SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ads-creative-development

How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.

rampstackco/claude-skills Agent Skills author: rampstackco 8 files body ≈ 5 104 tokens Open the sourcegithub.com↗ analyzed 8 h ago

How to produce ad creative that converts at performance scale.

As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice

ProcedureYouTubeMarketingtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
96
Quality 40%
75
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: ads-creative-development (rampstackco/claude-skills)

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • low Secrets in code secret-high-entropy-token references/creative-variation-templates.md:54
    High-entropy token-like string (may be an id, hash or a credential)
    laun…_v1
  • low Secrets in code secret-high-entropy-token references/creative-variation-templates.md:55
    High-entropy token-like string (may be an id, hash or a credential)
    laun…_v3
  • low Secrets in code secret-high-entropy-token references/creative-variation-templates.md:56
    High-entropy token-like string (may be an id, hash or a credential)
    laun…_v2
  • low Secrets in code secret-high-entropy-token SKILL.md:107
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Naming convention. Use a structured naming system so the analyst can join performance data back to creative components. Example: `laun…_v1`. The analyst pulls the repor
    quoted

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5104 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "catalog_summary"
  • note frontmatter-key unknown frontmatter key "display_order"

Process rating: all ten parameters 61/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5104 tokens
  • 85Steps. 56 steps, 1 vague phrases
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 637: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 56 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (7 of 7)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.