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

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

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

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

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

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

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

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

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

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

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

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k