Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/31/2026.claude/skills/cross-session-memoryRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
cross-session-memory
给 AI agent/bot 做跨会话持久记忆的分层混合方案。当用户要"给 bot 加记忆""让 agent 记住之前的事""跨会话上下文持久化""记忆去重/断链/陈旧检查"，或要搭一个有长期记忆的 agent 时使用。方案=markdown 真理源(人可读可手改) + SQLite 派生索引(选择性召回) + 生命周期检查(断链/重复/陈旧)，纯标准库零依赖。
Identity and source
Publisher attributionsharinchan233registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 61% rule confidence
Package forminstruction with code11 recorded files
Canonical sourceClawHub registryclawhub:sharinchan233:cross-session-memory
Platform declarations
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
OpenClawnative officialProvenance: registry distribution
Independent structural checks
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/31/2026.agents/skills/cross-session-memoryRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/31/2026skills/cross-session-memoryRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Installation and inspection
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @sharinchan233/cross-session-memoryclawhub inspect @sharinchan233/cross-session-memory --version 1.0.0Security evidence
SkillVetAI static result: no findings detected
This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
- Status
- completed
- Coverage
- full text content
- Files
- 11 / 11 inspected as text
- Checked
- 8/31/2026, 12:46:38 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
2 inferred permission indicators
- network access — automatically inferred
- filesystem read — automatically inferred
1 dependency and API indicators
- api: clawhub.ai
External clawhub result: clean
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
- Evidence checked
- 8/31/2026, 11:48:41 AM
- Release binding
- Matches this record
- vt: clean
- skillspector: clean
- llm: clean
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:b982056d4a8983fbf051c94118a1331d8268a5c3d501e8c1197376d8004650d0Show up to 11 recorded paths
examples/sample-memory/MEMORY.mdexamples/sample-memory/note-a.mdexamples/sample-memory/note-b.mdexamples/sample-memory/old-experiment.mdexamples/sample-memory/robot-arm-servos.mdexamples/sample-memory/thesis-syntactic-priming.mdscripts/build_index.pyscripts/lint.pyscripts/recall.pyskill-card.mdSKILL.md
Source changelog
- Initial release of cross-session-memory skill. - Provides a layered hybrid long-term memory for AI bots/agents with human-readable markdown as the source, SQLite for selective recall, and lifecycle checks for data integrity. - Enables efficient, accurate recall across sessions while automatically handling deduplication, link checking, and data staleness. - Zero dependencies—only Python standard library required; works well with Chinese substring matching. - Includes sample usage and scripts for indexing, recall, and linting memory data.