CtrlK
BlogDocsLog inGet started
Tessl Logo

attribution-setup

When the user wants to set up, debug, or interpret app install attribution — including SKAdNetwork (SKAN), Apple's AdAttributionKit, Google Play Install Referrer, MMPs (AppsFlyer, Adjust, Singular, Branch, Kochava), deep links, deferred deep links, conversion values, postback windows, or privacy thresholds. Use when the user mentions "SKAdNetwork", "SKAN", "SKAN 4", "AdAttributionKit", "AAK", "MMP", "AppsFlyer", "Adjust", "Singular", "Branch", "attribution", "conversion value", "postback", "Install Referrer", "deferred deep link", "iOS 14.5", "ATT", "App Tracking Transparency", "IDFA", or "I can't measure my ad campaigns". For paid campaign strategy, see ua-campaign and apple-search-ads. For analytics events, see app-analytics.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, table-driven, highly actionable skill body that respects token budget and gives real SDK calls and concrete schemas. The main gap is enforcement: validation checkpoints exist only as template placeholders rather than explicit feedback loops.

Suggestions

Replace the TESTING PLAN placeholders in the Output Template with an explicit validate→fix→retry loop (e.g., 'Verify postback in MMP within X hours; if missing, check privacy threshold and ATT prompt ordering, then re-test').

Add a brief verification step to each MMP setup checklist (e.g., 'Confirm SKAN postback received in dashboard before enabling network integrations') so the workflow has concrete checkpoints rather than only install steps.

Consider extracting the per-MMP setup checklists into reference files (e.g., references/appsflyer.md) to keep SKILL.md as a lean overview, which would also strengthen progressive disclosure.

DimensionReasoningScore

Conciseness

Lean table-driven content that assumes Claude's competence — no padded explanations of what an MMP or a postback is; every section earns its tokens.

5 / 5

Actionability

Provides copy-paste-ready specifics: real SDK signatures ('AppsFlyerLib.shared().start()', 'Adjust.appDidLaunch'), a concrete 6-bit CV schema table, per-MMP checklists, and a symptom→cause debug playbook covering the common cases.

5 / 5

Workflow Clarity

Clear sequencing via the Initial Assessment, per-MMP checklists, and an output template with a testing plan, but validation checkpoints are template-ized placeholders rather than explicit validate→fix→retry loops for the fragile SDK/CV setup.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md with clear section headers and no nested references; no bundle files are present to split out. Could push to 5 by moving per-MMP checklists into reference files, but the inline structure is appropriate.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplar description: concrete actions, comprehensive natural trigger terms, explicit what-and-when guidance, and clear boundary handoffs to sibling skills. No padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('set up, debug, or interpret') alongside a comprehensive enumeration of attribution mechanisms (SKAdNetwork, AdAttributionKit, Install Referrer, MMPs, deep links, conversion values, postback windows, privacy thresholds).

5 / 5

Completeness

Explicitly answers both 'what' (set up/debug/interpret install attribution and named mechanisms) and 'when' via a concrete 'Use when...' clause listing trigger terms.

5 / 5

Trigger Term Quality

Covers comprehensive natural terms and synonyms users would say — 'SKAdNetwork', 'SKAN', 'MMP', 'AppsFlyer', 'Adjust', 'attribution', 'conversion value', 'postback', 'deferred deep link', 'ATT', 'IDFA', plus the colloquial 'I can't measure my ad campaigns'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (app install attribution) and explicitly hands off adjacent territory to ua-campaign, apple-search-ads, and app-analytics, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Eronred/aso-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.