Name: bullhorn
Rating: 56.8 (1 reviews)
Author: membranedev

bullhorn

Bullhorn integration. Manage Persons, Organizations, Deals, Leads, Projects, Users and more. Use when the user wants to interact with Bullhorn data.

Quality

65%

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/bullhorn/SKILL.md

Quality

Content

67%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 a well-structured, highly actionable guide to driving Bullhorn through the Membrane CLI, with concrete commands and an explicit connection-state feedback loop. Its main weakness is token weight from two large inline reference tables that would be better externalized.

Suggestions

Move the ~70-item "Bullhorn Overview" entity list into a separate reference file (e.g., references/entities.md) and link to it from the body, keeping only the most-used entities inline.

Consider externalizing the full "Popular actions" table to a reference file and showing 4-5 key examples inline, to reduce the inline token footprint.

Add one fully worked end-to-end example (connection ensure → capture id → action list → action run with a real input and sample output) to close the actionability gap from placeholder-only examples.

Dimension	Reasoning	Score
Conciseness	The CLI command guidance is lean, but the ~70-item flat "Bullhorn Overview" entity list and the 20-row "Popular actions" table are bulky inline reference material that could be tightened or externalized, adding tokens that compete with context.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, auth, connection, action list/run, and proxy with a documented flags table, but every example uses placeholders (CONNECTION_ID, QUERY) with no fully worked end-to-end call showing a real action and its output.	4 / 5
Workflow Clarity	The install → authenticate → connect → search → run sequence is clear and the connection state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) provides explicit polling feedback loops, but the "Step 2" reference has no matching labeled header, leaving a minor sequencing gap.	4 / 5
Progressive Disclosure	The body is well-organized into clearly headed sections with no nested references, but the large entity and action tables are inlined rather than split into one-level-deep reference files, a minor organization gap for a 240-line skill.	4 / 5
	Total	15 / 20 Passed

Description

62%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 is clearly scoped to a named product and includes an explicit Use-when trigger, satisfying the what/when requirement. It is weakened by a single generic verb ("Manage"), the vague "and more", and a lack of natural synonym trigger terms.

Suggestions

Replace the single generic verb "Manage" with several distinct concrete actions (e.g., "Search candidates and job orders, create and update placements, sync contacts and deals").

Drop the vague "and more" and instead list 3-4 of the most-used actions to lift specificity.

Add natural trigger terms a user would actually say, e.g., "Use when the user wants to search Bullhorn candidates, track job submissions, or manage placements and client contacts."

Dimension	Reasoning	Score
Specificity	The description names many concrete Bullhorn entity types ("Persons, Organizations, Deals, Leads, Projects, Users") but applies only one generic verb ("Manage") plus the vague "and more", so it lists domain objects rather than several distinct concrete actions.	3 / 5
Completeness	It provides a clear "what" (Bullhorn integration managing listed entities) and an explicit "Use when the user wants to interact with Bullhorn data" trigger, but the "when" clause is fairly generic rather than enumerating concrete trigger phrases.	4 / 5
Trigger Term Quality	The trigger relies on the product name "Bullhorn" ("interact with Bullhorn data"), which users would say, but it omits common natural synonyms and context terms like CRM, ATS, recruiting, candidates, or job orders that a user might actually phrase.	3 / 5
Distinctiveness Conflict Risk	Leading with "Bullhorn integration" gives it a clear niche with minimal conflict risk, though the generic entity list (Persons, Organizations, Deals) creates minor overlap with other CRM-type skills.	4 / 5
	Total	14 / 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/bullhorn/SKILL.md
Commit: f484c82

Reviewed: 4 days 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.