AGENT SKILL

technical-manuscript-verification

Verify technical nonfiction manuscripts for runnable accuracy, including commands, configuration, code snippets, links, version drift, screenshots, prerequisites, security warnings, expected outputs, and reproducibility. Use when auditing self-hosting, DevOps, programming, infrastructure, data, security, or software tutorial drafts before beta reading, publication, or release.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
technical-manuscript-verification
license
MIT
metadata
{ "tags": "writing,books,nonfiction,technical-writing,verification", "version": "0.1.0", "category": "Writing", "displayName": "Technical Manuscript Verification" }
description
Verify technical nonfiction manuscripts for runnable accuracy, including commands, configuration, code snippets, links, version drift, screenshots, prerequisites, security warnings, expected outputs, and reproducibility. Use when auditing self-hosting, DevOps, programming, infrastructure, data, security, or software tutorial drafts before beta reading, publication, or release.
compatibility
Codex, Claude Code, and other Agent Skills-compatible clients.

02 资源文件 6

03 SKILL.md 正文

Technical Manuscript Verification

Core Lens

Technical nonfiction must work in the reader's environment, not just in the author's memory. Verification checks whether commands run, configs are coherent, screenshots match text, links still resolve, safety boundaries are clear, and the reader has enough context to recover from failure.

Use this skill to audit:

  • Technical book chapters and tutorials.
  • Self-hosting and infrastructure guides.
  • Code snippets, shell commands, Docker Compose files, config examples, diagrams, and screenshots.
  • Claims that depend on current platform behavior or version-specific documentation.
  • Pre-beta or pre-publication technical accuracy.

Reference Routing

Need Read
Verification concepts and terminology references/core/knowledge.md
Audit rules and evidence standards references/core/rules.md
Example findings and verification tables references/core/examples.md
Fast verification checklist references/core/checklist.md
Step-by-step verification pass workflows/verify-technical-manuscript.md

Workflow

1. Define The Verification Scope

Identify what needs verification:

  • Commands and code.
  • Config files and environment variables.
  • Installation and setup steps.
  • Screenshots, diagrams, and expected outputs.
  • Links and external references.
  • Safety, security, privacy, data loss, and cost warnings.

Use a narrow pass when the manuscript is large.

2. Build An Evidence Table

For each technical item, track:

Item | Location | Assumption | Verification method | Result | Fix

Do not rely on plausibility when the item can be checked.

3. Verify Against Real Or Simulated Environments

Prefer running commands, linting configs, checking links, rendering examples, or consulting primary documentation. When execution is unsafe or impractical, state the assumption and the evidence still needed.

4. Classify Findings By Reader Risk

Prioritize:

  • Data loss, security exposure, privacy harm, or irreversible changes.
  • Commands that fail or produce different output.
  • Missing prerequisites that block readers.
  • Current-info drift from tool or platform changes.
  • Misleading screenshots or diagrams.

5. Return Fixes The Author Can Apply

Recommend exact changes:

  • Add prerequisite.
  • Change command or config.
  • Add expected output.
  • Add warning, rollback, or troubleshooting note.
  • Move volatile steps to a companion resource.
  • Mark claim for current-doc verification.

Output Format

When verifying a manuscript, return:

  1. Verification scope and assumptions.
  2. Findings ordered by reader risk.
  3. Evidence table with pass/fail/untested status.
  4. Exact manuscript fixes.
  5. Items requiring current primary-source verification.
  6. Suggested beta-reader or expert-review checks.

Quality Bar

Be concrete and evidence-driven. Distinguish "verified," "likely," "untested," and "unsafe to test here." Never imply that a technical instruction works unless it was actually checked or the limitation is clearly stated.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

migrate-to-e2e

Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

e2e

Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

create-verification-skill

Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-search

deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

deja-reflect

End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

revid

Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.

图像与多媒体Skill与智能体开发
★ 1.6k