CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

grocery-shopping

Use when user needs to create grocery list from recipes - consolidates ingredients across recipes, checks pantry inventory, converts to purchasable quantities, and provides automation options for Costco/Instacart

Quality

85%

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

70%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 content is highly actionable and the six-phase workflow is clearly sequenced with checkpoints and stop conditions, but the file pays for it in token efficiency: ~485 lines with the same example list repeated three times and sections duplicating the frontmatter. Splitting examples and store tips into reference files would fix both the conciseness and progressive-disclosure weaknesses.

Suggestions

Cut the body to a single worked example: Example 1 and Example 3 re-render the Phase 5 output format almost verbatim, so keep one canonical template and delete the duplicates.

Move Store-Specific Tips, Common Mistakes/Red Flags, and the Examples section into reference files (e.g. references/examples.md, references/stores.md) linked one level deep from the phase content, and remove the Quick Reference table that restates the phase list.

Trim trivia Claude already knows ('Store brands often cheaper, same quality', 'Widest selection, good prices') and the 'When to Use' block that duplicates the frontmatter description, keeping only the don't-use boundary guidance.

DimensionReasoningScore

Conciseness

The body is noticeably verbose for a straightforward task: the same shopping-list example is rendered three times (Phase 5, Example 1, Example 3), the Quick Reference table and 'When to Use' section duplicate the phase list and the frontmatter description, and generic trivia like 'Store brands often cheaper, same quality' pads the text. This fits the 'several unnecessary explanations or padded sections' anchor rather than the mostly-efficient level 3, though it avoids teaching truly basic concepts that would drop it to 1.

2 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact setup questions to ask, worked consolidation arithmetic ('1/3 cup + 1/4 cup = 7/12 cup'), specific package-size conversions with leftover notes ('Buy 12 oz bag, need ~4 oz'), and copy-paste-ready output templates. Per the rubric's scoring note, the absence of code is not penalized since the guidance is this concrete.

5 / 5

Workflow Clarity

Six phases are clearly sequenced with a checkbox progress tracker, an explicit user-confirmation checkpoint in Phase 3 ('Should I remove these from the shopping list, or do you need to restock any?'), STOP conditions for edge cases, and a Success Metrics checklist. This matches the level-5 anchor with feedback loops and checklists; the operation is non-destructive, so the batch-validation cap does not apply.

5 / 5

Progressive Disclosure

The single ~485-line file has good section headers and internal navigation, but there are no bundle files at all, and content that clearly belongs in separate references (three full Examples, Store-Specific Tips, Common Mistakes/Red Flags) is inlined. This lands on the 'some structure but content that should be separate is inline' anchor rather than 2, since sections are well-organized, or 4, since nothing is split out.

3 / 5

Total

15

/

20

Passed

Description

92%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: it opens with an explicit 'Use when' trigger, enumerates concrete pipeline capabilities in third person, and anchors on distinctive terms like Costco and Instacart. Its only weakness is modest keyword coverage, missing natural synonyms such as 'shopping list' and 'meal prep' that users commonly say.

DimensionReasoningScore

Specificity

The description lists four concrete actions spanning the entire workflow ('consolidates ingredients across recipes, checks pantry inventory, converts to purchasable quantities, and provides automation options for Costco/Instacart'), matching the comprehensive-coverage anchor; it does not fall to 4 because there are no meaningful coverage gaps.

5 / 5

Completeness

It explicitly answers both 'when' ('Use when user needs to create grocery list from recipes') and 'what' (the four named capabilities), matching the level-5 anchor with concrete trigger phrasing rather than the merely adequate 'when' of level 4.

5 / 5

Trigger Term Quality

Natural terms like 'grocery list', 'recipes', 'pantry', 'Costco', and 'Instacart' give good keyword coverage, but common user phrasings such as 'shopping list' and 'meal prep'/'meal planning' are missing, so it does not reach the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

The trigger requires grocery-list creation intent and names distinctive entities (Costco, Instacart), giving a clear niche with minimal overlap against adjacent recipe-finding or meal-planning skills; it is more distinct than the level-4 'minor overlap risk' anchor.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

kmondlane/ExoMind

Path

skills/grocery-shopping/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.