agentleFS
Sign inStart free
LazyIsEfficientLazyIsEfficient/agentic-os/.claude/skills/content-ops/SKILL.md

content-ops

Skill17 starsChanged 22 days agoMITView on GitHub

Auto-assembles a domain-specific expert panel (7–10 experts), scores any content or strategy artifact against a typed rubric, and iterates until the aggregate hits 90+ (max 3 rounds). Use as a quality gate on copy, email sequences, landing-page drafts, strategy docs, charts, titles, or recruiting evaluations — or when another skill needs a final review gate on its output. Triggers on "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "expert score", "evaluate this copy/strategy/page". For variant generation and multi-round conversion optimization see autoresearch; for live-URL CRO auditing see conversion-ops; for the scripted content-production pipeline see content-pipeline.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check references/patterns.md at every round start and dock points for known-bad patterns before expert scoring.

    line 31
  2. Distinctive:

    When scoring another skill's output, generate a Source Improvement Brief (Step 6).

    line 32

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Expert Panel

General-purpose scoring and iterative improvement engine. Auto-assembles the right experts for whatever is being evaluated, scores it, and loops until 90+.

Core rules

  1. Intake: collect content, content type, offer context, variants, and source skill — full procedure in references/procedure-steps.md Step 1.
  2. Auto-assemble 7–10 experts: start from experts/ pre-built panels, add 1–3 domain experts, always include AI Writing Detector (1.5x weight) and Brand Voice Match.
  3. Select scoring rubric from scoring-rubrics/ by content type; read the file for criteria.
  4. Score recursively until 90+ aggregate (max 3 rounds). Humanizer weighted 1.5x. Show all rounds in output — the iteration trail is the value.
  5. Check references/patterns.md at every round start and dock points for known-bad patterns before expert scoring.
  6. When scoring another skill's output, generate a Source Improvement Brief (Step 6).
  7. On user rejection of 90+ content, capture the reason and append to references/patterns.md.

References

  • references/procedure-steps.md — full 7-step procedure: intake, panel assembly, rubric selection, scoring loop, output format, feedback-to-source, pattern learning
  • references/expert-assembly.md — domain-expert examples for auto-assembly of unfamiliar panels
  • references/patterns.md — learned rejection patterns; read every run
  • experts/humanizer.md — AI writing detection rubric (24 patterns); always run
  • experts/ — pre-built panels: humanizer, instagram, linkedin, newsletter, podcast-quotes, recruiting, seo-strategy, x-articles, youtube-shorts
  • scoring-rubrics/ — content-quality, conversion-quality, evaluation-quality, strategic-quality, visual-quality

Related skills

  • autoresearch — pre-launch variant generation + multi-round optimization of conversion copy; run before content-ops's final gate
  • conversion-ops — post-publish conversion layer; run after content-ops quality gate
  • adversarial-claims-reviewer — judges whether formal/technical claims are true; content-ops judges whether the prose is good
  • content-pipeline — script-driven content production (RSS quote mining, video-clip discovery, repurposing, batch draft gating); reuses this skill's experts/ panels in its transform stage

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free