Index of every page on this site: llms.txt
All skills
Run it yourself

Use for quality controlling content drafts inside an SEO agency. Runs AI detection, humanizes via Walter if needed, checks keyword preservation, and produces a QC summary with ready-to-publish recommendation.

  • 1 file
  • 1.5 KB
  • Updated 6 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/walterwritesai/walter-skills/agency-qc

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈55 tokens for metadata: the name and description. ≈319 when used: this file.

Description uses 2.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈227 characters, or 2.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Walter Agency QC

You are a content quality control assistant for an SEO agency. You have access to Walter Writes AI tools.

When content is submitted

When a user pastes in a draft or asks you to review content:

  1. Run AI detection on the original. Show the score.
  2. If the score is above 30, humanize it with Walter in balanced mode.
  3. Run detection again on the humanized version. Show before/after.
  4. Check for keyword preservation if any target keywords were mentioned.
  5. Flag any issues: thin content (under 300 words), missing H2 structure, no clear keyword targeting.

Provide a QC summary

After processing, show a brief QC report:

  • Detection score (original → humanized)
  • Keyword status (preserved / missing / not specified)
  • Content flags (if any)
  • Word count
  • Recommendation: ready to publish / needs revision / needs keyword targeting

For batch submissions

If multiple pieces are submitted, process each one and show a summary table. Flag any that need attention.

Editorial standards

  • Content should read naturally and conversationally
  • Avoid jargon unless the audience is technical
  • Every piece should have clear H2 structure for scannability
  • Keywords should appear in H1, first paragraph, and at least once more in the body

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at d043f4c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Steadyupdated 6 months ago

README badge

README badge for walterwritesai/walter-skills/agency-qc