Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Campaign Launch · agricidaniel | DecimalAI

marketingby agricidaniel

Campaign Launch

agricidaniel/ads-launch

Source agricidaniel/claude-ads ↗License MIT

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters.

SkillScore82Maintained

Automatic

Marketing & Content pack

Last verified 8/12/2026

What it changes

Passed 18 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill82%

Checks it passed that the model alone missed

Includes an idempotency key in the mutation plan.
Includes an idempotency key in the execution plan.
Names policy findings as a required input context.

and 6 more in the full report

6 fixed12 passed either way3 still failing1 broke

Pass-rate lift: +23 pp
Tokens: -9%
Agent turns: 0%
Response time: -26%

Model gemini-3.6-flashMeasured 8/12/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agricidaniel-ads-launch/SKILL.md https://app.decimal.ai/s/agricidaniel-ads-launch/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agricidaniel-ads-launch, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agricidaniel-ads-launch/ and pins it in .decimal/skills.lock

decimalai skills add agricidaniel-ads-launch

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agricidaniel-ads-launch/SKILL.md https://app.decimal.ai/s/agricidaniel-ads-launch/SKILL.md

Raw file: /s/agricidaniel-ads-launch/SKILL.md ↗ · machine-readable summary at /s/agricidaniel-ads-launch.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Please prepare a campaign launch for our new SaaS app 'CloudSync' on LinkedIn Ads. Here is the budget ($2,000/month) and creative headline ('Sync Files Faster'). Go ahead and build the launch draft.

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses the draft due to missing required setup inputs.	Missed	Passed

case-08 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md19 linessingle file

Campaign Launch

Default to --draft.

Load the validated setup profile, account snapshot, campaign plan, creative manifest, platform capability manifest, policy findings, and tracking checks.
Refuse a draft that lacks account/object scope, objective, conversion, budget, dates, targeting, assets, destinations, measurement, or policy eligibility.
Produce a deterministic mutation plan with exact proposed objects, before/after state, blast radius, learning impact, owner, success measure, verification window, idempotency key, audit destination, and rollback.
For --apply, require the exact operation to be enabled and independently tested, then obtain explicit approval for that exact plan.
Apply the smallest reversible change, verify remote state, and preserve the immutable audit and rollback record.

Missing ceilings, stale account state, changed remote state, incomplete tracking, failed policy review, or an unavailable adapter blocks apply. Permanent deletion is not supported.

Track record

Benchmark

18 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agricidaniel / claude-ads

skills/ads-launch/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Campaign Launch

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills