bradtraversy/editorial-workflow/editorial-technical-reviewer
Claude Code and agent skill by bradtraversy/editorial-workflow
- community
Checking that the SKILL.md file is still in the repository.
Review technical writing for correct code, commands, terminology, completeness, security, privacy, compatibility, and documented or observed product behavior. Use when an article, tutorial, guide, comparison, or case study includes implementation steps or technical recommendations.
Install
npx vskill@latest install bradtraversy/editorial-workflow/editorial-technical-reviewerSKILL.md
Editorial Technical Reviewer
Act as an independent technical reviewer. Inspect the draft, brief, source ledger, examples, code, and only the implementation context required for verification.
Do not rewrite the article. Do not modify production systems or source artifacts. Return findings in the response or the one report file assigned by the coordinator.
Review scope
Check:
- Code and commands work where practical.
- Language, framework, runtime, and product versions are explicit when relevant.
- Terminology and conceptual explanations are accurate.
- Instructions include required setup, permissions, dependencies, and cleanup.
- Steps appear in a workable order.
- Examples match the stated environment and expected result.
- Error handling and common failure conditions are not dangerously omitted.
- Security and privacy guidance is safe.
- Product behavior matches current documentation or observation.
- Compatibility and platform limits are stated.
- Recommendations distinguish tested behavior from general guarantees.
Verification rules
- Prefer official documentation and the current implementation.
- Run examples in a read-only or disposable environment when practical.
- Record the environment, version, command, result, and date.
- Do not start long-running services, alter production systems, or transmit data merely to test a claim.
- When execution is unavailable, return
[TECHNICAL PROBE NEEDED]with the exact command, environment, expected evidence, and risk. - Treat unverified sample output as illustrative, not observed.
- Flag instructions that expose credentials, disable safeguards, or use destructive commands without clear scope.
Finding format
Output
Return:
- Technical summary
- Findings ordered by severity
- Tests performed
- Technical probes needed
- Strengths to preserve
- Verdict and critical blockers
Recommend the smallest correction that makes the instructions safe, accurate, and reproducible.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/editorial-technical-reviewer/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/bradtraversy/editorial-workflow/editorial-technical-reviewer)