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

Run a fail-closed quality gate on AI-written social posts before they ship: score nine gates out of 100, catch eight automatic critical failures, and check rights, safety, disclosure, and platform-native structure with a printable checklist. Use when doing the final check on any AI-assisted post, or whenever a claim, link, price, prompt, or visual changes after the first draft.

  • 4 files
  • 20.4 KB
  • Updated 5 days ago
  • GitHub
Use this Skill: https://skilld.dev/gh/jokerhtml/needcraft-skills/ai-content-qa

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

examplesquality-gate-checklist.md

≈880 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Quality Gate Checklist — 92/100

Copy this file into your plan for every scored post. Tick each box in order. A post with no recorded score has not passed.

Post: (title / topic) Platform(s): (list each version separately — one checklist per platform version) Date checked: (date) Checker: (name — the checker re-opens sources and links itself)

The bar

  • Score is 92/100 or higher AND every critical gate passed
  • Score recorded below with per-gate points

Scored gates (100 points)

Gate Points (max) Scored
Accuracy / evidence 20 /20
Practical usefulness 15 /15
Prompt / workflow completeness 15 /15
Tool research / links 10 /10
Hook / storytelling 10 /10
Originality 10 /10
Visual / audio 10 /10
Platform-native structure 5 /5
SEO / accessibility 5 /5
Total 100 /100

Note: 92/100 is a house threshold chosen by the author as a deliberately strict bar. It is not a proven predictor of reach, engagement, or sales.

Critical failures (any one = REVISE or REJECT, regardless of score)

  • No unverified factual claim, fabricated tool feature, fake ranking, fake test, or misleading "best" claim
  • No broken, unsafe, unofficial, or wrong-destination tool link; no unverified price or free-tier promise
  • Exact prompt/steps present wherever a workflow is taught
  • No copied creator work, reused clips without meaningful original contribution, or unclear rights
  • No misleading income/viral/monetisation guarantee; no inaccurate platform-policy claim
  • Required AI disclosure (or other platform disclosure) present where applicable
  • No unreadable mobile text, deceptive thumbnail, fake product UI, or major production defect
  • No identical mass-produced copy across platforms without native adaptation

Pre-delivery checklist

  • Claim ledger present; every claim has source URL + date + confidence; no UNVERIFIED figure stated as fact
  • Every tool link opened (or re-checked) and lands on the official destination
  • Prompt block complete (8 parts) wherever a workflow is taught
  • Hands-on vs desk-researched label present and true
  • "Last checked" date present
  • Hook passes the 4 S's — Subject / Stakes / Speed / Clarity — and sits in the first line
  • One CTA per platform version; no triple-ask closer
  • Specificity floor: ≥1 number + ≥1 named entity + ≥1 concrete detail per 100 words
  • No AI-tell phrases; em-dash ≤1 per 100 words; no emoji walls
  • Character limits respected: X ≤280 weighted per post (Premium ≤25,000) · Threads ≤500 · IG caption ≤2,200 · Pinterest title ≤100, description ≤800 · LinkedIn ≤3,000 · Facebook: no published limit, check the composer
  • X native thread (first post no link, ends with a thread marker; link in the reply). Threads link in first reply only + native topic tag
  • Hashtags: IG ≤5, LinkedIn 0–1, others 1–3 where they help
  • Visual checklist passed: full text scan done, mobile-readable, no fake UI, card and image agree, alt text / captions present
  • AI disclosure checked; no income/viral guarantee; no fake ranking or "best" claim

Verdict

  • PASS — score ≥92 and zero critical failures
  • REVISE — reason: (what must change, which gate)
  • REJECT — reason: (why it cannot be fixed as written)

Signature / date: _______________

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 90f40b1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 5 days ago
Other metadata
metadata
{
  "version": "1.0.0",
  "date": "2026-11-16",
  "author": "Muhammad Saad Ranjha / NeedCraft"
}

README badge

README badge for jokerhtml/needcraft-skills/ai-content-qa