SKILLEMALL.ai
GitHub ↗ RU Sign in

BF meta-ads-subagent

Subagente autônomo especialista em Meta Ads. Cria campanhas completas via MCP (Super Prompt), gera criativos com IA, monitora métricas (CPA/ROAS/CTR), executa otimizações, pausa anúncios ruins e alerta via Papi. Suporta multi-contas de anúncios.

ClawHub Agent Skills author: Rafa Martins v1.0.3 MIT-0 10 files body ≈ 8 241 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Subagente autônomo especialista em Meta Ads.

As a process F 32/100 · Will not run — References files that are not bundled: references/audit_playbook.md, scripts/audit_account.py, references/funnel_and_conversion_troubleshooting.md

IntegrationWhatsAppTelegramAI and agentsSecuritytype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
100
Quality 40%
47
Run on models
none yet
Process rating
F
32/100
Will not run
References files that are not bundled: references/audit_playbook.md, scripts/audit_account.py, references/funnel_and_conversion_troubleshooting.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

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 8241 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/audit_playbook.md
  • warning missing-ref reference to a missing file: scripts/audit_account.py
  • warning missing-ref reference to a missing file: references/funnel_and_conversion_troubleshooting.md
  • warning missing-ref reference to a missing file: references/page_identity_and_branding.md
  • warning missing-ref reference to a missing file: references/funnel_checkout_optimization.md
  • warning missing-ref reference to a missing file: references/funnel_audit_and_billing_troubleshooting.md
  • warning missing-ref reference to a missing file: references/meta_api_compliance_and_billing.md
  • warning missing-ref reference to a missing file: references/auth_and_api_troubleshooting.md
  • warning missing-ref reference to a missing file: references/asset_provenance_audit.md
  • warning missing-ref reference to a missing file: scripts/meta_asset_provenance_sweep.py
  • warning missing-ref reference to a missing file: references/meta_ads_audit_and_lp_monitoring.md
  • warning missing-ref reference to a missing file: references/unanswered_leads_triaging_patterns.md
  • warning missing-ref reference to a missing file: references/creative_url_swapping_and_pricing_strategy.md
  • warning missing-ref reference to a missing file: references/landing_page_traffic_readiness.md
  • warning missing-ref reference to a missing file: references/landing_page_conversion_protocol.md
  • warning missing-ref reference to a missing file: references/meta_pixel_and_billing_management.md
  • warning missing-ref reference to a missing file: references/landing_page_audit.md
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 32/100

Will not run. References files that are not bundled: references/audit_playbook.md, scripts/audit_account.py, references/funnel_and_conversion_troubleshooting.md
  • 0Tools and files. 17 referenced file(s) missing: references/audit_playbook.md, scripts/audit_account.py, references/funnel_and_conversion_troubleshooting.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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 40Execution cost. Instruction body is 8241 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 156 steps, 2 vague phrases
  • 100Consistency. Name and required fields are in place
  • 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -227 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 245: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 156 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (3 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.

External checks

ClawHub: suspicious
This skill has a clear Meta Ads automation purpose, but it handles powerful ad-account credentials and live campaign changes with unsafe scoping and approval gaps.
LLM: suspicious (high) · 10 Sept 2026