.claude/skills/self-improving-agent1 structural issue
- error: metadata must be a mapping.
SKILL.md
Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is outdated, or a better approach is found. Review relevant saved guidance before major tasks, reuse, and promotion; revalidate it according to wha
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/self-improving-agentSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/self-improving-agentSKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/self-improving-agentSKILL.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 @pskoett/self-improving-agentclawhub inspect @pskoett/self-improving-agent --version 4.0.5This 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.
sha256:9a30522d490acf73535c22a14c7b5a56371439e9a825dd770d72184512ad8186assets/ERRORS.mdassets/FEATURE_REQUESTS.mdassets/LEARNINGS.mdassets/SKILL-TEMPLATE.mdCHANGELOG.mdhooks/openclaw/handler.jshooks/openclaw/handler.test.jshooks/openclaw/handler.tshooks/openclaw/HOOK.mdreferences/examples.mdreferences/maintenance-evals.mdreferences/openclaw-integration.mdreferences/uninstall.mdscripts/extract-skill.shskill-card.mdSKILL.md## 4.0.5 ### Fixed - Disabling the hook now preserves learning history. Disable the whole hook and restart; there is no separate reminder-only switch. - Uninstall instructions use the actual installation paths and archive the skill and hook outside discovery directories. - Learning files and promoted workspace guidance are preserved during uninstall. Permanent data deletion requires separate explicit authorization, verified paths, and a verified backup. - Feature-request logging now requires evidence of a missing capability. Ordinary questions and follow-up tasks no longer count as automatic logging triggers. ### Upgrade notes Update the installed skill and start a fresh session. Hook code is unchanged from 4.0.4, so no hook replacement or learning-data migration is needed.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:3f0a4d7d90607bf8bc3db75a5d214a9bb0e7bd184fa107c80324b7b5a7dc2d5f