CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

goose-ads

Edit, resize, animate and study image ads with GooseWorks in this chat. New static or image ads go to the make-static-ads skill when it is installed or catalog_fetch opens it. Read the brand and follow the active playbook, preserving factual prerequisites and approvals.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/entry/goose-ads/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 efficiently written router that maps existing-ad operations to concrete GooseWorks actions with strong spend-approval gates and communication rules. Its main weaknesses are delegation of execution sequencing to external next_step/playbook state without even one worked example, and repetitive make-static-ads routing across three sections.

Suggestions

Add one short worked example that sequences a single operation end-to-end (e.g., quote -> show price -> customer yes -> animate -> poll job_get), so the workflow does not rely entirely on external next_step state.

Consolidate the make-static-ads routing rule, which currently appears in the intro paragraph, the fifth bullet, and the Rules section, into one authoritative statement.

Give the routing bullet list its own section header (e.g., '## Operations') so the dispatch table is signposted as clearly as '## Rules'.

DimensionReasoningScore

Conciseness

The body is telegraphic with no concept explanations or padding, but make-static-ads routing is repeated in the intro paragraph, the fifth bullet, and the Rules section, and a few sentences are contorted enough to need re-reading — minor instances that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Concrete operations are named with conditions (job_get, ads_creative_read, ads_creative_animate priced first via ads_creative_animation_quote, ads_creative_resize only after the customer's yes, ads_template_create, meta_read), but no invocation syntax is shown and key details defer to external state ("the connection's listed knowledge action", "the actual execution next_step"), leaving minor gaps below fully executable guidance.

4 / 5

Workflow Clarity

This is a dispatch table rather than a sequenced workflow: approval checkpoints are explicit for paid operations ("price it first", "wait for their yes", "pass on a yes only once they gave it to that total"), but end-to-end sequences, polling, and validation loops are delegated to an external "next_step" and the fetched playbook, leaving the sequence present yet largely implicit — matching anchor 3 rather than 4 where most checkpoints and the sequence are in the document.

3 / 5

Progressive Disclosure

The single-file bundle (~35-line body) is appropriately compact with an intro routing paragraph, an operation bullet list, and a "## Rules" section, and nothing inlined belongs in a separate file; the unlabeled routing bullet block is a minor organization gap keeping it below a 5.

4 / 5

Total

15

/

20

Passed

Description

58%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 communicates a clear niche (existing image-ad operations within GooseWorks) and wisely disambiguates new-ad creation, but it lacks an explicit "Use when..." trigger clause and natural synonym coverage. Adding trigger phrases like "Use when editing, resizing, animating, or checking the performance of existing image ads or banners" would lift both completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the customer wants to edit, resize, animate, or check how existing image ads are performing').

Include natural synonyms users would say, such as 'banner', 'creative', or 'social graphic', to broaden trigger-term coverage.

Spell out what 'study' covers (e.g., performance reads and analysis via provider data) instead of leaving it abstract.

DimensionReasoningScore

Specificity

"Edit, resize, animate and study image ads" names the domain and several concrete actions, but "study" is vague and sub-capabilities (tags, ratings, templates, performance analysis) go unmentioned, matching "several specific actions; minor gaps" rather than comprehensive coverage.

4 / 5

Completeness

The "what" is clear (edit, resize, animate, study image ads), but there is no "Use when..." clause or equivalent trigger guidance; the second sentence routes new ads elsewhere rather than stating when this skill applies, capping completeness at 3 per the guideline.

3 / 5

Trigger Term Quality

Terms like "image ads", "edit", "resize", and "animate" are natural, but common user variations such as "banner", "creative", "social graphic", or "campaign" are absent, fitting "some relevant keywords but missing common variations or synonyms".

3 / 5

Distinctiveness Conflict Risk

"image ads with GooseWorks" plus explicit routing of new ads to make-static-ads carves a mostly distinct niche with only minor overlap risk against that closely related creation skill.

4 / 5

Total

14

/

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/entry/goose-ads/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.