CtrlK
BlogDocsLog inGet started
Tessl Logo

juicebox-reference-architecture

Implement Juicebox reference architecture. Trigger: "juicebox architecture", "recruiting platform design".

52

Quality

59%

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 ./plugins/saas-packs/juicebox-pack/skills/juicebox-reference-architecture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 concise, technical, and provides concrete code with an error-handling table, but it lacks an explicit validation-gated workflow and critically fails progressive disclosure by inlining code that duplicates orphaned bundle files the body never links to.

Suggestions

Replace the inlined service-layer/caching/event-pipeline code with a concise overview and point to the existing bundle files, e.g., '## Service Layer — see [service-layer.md](references/service-layer.md)' and '## Implementation patterns — see [implementation-guide.md](references/implementation-guide.md)'.

Add an explicit implementation workflow with validation checkpoints (e.g., validate ATS export payload before sending, verify dedup counts, retry-on-failure loop) to lift workflow clarity above the batch-operations cap of 3.

Fix 'Next Steps' to reference the actual bundle files present rather than the non-existent 'juicebox-deploy-integration' skill.

DimensionReasoningScore

Conciseness

The body is dense and technical, assumes competence (does not explain Redis, Bull, or ATS), and inline comments justify rather than pad values (e.g., '30 min — candidate pools shift slowly'), fitting 'Efficient; minor instances of over-explanation that could be trimmed'. Not a 5 because the inlined code blocks and diagram carry some content that earns a separate-file home rather than the overview.

4 / 5

Actionability

Concrete TypeScript is provided for CandidateSearchService, CACHE_CONFIG, RecruitingPipeline, and the data model interfaces, fitting 'Mostly executable guidance; concrete code with minor gaps'. Not a 5 because helper methods (scoreCandidate, deduplicateAgainstATS, hashCriteria, flagForRecruiterReview) are referenced but undefined, so it is not copy-paste ready.

4 / 5

Workflow Clarity

Architecture components and an error-handling table give rough sequencing and recovery guidance, but there is no explicit implementation workflow with validation checkpoints, and batch/destructive operations (ATS export, outreach) lack validate-fix-retry loops, fitting the anchor 'Steps listed but validation gaps' and the batch-operations cap at 3. Not a 4 because no explicit checkpoints or feedback loops are present.

3 / 5

Progressive Disclosure

Substantial code (service layer, caching, event pipeline, data model) is inlined in the body even though bundle files references/service-layer.md (522 lines) and references/implementation-guide.md (245 lines) exist and are never referenced from the body; 'Next Steps' points to a different skill instead, fitting 'content that clearly belongs in separate files is inlined; or references are buried'. Not a 3 because the bundle references are entirely absent rather than merely weakly signaled.

2 / 5

Total

13

/

20

Passed

Description

57%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 includes an explicit trigger clause and a clear niche, but its 'what' is a single broad verb with no concrete capabilities enumerated. It is distinct yet under-specified in action detail.

Suggestions

Expand the 'what' beyond 'Implement' to list 2-4 concrete capabilities (e.g., 'Design candidate search and scoring services, configure Redis caching tiers, and wire ATS export to Greenhouse/Lever').

Add natural synonym triggers such as 'candidate search platform', 'ATS integration design', or 'recruiting pipeline architecture' for broader keyword coverage.

Tighten the broad 'recruiting platform design' trigger to be more Juicebox-specific to reduce overlap with generic recruiting skills.

DimensionReasoningScore

Specificity

The phrase 'Implement Juicebox reference architecture' names the domain but offers only one minimal, generic action ('Implement') with no concrete sub-actions, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because there is not even 1-2 concrete actions listed, only a single broad verb.

2 / 5

Completeness

It states a 'what' ('Implement Juicebox reference architecture') and an explicit 'when' via the Trigger clause with concrete trigger phrases, fitting 'Has both what and when; when could be more explicit or specific'. Not a 5 because the 'what' is broad and not comprehensive in describing concrete capabilities.

4 / 5

Trigger Term Quality

The Trigger clause provides two relevant phrases ('juicebox architecture', 'recruiting platform design') that users might say, but coverage is thin with no synonyms or file/extension-style variations, fitting 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because keyword coverage is limited to two terms rather than a fuller set.

3 / 5

Distinctiveness Conflict Risk

'Juicebox architecture' is a clear niche trigger with minimal conflict risk, but 'recruiting platform design' is broader and could overlap with general recruiting/platform skills, fitting 'Mostly distinct; minor overlap risk with closely related skills'. Not a 5 because one trigger is generic enough to invite overlap.

4 / 5

Total

13

/

20

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.