技能盘点与效能体检
Office-agent skill inventory & health check. Scans any skills directory, measures size and context-token footprint, detects duplicates, and classifies skills into used / protected / closeable / manual-review buckets. Reverse-dependency scanning locks every skill referenced by automations, hooks
as observed 2026-10-07T11:52:53.866Z- Identifier
agent-skill-inventory- Source
- ClawHub
- Version observed
- 1.4.0
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-03T08:46:10.142Z
- Observations recorded
- 3
- Installs (reported upstream)
- 0
- Weekly downloads (upstream)
- 244
- Declared license
- MIT-0
Observation history
2026-10-07T11:52:53.866Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Scanner-driven hardening v1.3.1-v1.3.3: (1) rephrased the SKILL.en.md bullet that tripped the secret regex; (2) report-language wording no longer uses always/始终 — 'report language | "TRACE report remediation (1.3.3 -> 1.4.0): (1) new FAQ section with 9 Q&As in SKILL.md plus a 5-question quick reference in README, including a 6-row error-code table (E-LOG/E-ROO |
latestVersion |
"1.3.3" | "1.4.0" |
2026-10-05T10:33:23.015Z
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Language setting: --set-lang auto|zh|en (saved preference, effective immediately) + --show-lang (current setting and option descriptions); --lang stays a one-off override; auto fo | "Scanner-driven hardening v1.3.1-v1.3.3: (1) rephrased the SKILL.en.md bullet that tripped the secret regex; (2) report-language wording no longer uses always/始终 — 'report language |
latestVersion |
"1.3.0" | "1.3.3" |
summary |
"Office-agent skill inventory & health check. Scans any skills directory, measures size and context-token footprint, detects duplicates, and classifies skills into used / protected | "Office-agent skill inventory & health check. Scans any skills directory, measures size and context-token footprint, detects duplicates, and classifies skills into used / protected |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.