaluated_at": "2026-02-21T10:00:00Z",
  "mode": "full",
  "batch_progress": {
    "total": 80,
    "evaluated": 80,
    "status": "completed"
  },
  "skills": {
    "skill-name": {
      "path": "~/.claude/skills/skill-name/SKILL.md",
      "verdict": "Keep",
      "reason": "Concrete, actionable, unique value for X workflow",
      "mtime": "2026-01-15T08:30:00Z"
    }
  }
}

~/.claude/skills/skill-stocktake/results.json

evaluated_at
: 必须设为评估完成的实际UTC时间。可通过Bash命令获取：

date -u +%Y-%m-%dT%H:%M:%SZ

。禁止使用仅日期的近似值如

T00:00:00Z

。

json

{
  "evaluated_at": "2026-02-21T10:00:00Z",
  "mode": "full",
  "batch_progress": {
    "total": 80,
    "evaluated": 80,
    "status": "completed"
  },
  "skills": {
    "skill-name": {
      "path": "~/.claude/skills/skill-name/SKILL.md",
      "verdict": "Keep",
      "reason": "Concrete, actionable, unique value for X workflow",
      "mtime": "2026-01-15T08:30:00Z"
    }
  }
}

Notes

注意事项

Evaluation is blind: the same checklist applies to all skills regardless of origin (ECC, self-authored, auto-extracted)
Archive / delete operations always require explicit user confirmation
No verdict branching by skill origin

评估采用盲审机制：所有技能无论来源（ECC、自行编写、自动提取）均适用同一检查表
归档/删除操作始终需要用户明确确认
不会根据技能来源进行差异化判定