.claude/skills/snapshot-wipe-resilience1 structural issue
- error: description exceeds the 1,024-character Agent Skills limit.
SKILL.md
Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Detect and auto-repair partially-wiped agent workspaces, with hybrid post-quantum end-to-end encryption (X25519+ML-KEM-1024, ML-DSA-87) for any data sent off-box in sandboxes that only persist part of the filesystem between turns, and sync the recovery manifest off-box to a pastebin so it survives a total wipe. Verifies integrity (hash, byte-size, exec bits, tree sentinels) instead of mere existence, then runs tiered restore recipes for exactly the damaged pieces. Use when: (1) an agent sandbox 'forgets' files, bi…
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/snapshot-wipe-resilienceSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/snapshot-wipe-resilienceSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/snapshot-wipe-resilienceSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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 @orionshaowswmw/snapshot-wipe-resilienceclawhub inspect @orionshaowswmw/snapshot-wipe-resilience --version 1.4.10This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:7356983dd8bb0737852047c728bbff76aa888e630d051d257cef1c649d5d5bae_meta.jsonREADME.mdreference/manifest.example.jsonreference/turn-start-hook.shscripts/swr_crypto.pyscripts/swr_paste.pyscripts/swr.pyskill-card.mdSKILL.mdv1.5.0 any-workspace: agent presets (arena/openclaw/claude-code/generic) with secrets-never-in-recipes rule + symlink-escape guard, swr models scan -> blob tracking, export-recipes sh/md/json portable runbook (toposorted, bash -n valid)