.claude/skills/evaluate-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Measure a skill's reliability — run it k times for a pass@k score, design or interpret its eval, or compare it against the base agent. Use when the user wants to run, design, or interpret a skill's eval, or write an .eval.yaml spec.
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/evaluate-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/evaluate-skillRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/evaluate-skillRuntime, 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 @edonadei/evaluate-skillclawhub inspect @edonadei/evaluate-skill --version 1.0.14This 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.
sha256:2dad0e1a377430e6080891d630bcbbe30ea2da5b7d920f27cc15a2c17aaa906devaluate-skill.eval.yamlREFERENCE.mdskill-card.mdSKILL.md### Changed - Clean-up from the 1.0.13 that added way too much files. - Built around four questions, each with its own place to fix: does the skill fire (`description`), does it work (body), does it earn its place (the tasks), does it hold across edits. - New workflow order: run the control (`--ablate <skill>`) once, before editing the skill, and keep it. After each edit, compare against the previous full run as well as the control, because a worse skill can still beat the control. - New diagnosis table traces each failure to its fix: setup errors, unusable attempts, `cheat`, a skill that didn't fire, an extra skill that fired, a skill that fired but failed, and tasks that pass without the skill. - Specs it writes put `activates:` on every execution task (plus any skill the task delegates to), never name the skill in a prompt, and include at least one trigger probe. - Now owns writing a…
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.
sha256:522f41fc0084022791622e6a0fe46a4f7882665194dac578df8c07500f53b104