Name: lever
Rating: 62.4 (1 reviews)
Author: membranedev

lever

Lever integration. Manage Leads, Persons, Organizations, Deals, Activities, Notes and more. Use when the user wants to interact with Lever data.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/lever/SKILL.md

Quality

Content

76%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 delivers highly actionable, copy-paste-ready Membrane commands and a well-sequenced connection workflow with explicit state and feedback handling. Its weaknesses are mild introductory over-explanation of what an ATS is, inlined reference-grade tables, and—most importantly—no verification step after destructive actions, which caps workflow clarity.

Suggestions

After running destructive/batch actions (archive opportunity, delete interview, create opportunity), add a verification step such as re-fetching with get-opportunity or list-interviews-for-opportunity to confirm the change took effect.

Trim the opening paragraph explaining what an ATS/recruiting system is; Claude already knows this, so lead with the integration mechanics instead.

Consider moving the full popular-actions table and proxy-flag reference into a references/ file, keeping SKILL.md as an overview with a one-level-deep pointer.

Dimension	Reasoning	Score
Conciseness	The body is largely lean command-driven content with a compact actions table and terse best practices, matching the efficient anchor; not 5 because the opening paragraph explains what an ATS/recruiting is and a few asides (e.g. "so you can focus on the integration logic") are mild padding Claude does not need, and not 3 because the bulk earns its place.	4 / 5
Actionability	It provides copy-paste-ready commands throughout (install, login, connection ensure, --wait polling, action list/run with concrete --input JSON, proxy flags) plus a popular-actions table with real keys, matching the fully-executable anchor covering common cases.	5 / 5
Workflow Clarity	The connection flow is well-sequenced with explicit state handling and a poll/feedback loop, but running destructive/batch actions (archive opportunity, delete interview, create opportunity) has no verification step afterward; per the rubric, missing validation for destructive or batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections with headers and tables and no nested references, but the 20-row popular-actions table and proxy-flag reference are inlined reference-grade material with no external file split, sitting between the good-structure (4) and clear-overview-with-references (5) anchors.	4 / 5
	Total	16 / 20 Passed

Description

71%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 clearly names the Lever integration domain and several concrete entities, and includes an explicit "Use when" trigger, yielding strong completeness and distinctiveness. Its weaknesses are a generic "Manage... and more" verb and an abstract "when" clause that omits recruiting-specific natural trigger terms.

Suggestions

Replace the generic "interact with Lever data" trigger with concrete phrases users actually say, e.g. "Use when working with candidates, job postings, requisitions, interviews, or applicant tracking in Lever."

Swap "Manage... and more" for distinct action verbs reflecting real operations, e.g. "list, create, and update opportunities, postings, requisitions, and notes."

Dimension	Reasoning	Score
Specificity	"Manage Leads, Persons, Organizations, Deals, Activities, Notes" names six concrete entities, matching the anchor for several specific actions with minor gaps; not 5 because the single generic verb "Manage" and "and more" signal incomplete coverage, and not 3 because it lists far more than 1-2 entities.	4 / 5
Completeness	It has a clear "what" (Lever integration managing named entities) and an explicit "when" ("Use when the user wants to interact with Lever data"), matching the anchor where both are present but the when could be more specific; not 5 because the when lacks concrete trigger phrases, not 3 because the when is explicit rather than merely implied.	4 / 5
Trigger Term Quality	Terms like "Lever integration", "Lever data", and the named entities give some relevant keywords, but the trigger "when the user wants to interact with Lever data" is generic and misses natural recruiting phrases users actually say (candidates, postings, interviews, ATS); sits between anchors 3 and 4 and leans down due to the generic trigger.	3 / 5
Distinctiveness Conflict Risk	"Lever integration" scoped to named Lever entities gives a clear app-specific niche with minimal conflict risk, matching the anchor for a clear niche with distinct triggers; the Lever-specific framing is as distinguishable as a named-app skill can be.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/lever/SKILL.md
Commit: f484c82

Reviewed: ~18 hours ago

Table of Contents

Discovery Implementation Validation

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.