CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

analyze-performance

Weekly performance read across every channel we run: what worked, why, and what to make next, judged on the business's real number (store revenue, qualified pipeline, retained users), not platform claims. Use when: write my Monday report; how are my ads doing — which ad won?; are my ads actually making money (Meta says 4x ROAS but revenue is flat); why did sales drop this week; did the test win; is my tracking working; monthly numbers for the replan; anything on fire today. Not for acting on the recommendations (pausing, scaling, launching) — use run-paid-campaigns; not for replanning the budget — use plan-campaign.

Quality

95%

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

96%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.

An exceptionally dense, highly actionable playbook: exact tools, paths, and decision rules throughout, with a well-sequenced workflow, explicit validation checks, and a genuine one-level reference bundle. The only notable gap is progressive disclosure — some content is inlined that could live in references, and the reference files cross-reference each other.

DimensionReasoningScore

Conciseness

The 75-line body is maximally token-efficient: no concept explanations, no padding, every sentence carries tool names, paths, frontmatter fields, or criteria. It fully assumes competence and matches the "every token earns its place" anchor; there is no over-explanation to trim, so it is not the 4 anchor.

5 / 5

Actionability

Instruction-only guidance at copy-paste specificity: exact workspace paths (reports/performance/<YYYY-MM-DD>.md, ads/campaigns/<slug>/state.md), exact tool calls (gooseworks:campaign_read, brand_read sections, knowledge_search ["learning"]), exact tags, titles, and decision criteria ("capped at likely unless store new-customer orders moved with it"). No key details are missing for the common cases.

5 / 5

Workflow Clarity

Clear routing ("Route first"), five sequenced setup gates, nine numbered steps, explicit inline checks ("labels per section (truth / claimed / derived); no platform revenue as truth; every rostered channel present"), a "Done when" completion checklist, and a reply-driven feedback loop (step 7 re-saves the report and records decisions). The skill is read-only with money moves gated elsewhere, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

A clear overview with well-signaled one-level references — all nine referenced files exist in references/ and each is pointed to with its purpose and section. It falls short of the top anchor because the long inline workspace-file inventory in "Before you start 2" and cross-references between reference files (run-memory.md → measurement-contract.md §4, monthly-and-pulse.md, plus its method-copy path remapping) add navigational friction.

4 / 5

Total

19

/

20

Passed

Description

95%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.

A strong description: concrete outputs, a comprehensive set of natural trigger phrases quoted as users would actually say them, and explicit disambiguation against sibling skills. The only softness is that the central action ("read/judge") is slightly less verb-object concrete than a maximal example.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions and outputs ("Weekly performance read across every channel", "what worked, why, and what to make next", "store revenue, qualified pipeline, retained users", Monday report, monthly replan numbers). The core verb stays slightly more abstract than the 5-anchor's fully concrete verb-object list, so it sits at "several specific actions; minor gaps" rather than comprehensive.

4 / 5

Completeness

Explicitly answers both what ("Weekly performance read across every channel we run ... judged on the business's real number ... not platform claims") and when ("Use when: write my Monday report; ... anything on fire today"), with concrete trigger phrases plus explicit not-for boundaries — an exact match to the top anchor.

5 / 5

Trigger Term Quality

The "Use when" list contains literal natural user utterances with synonyms and variants — "write my Monday report", "how are my ads doing — which ad won?", "did the test win", "is my tracking working", "why did sales drop this week", "anything on fire today" — matching the comprehensive-coverage anchor; no common phrasing is missing.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (performance analysis judged on business numbers, not platform claims) and actively routes neighboring work away ("use run-paid-campaigns", "use plan-campaign"), giving minimal conflict risk.

5 / 5

Total

19

/

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/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.