.claude/skills/concept-radarRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
概念雷达——从一个链接或一批作者里,把「值得跟进的新概念」捞出来:去重、给证据、打分、可导出。治的是信息焦虑:不追热点,只留能落地的概念。Discovers, deduplicates, evaluates, and exports evidence-backed concepts from one URL or an author pool. Use when the user wants to track a field, mine an author's idea pool, or run recurring concept research; publishing is optional. Not a news feed — output is evidence-graded concepts, not breaking headlines.
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/concept-radarRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/concept-radarRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/concept-radarRuntime, 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 @bonniegeng-max/concept-radarclawhub inspect @bonniegeng-max/concept-radar --version 0.1.3This 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:cb3b64cfbf2cd50f177f39f199df5a91bf39c5687b0241e2ad0ac4bd58d5d895config/authors.example.yamlexamples/selection.example.jsonREADME.mdreferences/card-schema.jsonreferences/evidence-policy.mdreferences/quality-rubric.mdreferences/state-contract.mdRELEASE.mdscripts/concept_radar.pyskill-card.mdSKILL.mdtests/test_concept_radar.pyConcept Radar 0.1.3 shifts from a read-only, conversation-based workflow to a configurable scan-and-export workflow. - Adds single-URL and author-pool scanning, with Markdown and JSON exports by default. - Adds configuration, runtime state, validation, and recovery rules; failed fetches must not be treated as “no updates.” - Introduces structured concept cards with evidence-linked claims, maturity, confidence, action recommendations, and comparison sources. - Makes Feishu publishing optional and requires an explicit user request. - Adds documentation, schemas, scripts, examples, and tests; removes `_meta.json` and `skill-card.md`.
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
Permission escalation detectedThese older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:316cb6a1b22bd1afb8ec57164468cbd1a9b2142e28589f63fde28b1546c58419sha256:7a1c5ec2f8c5fe516617353c309c43ecde00b6d04f196b5cd0c4bb4cf0cad287sha256:55c28f97d248085227dd9f56885ae5bb6be3670928cd96c885f8c95e3ef8a152