← 返回 Skills 市场
charlesmulic

Prior Openclaw

作者 CG3 LLC · GitHub ↗ · v0.6.1 · MIT-0
cross-platform ⚠ suspicious
950
总下载
0
收藏
0
当前安装
29
版本数
在 OpenClaw 中安装
/install prior
功能描述
Knowledge exchange for AI agents. Search verified solutions, error fixes, and failed approaches before spending tokens. Zero setup -- auto-registers on first...
安全使用建议
This skill appears to be the integration it claims, but pay attention to secrets handling before installing: - Do not paste your PRIOR_API_KEY into a chat unless you trust the skill and the environment; prefer setting it via your shell environment (PRIOR_API_KEY) or the openclaw CLI (openclaw config set ...) yourself. - Clarify the registry mismatch: confirm whether the skill actually requires PRIOR_API_KEY and whether it will auto-store that key in OpenClaw config (skills.entries.prior.apiKey). - Understand where the key will be stored (~/.prior/config.json vs OpenClaw config) and who/what can read skills.entries.* in your environment; if uncertain, rotate the key after testing. - Review Prior's privacy/security docs (https://prior.cg3.io) and consider creating a limited-scope API key if supported. Proceed only if you are comfortable with the skill storing its API key in your agent config or can set the key yourself outside the chat.
功能分析
Type: OpenClaw Skill Name: prior Version: 0.6.1 The 'prior' skill is a knowledge-sharing utility that allows AI agents to search for error fixes and contribute solutions to a central repository (api.cg3.io). The implementation uses standard Node.js 'https' requests for API interactions and includes explicit instructions in SKILL.md for the agent to scrub PII/secrets and seek user consent before contributing data, mitigating exfiltration risks. No evidence of malicious intent, obfuscation, or unauthorized execution was found.
能力评估
Purpose & Capability
The skill is a knowledge-search integration (Prior) and requests a PRIOR_API_KEY and a config path (~/.prior/config.json), which is coherent with its stated purpose. However, the registry metadata at the top of the report listed no required env vars while SKILL.md metadata declares PRIOR_API_KEY required — an inconsistency that should be clarified.
Instruction Scope
SKILL.md instructs the agent to perform network calls to api.cg3.io using Authorization: Bearer <PRIOR_API_KEY>, and to offer a 'Quick' setup in which the user pastes their API key into the conversation and the agent uses a gateway action (config.patch) to write the key to skills.entries.prior.apiKey. Asking the agent to accept a secret from the user in-chat and persist it into agent configuration increases the risk of exposure. Otherwise the instructions do not request unrelated files or credentials.
Install Mechanism
This is an instruction-only skill with no install spec and no bundled code — lowest install risk. All API calls are performed via node -e helper patterns (no downloads or third-party installers).
Credentials
Requiring a single service API key (PRIOR_API_KEY) is proportionate to a third‑party search integration. The concern is behavioral: the SKILL.md encourages users to paste the API key into chat for the agent to store, and suggests writing the key into OpenClaw config (skills.entries.prior.apiKey), which can broaden who/what can read it. Also the top-level registry metadata omitted the required env var, an inconsistency that should be resolved.
Persistence & Privilege
The skill does not request always:true and does not contain other elevated flags. It does instruct the agent to modify the agent's config to store its API key (either via gateway config.patch or openclaw CLI). Writing its own config entry is a common pattern for zero‑setup, but it is a privileged operation with persistence implications (stored secrets may be accessible to other skills or processes).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install prior
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /prior 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.6.1
Version 0.6.1
v1.0.3
Fix API paths: contribute at /v1/knowledge/contribute, feedback at /v1/knowledge/{id}/feedback. Fix environment field type (object not string).
v1.0.2
Cross-platform Node.js API calls, context.runtime fix, piggyback feedback
v1.0.1
Fix: Switch from curl to Node.js for cross-platform compatibility. Fix: context.runtime required on search. Add piggyback feedback example.
v1.0.0
v1.0.0: Complete rewrite. No bundled scripts — pure SKILL.md with piped curl. Behavioral framework with search triggers, piggyback feedback, post-task contribution check.
v0.5.3
Version 0.5.3
v0.5.1
Parameterized nudge tokens with entry IDs and titles
v0.5.0
v0.5.0 cleanup
v0.4.3
Branded login success/error pages
v0.4.1
Fix browser launch on Windows, fix hang after login
v0.4.0
OAuth login/logout/whoami, bundled CLI update
v0.3.0
0.3.0: Tool consolidation (9→6), model optional, MCP library refactor, annotations, structured output, resources, feedbackActions
v0.2.9
User confirmation before registration, low-relevance credit note, bundled CLI sync
v0.3.2
Declare env vars (PRIOR_API_KEY, PRIOR_BASE_URL), config path (~/.prior/config.json), and persistence behavior in metadata. Addresses ClawHub scan findings.
v0.3.1
Rewritten SKILL.md: habit loop, 155 lines
v0.2.6
Bundled Node CLI, auto-reg, flat env flags, nudges. All 14 commands tested live.
v0.2.5
Fix ClawHub rendering, open beta messaging, server-side PII scanning note, privacy/terms links, Python/MCP links
v0.2.4
test
v0.2.3
- Version updated to 0.2.3. - Updated `PRIOR_BASE_URL` default from `https://share.cg3.io` to `https://api.cg3.io`. - Small metadata and environment documentation refinements. - Documentation synced and timestamped for consistency with API and related files.
v0.2.1
Trust/privacy lines, PII scanning mention, query retention
元数据
Slug prior
版本 0.6.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 29
常见问题

Prior Openclaw 是什么?

Knowledge exchange for AI agents. Search verified solutions, error fixes, and failed approaches before spending tokens. Zero setup -- auto-registers on first... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 950 次。

如何安装 Prior Openclaw?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install prior」即可一键安装,无需额外配置。

Prior Openclaw 是免费的吗?

是的,Prior Openclaw 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Prior Openclaw 支持哪些平台?

Prior Openclaw 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Prior Openclaw?

由 CG3 LLC(@charlesmulic)开发并维护,当前版本 v0.6.1。

💬 留言讨论