attribution

When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "whic...

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/attribution/SKILL.md

Quality

Content

75%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.

The body is a strong, expert overview: domain-specific guidance, concrete code patterns, clear sequenced workflows with guardrails, and well-signaled one-level references. The two weaknesses are that the referenced `references/*.md` files are not present in the bundle, and the overview is on the long side with some content that could move into those references.

Suggestions

Ship the referenced files (`references/attribution-models.md`, `measurement-paradigms.md`, `by-business-type.md`, `first-party-tracking.md`, `conversion-tracking.md`) — they are cited but missing from the bundle.

Move the full model and paradigm tables fully into their references and keep only a one-line pointer plus the decision rule inline, to tighten the overview.

Fold the "fail closed / audit first / verify in prod" checkpoints directly into the third-party stitch steps so the validation loop is part of the sequence.

Dimension	Reasoning	Score
Conciseness	The 222-line body is dense, expert, and assumes Claude's competence — it does not pad with basics Claude already knows, and pushes deep detail (worked examples, full playbooks, Shapley math) into references. It is not 5 because at this length some explanatory prose and several full tables could still be trimmed or moved entirely into the referenced files.	4 / 5
Actionability	Provides concrete, executable guidance: specific decision rules ("small budget → good UTM + last-non-direct + self-reported survey"), exact code-level patterns (`identify()`, `$initial_referrer`, `?metadata[ph_distinct_id]=<id>`, `$identify` with `$anon_distinct_id`), and a copy-ready output template. It is not 5 because much of the full executable code is deferred to references rather than shown inline.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced — the 5-step reconciliation framework and the 3-step third-party-domain stitch — with checkpoint-style guardrails ("fail closed," "Audit first," "verify the stitch in prod"). It is not 5 because the validation checkpoints live in a separate Guardrails section rather than inline in the stitch sequence, leaving minor gaps.	4 / 5
Progressive Disclosure	Good structure: an overview body with one-level-deep references signaled at natural points (e.g., "see `references/attribution-models.md`"). It is not 5 because the body itself is long and carries several full tables that could be split out, and the referenced files do not actually exist in the bundle (the `references/` directory is absent), so the navigation is signaled but not backed by real files.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

The description is well-structured: third-person voice, explicit what + when with concrete trigger phrases, and domain-specific keywords. Its main defect is that the field is literally truncated mid-word ("whic..."), which cuts off the remaining trigger terms and should be repaired even though what/when are already conveyed.

Suggestions

Restore the truncated description so the full trigger-term list (cut off at "whic...") is present.

Consider adding a short disambiguating phrase (e.g., "not general event tracking or pixel setup") to further reduce overlap with analytics/ads skills.

Dimension	Reasoning	Score
Specificity	Names the attribution domain and several concrete actions — "choose or interpret an attribution model" and "reconcile conflicting numbers across tools" — alongside the goal of figuring out which marketing drives conversions. It is not the 5 anchor because coverage is a handful of actions rather than comprehensive, and it clears the 3 anchor which expects only 1–2 actions.	4 / 5
Completeness	It explicitly answers both "what" (choose/interpret an attribution model, reconcile conflicting numbers) and "when" with concrete trigger phrases ("When the user wants to figure out...", "Also use when the user mentions..."). This matches the score-5 example structure; the truncation cuts off extra trigger terms but does not remove the explicit what/when guidance.	5 / 5
Trigger Term Quality	Lists natural phrases a marketer would actually say — "attribution," "attribution model," "first-touch vs last-touch," "multi-touch" — giving good keyword coverage. It is not 5 because the description is truncated mid-word at "whic...", cutting off the remaining trigger terms, so the coverage is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	Highly specific triggers like "first-touch vs last-touch" and "multi-touch" carve a clear attribution niche unlikely to fire for unrelated skills. It is not 5 because broader terms ("conversions," "marketing") leave minor overlap risk with closely related skills such as analytics and ads.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/attribution/SKILL.md
Commit: 6c06908

Reviewed: ~9 hours ago

Table of Contents

Discovery Implementation Validation

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.