CtrlK
BlogDocsLog inGet started
Tessl Logo

juicebox-core-workflow-a

Execute Juicebox people search with power filters and ATS export. Trigger: "find candidates", "people search", "juicebox search".

74

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and highly actionable with executable examples and a clean three-step pipeline, but the batch ATS export lacks an explicit validation/verification checkpoint, which is the one dimension holding it back from a perfect content score.

Suggestions

Add a validation checkpoint before Step 3's batch export — e.g., have Claude review/confirm the ranked top-20 candidates and verify a successful export response before proceeding — to lift workflow_clarity to 3.

Clarify how `client` is initialized (auth/setup) so the code blocks are fully self-contained and copy-paste runnable, strengthening actionability.

Turn the bare "Search Filters" bullet under Resources into an actual link or brief inline reference so navigation is fully signaled.

DimensionReasoningScore

Conciseness

The body is lean — a brief overview, three focused code blocks, a compact error table, and short resource/next-steps sections — with no explanation of concepts Claude already knows, matching the lean-and-efficient score-3 anchor.

3 / 3

Actionability

Three concrete, executable TypeScript blocks (search with explicit filters, a complete scoring function, and an export call) plus a table of concrete error fixes make the guidance copy-paste ready, matching the score-3 anchor.

3 / 3

Workflow Clarity

The three steps are clearly sequenced (search -> score -> export), but Step 3 exports a batch of 20 profiles to an ATS with no validation/verification checkpoint or feedback loop, so per the rubric's batch-operation guidance workflow clarity is capped at 2 rather than reaching the score-3 anchor.

2 / 3

Progressive Disclosure

This is a compact, single-purpose skill with no bundle files; its clearly organized sections (Overview, Instructions, Error Handling, Resources, Next Steps) and one-level-deep references satisfy the rubric's note that compact skills can score 3 on well-organized sections alone.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concise and hits all four dimensions at the top level: it states concrete capabilities, includes explicit user-natural triggers, answers both what and when, and occupies a clear niche unlikely to conflict. It is among the strongest descriptions in the reference set.

DimensionReasoningScore

Specificity

"Execute Juicebox people search with power filters and ATS export" names the domain and multiple concrete actions (power-filter search, ATS export), matching the score-3 anchor of listing several specific concrete actions rather than just naming a domain.

3 / 3

Completeness

It states what the skill does (people search with power filters and ATS export) and gives an explicit equivalent trigger clause for when to use it, satisfying both halves required for the score-3 anchor.

3 / 3

Trigger Term Quality

The explicit "Trigger: "find candidates", "people search", "juicebox search"" block provides natural phrases a user would actually say, giving good coverage beyond the single-phrase score-2 example.

3 / 3

Distinctiveness Conflict Risk

The Juicebox-specific niche plus distinct triggers ("juicebox search", "find candidates") make it unlikely to fire for unrelated skills, matching the clear-niche score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.