Name: hunter
Rating: 51.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

hunter

Hunter integration. Manage Organizations. Use when the user wants to interact with Hunter data.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

63%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 is a solid, actionable integration guide with strong connection-readiness feedback loops and copy-paste commands, but it carries some marketing prose and is monolithic for its length. Splitting the action catalog and proxy reference into bundled reference files, and fixing the step numbering, would noticeably improve it.

Suggestions

Remove the marketing intro ('Sales and marketing professionals use it to generate leads and contact potential customers') and other auth-plumbing commentary to tighten token usage.

Move the popular-actions table and proxy flag reference into separate bundled reference files (e.g. references/actions.md, references/proxy.md) and link to them from SKILL.md, since the skill exceeds 50 lines and would benefit from progressive disclosure.

Fix the workflow numbering (add a '1a' or relabel, define 'Step 2') and add an explicit verification step after running actions (e.g. check the `output` field and handle non-READY/error states) to close the validation gap.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command examples and tables, but includes unnecessary explanation such as the marketing intro ('Sales and marketing professionals use it to generate leads...') and 'so you can focus on the integration logic rather than auth plumbing', fitting 'mostly efficient but includes some unnecessary explanation or could be tightened.' It is not 4 because the padding is more than minor.	3 / 5
Actionability	Provides copy-paste-ready commands for install, login, connection ensure/get, action list, action run (with JSON input), and request proxying, plus a popular-actions table and flag reference. It is not 5 because examples rely on placeholders (CONNECTION_ID, QUERY, <actionId>) and the mapping from an action key to its runnable actionId is left implicit.	4 / 5
Workflow Clarity	There is a clear sequence (install → auth → connect → poll for READY → handle clientAction → search → run) with explicit state-driven feedback loops for connection readiness and error recovery. It is not 5 because the step numbering is incoherent ('1b' with no '1a', undefined 'Step 2') and there is no verification step after running an action or proxy request.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but the ~150-line skill is a single monolithic file with no one-level-deep references, and reference-like content (the popular-actions catalog and proxy flag table) is inlined rather than split out. It is not 4 because content that would benefit from separate files is not separated and no references are signaled.	3 / 5
	Total	14 / 20 Passed

Description

50%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 correctly includes an explicit 'Use when...' trigger and names the specific product, giving it decent completeness and distinctiveness, but it is thin on concrete capabilities and natural trigger keywords. The action listed ('Manage Organizations') is generic and does not reflect Hunter's actual email-finding/verification purpose.

Suggestions

Replace the generic 'Manage Organizations' with concrete capabilities users associate with Hunter, e.g. 'Find and verify email addresses, search domains for emails, and enrich company/person data.'

Add natural trigger keywords users actually say, such as 'find email', 'verify email', 'email finder', 'domain search', or 'lead generation', so the skill surfaces for those requests.

Tighten the 'when' clause to reference concrete triggers, e.g. 'Use when the user wants to find, verify, or look up email addresses, or enrich company and contact data via Hunter.'

Dimension	Reasoning	Score
Specificity	Names the domain ('Hunter integration') but the only action ('Manage Organizations') is minimal and generic rather than a concrete capability, matching the anchor 'Names the domain but actions are minimal or generic.' It is not a 3 because 'Manage Organizations' is not a concrete, specific action like 'extracts content'.	2 / 5
Completeness	Both a 'what' ('Hunter integration. Manage Organizations.') and an explicit 'when' ('Use when the user wants to interact with Hunter data.') are present, with the 'when' clause explicit rather than implied. It is not 5 because the 'when' lacks concrete trigger phrases and the 'what' is vague, and not 3 because the 'when' is explicit, not weakly implied.	4 / 5
Trigger Term Quality	The only keyword is the product name 'Hunter' plus the generic phrase 'interact with Hunter data'; the natural phrases users actually say ('find email', 'verify email', 'email finder', 'domain search') are absent, fitting 'one or two generic keywords; missing the natural phrases users say.' It is not a 3 because no relevant natural synonyms are present.	2 / 5
Distinctiveness Conflict Risk	Naming a specific product ('Hunter integration') gives a clear niche with mostly distinct triggers and minimal conflict risk. It is not 5 because the generic 'Manage Organizations' phrasing could overlap with CRM/org-management skills, introducing minor overlap risk.	4 / 5
	Total	12 / 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/hunter/SKILL.md
Commit: f484c82

Reviewed: 5 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.