📦

align

Name: align
Author: hmmhmmhm

內容修訂 r1 安全 ⚙️ 外部命令

Align Project Decisions With Your Expectations

Unclear goals and changing priorities can make agent decisions diverge from your expectations. Align captures confirmed criteria in ALIGN.md and reviews meaningful changes against them.

支援: Claude Codex Code(CC)

🥉 78 銅級

Maintain this Skill? Claim it 🥉 78 銅級

使用我的智慧代理安裝

將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。

智能體請求

Review the Skillstore skill "align" from https://skillstore.io/skills/hmmhmmhm-align.md and its manifest at https://skillstore.io/api/skills/hmmhmmhm-align/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。

Markdown 詳情 GET /skills/hmmhmmhm-align.md 已簽名 manifest GET /api/skills/hmmhmmhm-align/manifest 已簽名 lockfile GET /api/skills/hmmhmmhm-align/lockfile

測試它

正在使用「align」。 Align my appointment-booking project. Prioritize mobile access and keep payments out of the first release.

預期結果:

Draft purpose: Let customers book available appointment slots from a phone.
Priority: Mobile usability takes precedence over optional desktop enhancements.
Exclusion: Payment processing is outside the first release.
Open question: What booking completion rate will define success?
Confirmation status: Not yet confirmed; no agreement has been saved.

正在使用「align」。 Review a payment feature against our confirmed agreement, which excludes payments from the first release.

預期結果:

Meaningful drift: The payment feature conflicts with the confirmed first-release exclusion.
Proposed decision: Defer payment work unless you explicitly change the release scope.
The current agreement and full-confirmation timestamp remain unchanged.

正在使用「align」。 I authorize changing the launch platform from desktop to mobile. Keep all other agreement criteria.

預期結果:

Updated ALIGN.md: Launch platform is now mobile; unrelated criteria remain unchanged.
Recorded partial confirmation on the launch-platform criterion.
The full-alignment timestamp remains unchanged because this was not a full reconfirmation.

安全審計

安全

v1 • 2026/10/12 開啟版本化報告

All 14 static findings are false positives: Markdown formatting, a read-only Git check, and duplicate-section guidance. No evidence found of prompt injection, credential access, data exfiltration, or malicious execution. The skill requires authorized agreement changes, preserves existing instructions, and prohibits silent hooks or global configuration changes.

已掃描檔案

153

分析行數

複核項目

已忽略的誤報

風險因素

⚙️ 外部命令 (13)

SKILL.md:10 SKILL.md:17 SKILL.md:21 SKILL.md:59 SKILL.md:79 SKILL.md:80 SKILL.md:89 SKILL.md:94 SKILL.md:95 SKILL.md:98 SKILL.md:100 SKILL.md:111 SKILL.md:117

最近一次完成的靜態與語意稽核未偵測到已確認的安全發現。這並不能證明該 Skill 沒有副作用。

審計單位: codex

分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。

開啟版本化報告

複製報告連結

https://skillstore.io/skills/hmmhmmhm-align/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/hmmhmmhm-align/security.svg)](https://skillstore.io/skills/hmmhmmhm-align?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/hmmhmmhm-align?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/hmmhmmhm-align/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/hmmhmmhm-align.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

學術引用 (APA · BibTeX · CFF)

APA 引用

hmmhmmhm. (2026). align security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/hmmhmmhm-align/audits/1

BibTeX 引用

@techreport{hmmhmmhm-hmmhmmhm-align-2026,
  author = {hmmhmmhm},
  title = {align security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/hmmhmmhm-align/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "align security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "hmmhmmhm"
date-released: "2026-10-12"
url: "https://skillstore.io/skills/hmmhmmhm-align/audits/1"
identifiers:
  - type: other
    value: "skillstore:hmmhmmhm-align:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據證據置信度: 中

架構

可維護性

內容

社群

規範符合度

你可以打造什麼

Define a New Project

Clarify intended users, success criteria, priorities, and exclusions before an agent makes implementation decisions.

Review Development Drift

Compare relevant implementation changes with an existing agreement and propose revisions only when new evidence matters.

Clarify Writing Priorities

Record audience, quality expectations, constraints, and autonomy boundaries for an ongoing writing project.

試試這些提示

Start an Agreement

Use align to clarify goals for [project]. Ask about the most important gaps, then show a concise draft for my review.

Align an Existing Project

Use align for [project]. Review relevant documentation and summarize the current direction. Ask what I want to retain or change before drafting ALIGN.md.

Review Possible Drift

Use align to compare [recent changes] with our existing ALIGN.md. Use available history, disclose gaps, and propose revisions only for meaningful inconsistencies.

Update a Specific Criterion

Use align to update [criterion] to [new requirement]; I authorize this lasting change. Preserve unrelated criteria and the full-confirmation timestamp. Record this partial confirmation.

最佳實務

Identify the target project and provide existing agreements, relevant documentation, and available history.
State concrete priorities, exclusions, and autonomy boundaries when important values conflict.
Confirm lasting changes explicitly and distinguish partial updates from full agreement confirmation.

避免

Treating implementation choices or inferred preferences as confirmed user requirements.
Repeating a full interview when routine work already fits the current agreement.
Advancing the full-confirmation timestamp after automatic review or a partial change.

常見問題

What does align produce?

It drafts or updates a concise ALIGN.md agreement covering goals, success criteria, scope, priorities, constraints, and relevant unresolved matters.

Which AI tools are listed as supported?

The skill lists Claude, Codex, and Claude Code. Actual instruction loading depends on the target agent and its project configuration.

Does the project need Git?

No. Git history helps review changes, but the skill must disclose missing history and must not initialize Git without a request.

When does the skill save an agreement?

It saves after you confirm the draft or clearly authorize the particular lasting changes. Explicit delegation may authorize saving an unconfirmed draft.

Will every future agent enforce ALIGN.md automatically?

No. The skill adds a project instruction reference, but agent compatibility varies. It prohibits silent hook installation and global setting changes.

How are partial confirmations recorded?

Only affected criteria receive updated confirmation times. The full-alignment timestamp changes only when you confirm the complete agreement.