universal-audit
92Audit Software Releases with Evidence
Release decisions often rely on incomplete evidence and inconsistent standards. This skill applies structured controls, deterministic scoring, and mandatory gates to assess readiness.
Polish Drafts While Preserving Your Voice
Automated drafts can sound repetitive or overly polished and may lose the writer's original voice. This skill applies minimal editorial fixes while preserving meaning.
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。
Review the Skillstore skill "human-writer" from https://skillstore.io/skills/glenskii-human-writer.md and its manifest at https://skillstore.io/api/skills/glenskii-human-writer/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。
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。
正在使用「human-writer」。 The app serves as a robust platform that streamlines daily reporting.
預期結果:
The app is a platform that simplifies daily reporting.
正在使用「human-writer」。 Audit this paragraph without editing: Distribution matters. This is the part most people skip.
預期結果:
Faux-insight setup: "This is the part most people skip." Suggested fix: remove the setup and keep the concrete claim.
正在使用「human-writer」。 Please polish this direct email: I need the revised figures by Thursday. Let me know if you would like more detail.
預期結果:
I need the revised figures by Thursday.
All 15 static findings are false positives caused by editorial prose, Markdown code spans, or a clear Unicode literal. The bundled script performs local text checks without dynamic commands, network access, or obfuscated behavior.
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。
https://skillstore.io/skills/glenskii-human-writer/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/glenskii-human-writer?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/glenskii-human-writer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/glenskii-human-writer/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/glenskii-human-writer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>glenskii. (2026). human-writer security audit report (audit version 3) [Author version 1.2.0]. Skillstore. https://skillstore.io/skills/glenskii-human-writer/audits/3@techreport{glenskii-glenskii-human-writer-2026,
author = {glenskii},
title = {human-writer security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/glenskii-human-writer/audits/3},
note = {Author version 1.2.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "human-writer security audit report (audit version 3)"
version: "1.2.0"
type: report
authors:
- name: "glenskii"
date-released: "2026-08-09"
url: "https://skillstore.io/skills/glenskii-human-writer/audits/3"
identifiers:
- type: other
value: "skillstore:glenskii-human-writer:audit:3"
description: "Skillstore immutable audit report identifier"
Remove robotic phrasing and formatting artifacts while keeping the sender's directness, facts, and requested action unchanged.
Apply the full checklist while protecting precise claims, terminology, headings, and the document's established register.
Identify visible writing patterns without rewriting the post or making unsupported claims about authorship.
Edit this draft with the lightest possible touch. Remove clear machine-written patterns, preserve my meaning and formatting, and return only the corrected text.
Audit this draft without rewriting it. Quote each detected pattern, name the checklist category, and suggest a brief fix without scoring authorship.
Edit this draft using the supplied voice profile. Preserve its tone, rhythm, terminology, facts, and deliberate rough edges. Flag any uncertain change.
Apply the full documentation and public-copy checks to this file. Preserve technical meaning, run the bundled editorial checker, and summarize substantial change categories.
作者
glenskii授權
MIT
作者版本
v1.2.0
Skillstore 修訂
r2
引用
f4838806900353c20a6899b1cbb5f5bc3a23357a
維護新鮮度
2026/8/9
使用量
11 次下載 · 1 次瀏覽
Audit Software Releases with Evidence
Release decisions often rely on incomplete evidence and inconsistent standards. This skill applies structured controls, deterministic scoring, and mandatory gates to assess readiness.
Track Long Tasks With a Portable State Ledger
Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.
Audit Python Web Apps Before Release
Python teams need repeatable checks for common application security controls. This skill provides configurable pytest coverage with clear evidence, boundaries, and release decisions.
Audit and Quarantine Gmail Spam Safely
Spam review can expose private mail or remove legitimate messages. This skill audits Gmail headers locally and applies only owner-confirmed quarantine or Trash actions.
Humaniser les brouillons IA avec une édition naturelle
由 softaworks
Les brouillons générés par l'IA paraissent souvent soignés, mais génériques. Ce skill repère les tournures courantes de l'écriture IA et réécrit le texte avec une formulation plus claire et plus naturelle.
Améliorer l’écriture grâce à une révision claire
由 shubhamsaboo
Une écriture peu claire peut masquer de bonnes idées et ralentir la relecture. Cette skill corrige la grammaire, le ton, la structure et la concision pour produire des brouillons plus propres.
Améliorer la grammaire et le style
由 AbdulSamad94
Les rédacteurs ont souvent besoin de corrections claires sans perdre leur voix. Cette compétence passe en revue la grammaire, la clarté, le style, la cohérence et la lisibilité, puis suggère des améliorations ciblées.
Supprimer les schémas d’écriture IA
由 hardikpandya
La prose assistée par IA peut sembler prévisible et générique. Stop Slop aide Claude, Codex et Claude Code à remplacer les schémas formulaïques par une écriture directe.
Rédiger une prose claire et concise
由 softaworks
Les brouillons assistés par l’IA deviennent souvent vagues, verbeux ou promotionnels. Cette compétence applique des règles inspirées de Strunk et des vérifications de motifs propres à l’IA pour rendre la prose directe.
Améliorer la grammaire et le style rédactionnel
由 Amraha-Anwar
Une grammaire imprécise et un style inégal peuvent affaiblir un texte pourtant utile. Cette skill aide Claude, Codex et Claude Code à améliorer la clarté, le ton, la fluidité et la voix de l’auteur.