SKILLEMALL.ai
GitHub ↗ RU Sign in

CD fb-creatives

How to make an N-creative FB / Meta / IG static ad pack for a real brand — generalized niche know-how, not one specific ad. A domain overlay on the standard pipeline: supplies the 5-set creative matrix (A real-people · B graphic / typography · C proof / data-viz · D meme · E niche-audience), the site-grounding pre-flight (curl CSS hex + Playwright hero screenshot used as `--ref` on every gen), the true-parallel batch shape on `openai/gpt-5.4-image-2`, the per-set prompt cookbook (testimonial portrait, code-card poster, strikethrough price stack, horizontal bar chart, meme header), and the deliverable folder layout (numbered PNGs + `ads-copy.md` + `README.md`). Works for ANY brand the user names — a SaaS dev tool, a DTC product, a B2B service — the skill supplies the matrix know-how, the user supplies the brand + URL. USE WHEN the user asks for an "ad pack", "32 creatives", "FB / Meta / IG ads", "creative matrix", "set of static ads", "performance creatives for <brand>", with N ≥ 4 stills and a single concrete brand / site. This is a niche SKILL (generalized), not a remix TEMPLATE. For "remix this exact ad but swap X", that is the remix path in docs/skills-vs-templates.md. For a single poster, use /poster.

alecs5am/ralphy Agent Skills author: alecs5am 1 file body ≈ 3 854 tokens Open the sourcegithub.com↗ analyzed 11 h ago

How to make an N-creative FB / Meta / IG static ad pack for a real brand — generalized niche know-how, not one specific ad.

As a process D 49/100 · Unfinished process — References files that are not bundled: ../poster/SKILL.md, ../../../docs/skills-vs-templates.md, ../../../.agents/skills/researcher/references/site-grounding.md

ProcedurePlaywrightAI and agentsMarketingtype 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
79/100
safety, quality, tests
Safety 60%
100
Quality 40%
48
Run on models
none yet
Process rating
D
49/100
Unfinished process
References files that are not bundled: ../poster/SKILL.md, ../../../docs/skills-vs-templates.md, ../../../.agents/skills/researcher/references/site-grounding.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ralphy

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1224 chars, limit 1024
  • warning missing-ref reference to a missing file: ../poster/SKILL.md
  • warning missing-ref reference to a missing file: ../../../docs/skills-vs-templates.md
  • warning missing-ref reference to a missing file: ../../../.agents/skills/researcher/references/site-grounding.md
  • warning missing-ref reference to a missing file: ../../../.agents/skills/intake/SKILL.md
  • warning missing-ref reference to a missing file: ../../../.agents/skills/art-director/SKILL.md
  • note frontmatter-key unknown frontmatter key "namespace"

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: ../poster/SKILL.md, ../../../docs/skills-vs-templates.md, ../../../.agents/skills/researcher/references/site-grounding.md
  • 0Tools and files. 5 referenced file(s) missing: ../poster/SKILL.md, ../../../docs/skills-vs-templates.md, ../../../.agents/skills/researcher/references/site-grounding.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 42 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3854 tokens
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1224: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 42 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.