SKILLEMALL.ai
GitHub ↗ RU Sign in

CB schedule-ads

Manage paid ads on AdManage.ai from declarative config - default schedules launches across Meta/TikTok/Snapchat/Pinterest/LinkedIn (always PAUSED); create provisions Meta campaigns and ad sets.

aeonfun/aeon Agent Skills author: aeonfun 3 files body ≈ 6 196 tokens Open the sourcegithub.com↗ analyzed 27 h ago

Manage paid ads on AdManage.ai from declarative config - default schedules launches across Meta/TikTok/Snapchat/Pinterest/LinkedIn (always PAUSED); create…

As a process B 66/100 · Nearly there — weak spots: when it triggers, inputs and preconditions

GeneratorMarketingtype 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
84/100
safety, quality, tests
Safety 60%
97
Quality 40%
65
Run on models
none yet
Process rating
B
66/100
Nearly there
When it triggers w 12
20
Inputs and preconditions w 11
30
Tools and files w 18
60
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.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Exfiltration net-credential-use SKILL.md:60
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    - Auth'd calls go through `./secretcurl` with the `{ADMANAGE_API_KEY}` placeholder — never a bare `$ADMANAGE_API_KEY` (the Bash permission layer refuses that). `ADMANAGE_API_KEY` is injected in-run vi
    quoted
  • low Exfiltration net-credential-use SKILL.md:243
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    - Auth'd calls go through `./secretcurl` with the `{ADMANAGE_API_KEY}` placeholder — never a bare `$ADMANAGE_API_KEY`. The key is injected in-run via `requires:`.
    quoted
  • low Exfiltration net-credential-use SKILL.md:451
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    - `ADMANAGE_API_KEY` — the AdManage.ai API key, injected in-run via this skill's `requires:` and used by both branches for the `/v1/*` calls. Always pass it as the `{ADMANAGE_API_KEY}` placeholder to
    quoted

Files scanned: 3. 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 ≈ 6196 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 66/100

  • 20When it triggers. No condition that starts the skill
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6196 tokens
  • 85Steps. 84 steps, 1 vague phrases
  • 100Failures and branches. 6 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 193: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 84 items
  • +3Output format is stated explicitly
  • +4Has examples (15 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.