Devto publish expert
Personal collection of reusable, validated Agent Skills
npx -y skills add paladini/agent-skills --skill devto-publish-expertAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Research, write, optimize, validate, and publish specialist technical articles for DEV Community with exactly four relevant tags and a draft-first safety workflow. Use when creating, rewriting, reviewing, scheduling, or publishing DEV.to tutorials, project launches, engineering explainers, case studies, or opinionated developer posts, including through a DEV/Forem MCP server or API.
SKILL.md
4.7 KB, 822 tokens by cl100k_base, as published. Nobody here has run it
DEV.to Publish Expert
Create technically credible articles that earn attention through usefulness, specificity, and a strong reader promise. Never fabricate results, popularity, benchmarks, quotes, or personal experience.
Workflow
- Establish the article goal, intended reader, language, source material, and desired action.
- Inspect the author's existing DEV.to posts when account tools are available. Avoid duplicate angles and reuse the author's authentic voice without copying passages.
- Research every unstable or non-obvious technical claim with current primary sources. Preserve source links near the relevant claims.
- Choose the format and outline using references/editorial-playbook.md.
- Draft the article in Markdown. Lead with the reader's problem and concrete outcome; reveal the implementation progressively.
- Select exactly four distinct, valid DEV.to tags. Use the tag strategy in the editorial playbook; never add an irrelevant popular tag for reach.
- Perform the editorial and technical review below.
- If a file artifact is useful, add DEV-compatible front matter and run
python scripts/validate_article.py ARTICLE.md. - When DEV tools are available, follow references/devto-publishing.md. Create a draft by default.
- Return the draft ID, its actual status, validation results, and the dashboard location. Never describe a temporary draft slug as a working preview URL.
Required article qualities
- Deliver the promised outcome with runnable or clearly labeled illustrative examples.
- Explain why decisions were made, not only which commands to copy.
- State prerequisites, versions, assumptions, limits, risks, and tradeoffs where relevant.
- Use a concrete title that creates curiosity without hiding the subject.
- Make the first three paragraphs useful without requiring prior project context.
- Prefer short paragraphs, descriptive headings, lists only when they improve scanning, and fenced code with language identifiers.
- Include a reproducible verification step or an honest way to evaluate the result.
- End with a specific takeaway, next action, or focused discussion question.
- Link primary documentation and original projects rather than search results or aggregators.
- Keep promotion subordinate to the tutorial or insight.
Four-tag contract
Require exactly four tags:
- one primary subject tag;
- one technology or ecosystem tag;
- one article-format or audience tag when genuinely applicable;
- one narrower discovery tag tied to the actual content.
Normalize tags to lowercase DEV-compatible slugs. Reject duplicates and irrelevant tags. Confirm current tag availability through DEV search or the connected tool when possible.
Editorial review
Before creating a draft, verify:
- The title and opening accurately match the article.
- Every factual claim is supported by the implementation, supplied evidence, or a cited primary source.
- Commands and code use consistent names and contain no secrets.
- The reader can distinguish tested code from pseudocode.
- The article does not promise virality, rankings, reactions, or outcomes.
- The conclusion adds a decision, lesson, or next step instead of repeating the introduction.
- Exactly four tags are present.
Publication boundary
Treat draft creation as reversible and public publication as an external side effect.
- Default to
published: false. - Create or update a public article only when the user explicitly requests publication in the current conversation.
- Before publishing, show the final title, description, four tags, canonical URL if any, and whether the article was validated.
- Never infer publication approval from approval to write, revise, preview, or save a draft.
- If the available integration cannot retrieve authenticated drafts, direct the user to
https://dev.to/dashboardand report that limitation.
Output contract
Provide:
- final title;
- one-sentence reader promise;
- short description;
- exactly four tags;
- complete Markdown;
- primary sources used;
- validation status;
- DEV.to status and article ID when a tool was called.
Do not claim that quality guarantees virality. Describe the article as optimized for clarity, credibility, discoverability, and discussion potential.
What ships with it: 5 files
10.1 KB alongside SKILL.md, 2 of them executable
agents/
- openai.yaml249 B
references/
- devto-publishing.md1.5 KB
- editorial-playbook.md3.3 KB
scripts/
- test_validate_article.pyruns1.4 KB
- validate_article.pyruns3.7 KB
Gives 0 of the 12 instructions most mcp tooling skills give in 822 tokens
Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07
- Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
- Test servers using MCP Inspectorin 61 of 638, across 19 files
- Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
- Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
- Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
- Define structured output schemas where possiblein 50 of 638, across 8 files
- Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
- Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
- Load framework documentation using WebFetchin 45 of 638, across 3 files
- Verify each evaluation answer independentlyin 45 of 638, across 3 files
- Implement API client with authentication and paginationin 45 of 638, across 3 files
- Define input schemas with validationin 27 of 638, across 9 files
Said here and by no other author read
- establish article goal and intended reader
- research non-obvious technical claims using current sources
- draft article in Markdown
- select exactly four valid DEV.to tags
- perform editorial and technical review
- add DEV-compatible front matter
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.