company-contact-finder

Find decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL people search via Gooseworks MCP. Given a company name and target titles, returns a list of contacts with name, title, LinkedIn URL, and location.

Quality

67%

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/lead-generation/capabilities/company-contact-finder/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, well-validated fallback workflow, but it is verbose due to repeated cost and input information and lacks progressive disclosure — all reference material is inline in a single long file.

Suggestions

Deduplicate cost information: state each provider's price once (e.g. in the Cost Comparison table) and reference it from the steps rather than repeating figures in every step header, the Tool Details table, and Metadata.

Move the Gooseworks MCP Tools Reference (Tool Details, Crustdata Filter Columns) and Troubleshooting into a separate reference file (e.g. references/tools.md) and link to it from the procedure to enable progressive disclosure.

Avoid re-describing the inputs in Step 1 since they are already covered by the Inputs table; reference the table instead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and domain-specific (MCP tool usage Claude does not already know), but it repeats the same cost figures ($0.01 Apollo, $0.66 Crustdata, etc.) across step headers, the Cost Comparison table, the Tool Details table, and the Metadata block, and re-describes the same inputs in both the Inputs table and Step 1, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready tool calls with concrete parameters (e.g. apollo_person_search with person_titles/organization_domains/per_page, crustdata conditions with real column/value pairs) plus concrete output formats (table and JSON), matching the top anchor.	3 / 3
Workflow Clarity	The Steps 1–7 are clearly sequenced with explicit decision checkpoints after each search ('If 3+ quality matches: skip to Step 7') and validation/quality checks in Step 3 (fuzzy company match, title filtering, count threshold) with feedback loops for insufficient results, satisfying the top anchor.	3 / 3
Progressive Disclosure	There are no bundle files and the skill is a ~290-line monolithic document with clear sections but everything inline; content that could be split out (Tool Details reference, Crustdata Filter Columns, Troubleshooting) lives in the body, matching the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 specific and distinctive about a concrete contact-finding capability and its data sources, but it lacks an explicit 'Use when...' trigger clause and omits common natural-language variations users might say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to find decision-makers, leads, or contacts at a specific company.'

Include common natural-language variations users would say, such as 'leads', 'prospects', or 'find people at a company'.

Optionally enumerate the concrete actions (search, deduplicate across sources, return enriched contacts) to lift specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('decision-makers at a specific company using Apollo, Crustdata, Fiber, and PDL') and concrete output fields ('name, title, LinkedIn URL, and location'), but it conveys essentially one capability rather than 'multiple specific concrete actions', so it sits at the anchor-2 level rather than 3.	2 / 3
Completeness	It clearly answers 'what does this do', but there is no 'Use when...' clause or equivalent explicit trigger guidance for when to invoke it, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes reasonably natural terms a user might say ('decision-makers', 'company', 'contacts', 'LinkedIn URL'), but misses common variations such as 'leads', 'prospects', or 'find people at a company', matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and distinctive — finding company contacts via the named Gooseworks MCP providers (Apollo/Crustdata/Fiber/PDL) — with triggers unlikely to overlap with other skills.	3 / 3
	Total	9 / 12 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: gooseworks-ai/goose-skills
Path: skills/lead-generation/capabilities/company-contact-finder/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.