skillfulagents/public-skillset/seo-daily-content

Claude Code and agent skill by skillfulagents/public-skillset

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Daily content unit — pick the top item from the content backlog and ship it end-to-end (article via blog-pipeline + publish, or a surface/cleanup unit via CMS edit or site PR). Invoked by the daily scheduled task; can also be run manually to burn down the backlog.

Install

npx vskill@latest install skillfulagents/public-skillset/seo-daily-content

SKILL.md

SEO Daily Content

Ships exactly one content unit per run from /workspace/seo/content-backlog.md.

Procedure

  1. Read context: /workspace/seo/STATE.md, /workspace/seo/content-backlog.md, and the

last ~3 entries of /workspace/seo/log.md (avoid duplicating an already-shipped unit — the backlog status is the source of truth).

  1. Pick unit type by day (UTC): Mon–Thu → [article]; Fri–Sun → [surface].

(Target mix: 4 articles + 3 surface units/week — adjust if STATE.md says the agreed cadence differs.) If no todo item of today's type exists, take the other type. Take the topmost todo item of that type (backlog is priority-ordered).

  1. Mark the item — set its status to [in-progress] in the backlog before starting.
Article path
  1. Refine keywords if needed with ahrefs-keywords (cheap overview call; the backlog

entry usually already has vol/KD).

  1. Run the `blog-pipeline` skill end-to-end for the item's primary/secondary keywords

(research → draft → fact-check → humanize → AI-detector QC → media → publish via the configured CMS path).

  1. Internal links: at least 3 internal links to relevant existing pages, and edit 1–2

older relevant posts to link TO the new article.

  1. Publish only if the auto-publish grant in CLAUDE.md is active; otherwise stop at

a ready-to-publish draft and flag it for human review. Verify the page renders live (curl the URL, check title/meta/JSON-LD) and record it in seo/content-inventory.json (blog-pipeline step 7).

  1. For alternatives/comparison posts naming competitors: factual, sourced claims only —

no disparagement; verify every competitor feature/pricing claim against their site.

Surface path

Execute the unit as described in the backlog entry — typical surface units:

  • CMS content changes (titles, metas, body patches, freshness dates) via the configured

CMS path.

  • Site code changes (llms.txt, robots.txt, sitemap fixes, structured data, components) →

repo PR if the site is in git and the CLAUDE.md autonomy rules allow merging; otherwise prepare the change and hand off.

  • Set/update a "last updated" date on any meaningfully edited page (freshness signal).

Wrap up (always)

  • Update the backlog item: [done] + date + live URL(s).
  • Append a dated entry to /workspace/seo/log.md: unit shipped, URL, primary kw, notes.
  • If the backlog has <5 todo articles or <3 todo surface units, note "backlog low" in

the log (weekly strategy replenishes; don't replenish here).

  • If the run fails partway (pipeline error, CI red): revert item to [todo], log the

failure + cause. Do NOT publish anything that failed QC.

Rules

  • One unit per run — never more.
  • Meta description ≤160 chars, unique; valid Article JSON-LD where the site supports it;

image alts set.

  • 1500–2500 words for articles — when your domain authority is below the incumbents',

depth is the edge; thin posts don't rank without DR behind them.

  • Never fabricate stats/quotes; fact-check pass is mandatory (part of blog-pipeline).

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/skillfulagents/public-skillset/seo-daily-content/badge)](https://verified-skill.com/skills/skillfulagents/public-skillset/seo-daily-content)

Something wrong with this skill or its page? Tell us.