Analyze Campaign Performance

Analyze campaign performance — skill template

Turn this template into a working skill by resolving every TODO. The seed prompt below is the published Anthropic example this template was derived from; your skill should generalize it for repeated, hands-off use.

Outcome

Analyze campaign performance data to identify your best and worst performing channels, then get specific budget reallocation recommendations for next quarter.

TODO: Restate the outcome for YOUR context in one sentence: who runs this, on what input, producing what artifact, how often.

Seed prompt (verbatim from source, © Anthropic PBC)

I'm running three campaigns targeting different customer segments. I have Q3 data showing impressions, clicks, conversions, and spend across social, search, and email.

Analyze performance and tell me:

- Which campaigns and channels are working
- Where to reallocate budget for Q4
- What patterns I'm missing across segments

Create a dashboard and analysis report. I need to know what to do differently next quarter.

Context: Our target ROI is 300%+. Enterprise customers have 3x higher LTV than SMB. Industry benchmark is 200-250% ROI. I can shift up to 30% of budget based on performance.

Required context and inputs

• Campaign performance data (XLSX files mentioned as example)
• Optional: Extended Thinking (for better results)
• TODO: exact file paths / folders / message formats this skill should expect
• TODO: domain context the model cannot infer (naming conventions, thresholds, house style)

Tools, connectors, APIs, and authentication

• No connectors detected on the source page; base Claude capabilities only
• TODO: confirm which connectors are enabled in the runtime that will execute this skill
• Authentication: connectors authenticate via their own OAuth flows — this skill must

NEVER ask for, store, or echo credentials, tokens, or API keys. If auth is missing, stop and tell the user which connector to enable.

Permissions and sensitive actions

• Reads: TODO (folders, channels, records this skill may read)
• Writes: TODO (what it may create/modify, and where)
• Held back for the primary agent / human: sending external communications, financial

transactions, deleting or overwriting originals, submitting web forms

Workflow

1. Describe the task
2. Give Claude context
3. What Claude creates
4. Follow up prompts

TODO: adapt the steps above (from the source page) into imperative instructions for the executing agent, including what to do between steps.

Decision points

• TODO: list each point where the skill must choose between paths, with the rule to apply
• Default rule: prefer the reversible option; when two readings of the input are

plausible, surface both rather than picking silently.

Validation criteria

• Output matches the outcome statement above (spot-check against the seed prompt's asks)
• Every factual claim is traceable to a provided input, connector record, or cited source
• TODO: add one domain-specific check a reviewer in your org would apply

Failure modes and fallbacks

• Ambiguous or missing input → ask one targeted question; if unattended, state the assumption inline and proceed
• Any step would take a sensitive/irreversible action → stop and hand back to the user (see Delegation)

Delegation

Apply the repo's delegation policy (docs/delegation-policy.md — bundle or restate it if you install this skill outside the repo). Defaults for this template:

• Run single-agent unless a step fans out over independent items (files, records,

vendors, channels). Only independent work parallelizes.

• Each delegated task must ship with: the minimal context slice it needs, an explicit

output contract, a validation check the primary agent runs on the result, and a fallback if it returns empty or fails.

• Final review, synthesis, and every sensitive action listed above stay with the

primary agent.

• TODO: name the concrete subtasks (if any) that qualify for delegation here.

Attribution

Derived from Analyze campaign performance (retrieved 2026-07-26). Seed prompt and workflow content © Anthropic PBC. Scaffold structure original to this repository.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: iankiku
• Source: iankiku/agent-skill-factory
• License: MIT

Install and usage instructions live in the source repository linked above.