Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/24/2026.claude/skills/auto-promptRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registry
auto-prompt
策略先行的解题协议（fore.vip）。用户抛出一个主题、问题或想法（要做的事、卡住的问题、想要的结果）时，先出一份最佳策略卡——按「本机已有资产 → 模型自有知识 → 主题相关官方文档 → 主题 T1 社区 → 搜索引擎」逐级做复用检查、命中即停，取最短路径；再拿策略回看原问题做一轮对抗式审视（是否答非所问 / 是否还有更短路径 / 是否跳级凭记忆作答 / 产物是否超纲），最多回炉一轮；然后按策略执行、结论先行地精简交付；问题解决后按「四问」判据把关键点沉淀进记忆（跨会话可复用、是事实而非过程、不与既有条目重复、低熵），碎片与流水账不写。当用户说「XX 怎么做」「帮我搞定 XX」「这个问题怎
Identity and source
Publisher attributionFORER AUTOregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction bundle3 recorded files
Canonical sourceClawHub registryclawhub:fore-auto:auto-prompt
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 · 9/24/2026.agents/skills/auto-promptRuntime, 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 · 9/24/2026skills/auto-promptRuntime, 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 @fore-auto/auto-promptclawhub inspect @fore-auto/auto-prompt --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
- 3 / 3 inspected as text
- Checked
- 9/24/2026, 4:47:59 AM
- Scanner
- 0.1.3
- Policy
- 1.0.3
1 inferred permission indicators
- network access — automatically inferred
1 dependency and API indicators
- api: clawhub.ai
External clawhub result: suspicious
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
- 9/23/2026, 7:17:38 PM
- Release binding
- Matches this record
- skillspector: suspicious
- llm: suspicious
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:48ebaef66f8a1607c58fb827484a4e43bddfd86eca9eb2b956b0d4021cb668ceShow up to 3 recorded paths
references/sources.mdskill-card.mdSKILL.md
Source changelog
AUTO.Prompt 1.0.0 initial release: - Introduces a strategy-first problem-solving protocol with tiered resource reuse and strict process control. - Provides a reusable strategy card template for handling tasks, questions, or solution requests. - Enforces shortest-path resolution by checking local assets, model knowledge, official docs, T1 communities, then search—stop at first hit. - Adds an adversarial review step to ensure relevance, minimality, and accuracy before execution. - Delivers concise, conclusion-first results, and persists only factual, reusable, non-duplicate low-entropy key points to memory.