CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

analyze-performance-diagnose

Step of the analyze-performance playbook: flags tracking breaks with fixes and explains each big metric move with evidence, confidence and ruled-out causes. Run analyze-performance instead; not for direct use.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary lean atom: dense inputs, three clearly ordered diagnostic steps with explicit evidence requirements, and clean delegation of detail to a single loaded reference. The only soft spot is that key thresholds and the cause checklist live entirely in the external reference (not verifiable in this bundle), leaving terms like "materially" and "equal maturity" undefined in-body.

DimensionReasoningScore

Conciseness

The 12-line body is lean and telegraphic ("test each break signature (ratio jump/collapse, zero-conversion days with spend, ROAS spike with flat orders, LPV/click drop, UTM traffic missing)"), explains nothing Claude already knows, and every token earns its place, matching anchor 5.

5 / 5

Actionability

Guidance is concrete for an instruction-only skill: enumerated break signatures, a per-break output schema (symptom, likely location, what to check, fix, what it blocks), and a page-match dimension list. It falls short of anchor 5 because "materially moved", "equal maturity", and the cause checklist itself are delegated to the loaded reference rather than specified in-body.

4 / 5

Workflow Clarity

The three steps (plumbing → metric-move explanation → page/message match) are clearly sequenced with explicit quality checkpoints ("One piece of evidence per named cause; confidence", "Mark affected numbers suspect"), matching anchor 4; it lacks the feedback/re-validation loops of anchor 5, and as read-only diagnosis it is not subject to the destructive-operation cap.

4 / 5

Progressive Disclosure

Under 50 lines with well-organized labeled sections (Load, Inputs, Do, Output) and a single, clearly signaled one-level-deep reference (`../analyze-performance/references/diagnosis.md`) that appropriately holds the detailed checklists, matching the simple-skill ideal in anchor 5.

5 / 5

Total

18

/

20

Passed

Description

71%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 specific and honest about its role as an internal playbook atom, with a clear "what" and explicit routing guidance that virtually eliminates trigger conflicts. Its main weakness is trigger-term coverage: it lacks the natural user phrasings and domain keywords (campaigns, ads, ROAS, "why did X change") that would make the underlying capabilities discoverable.

Suggestions

Add natural trigger phrases a user or orchestrator would say, e.g. "why did ROAS/orders drop", "tracking broke", "explain metric changes", to broaden keyword coverage.

Name the domain (paid campaigns / ad performance reporting) in the description — currently the marketing context is only implicit in the parent skill name.

Complement the negative redirect with a positive "when" clause, e.g. "Used when analyze-performance produces a performance report and needs its Plumbing and Why-it-moved sections."

DimensionReasoningScore

Specificity

"flags tracking breaks with fixes" and "explains each big metric move with evidence, confidence and ruled-out causes" list several concrete, well-specified actions, but coverage has minor gaps (e.g., the page/message-match capability is unmentioned), so it sits between anchor 3 and the comprehensive coverage of anchor 5.

4 / 5

Completeness

The "what" is clear (flag breaks with fixes; explain metric moves with evidence and ruled-out causes) and the "when" is explicitly addressed via "Run analyze-performance instead; not for direct use", which counts as explicit trigger guidance, but it is a negative redirect without concrete positive trigger phrases, so not anchor 5.

4 / 5

Trigger Term Quality

Relevant keywords like "tracking breaks", "metric move", and "analyze-performance" are present, but common natural phrasings users would say ("why did ROAS drop", "diagnose", "ad/campaign performance") are missing, matching anchor 3 rather than the good coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

"Step of the analyze-performance playbook" pins a clear niche and "Run analyze-performance instead; not for direct use" actively deflects wrong-skill triggering, giving minimal conflict risk as in anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

gooseworks-ai/goose-skills

Path

skills/marketing/analyze-performance-diagnose/SKILL.md

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.