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

81%

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

Quality

Content

88%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.

A highly actionable, well-sequenced procedure with executable tool calls, explicit decision thresholds between fallback providers, dedup rules, and troubleshooting recovery paths. The skill is a single self-contained file with good internal structure; its only real gaps are minor cost-information redundancy and inline reference tables that could be moved to a separate reference file.

Dimension	Reasoning	Score
Conciseness	The body is dense with task-specific information (tool calls, params, costs, decision thresholds) with almost no explanation of concepts Claude already knows; the only tightening opportunities are repeated cost figures across step headers, the cost table, tool details, and the metadata block, matching anchor 4 ('efficient; minor instances that could be trimmed') rather than anchor 5's every-token-earns-its-place or anchor 3's noticeable unnecessary explanation.	4 / 5
Actionability	Every step gives copy-paste-ready MCP calls with exact parameters and example values (e.g., the crustdata conditions JSON), plus concrete output formats in both table and JSON form, matching anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases').	5 / 5
Workflow Clarity	The 7-step procedure has an explicit decision checkpoint after each fallback ("If 3+ quality matches: skip to Step 7"), quality-validation filters in Step 3, dedup rules, and error-recovery guidance in Troubleshooting, matching anchor 5's explicit validation steps and feedback loops; it is not a 4 because no checkpoints are implicit.	5 / 5
Progressive Disclosure	No bundle files exist, and the single file is well-sectioned with clear headers and navigable tables; the inline API-reference material (cost comparison, tool details, Crustdata filter columns) is the kind of content that could be split into a reference file, which keeps it at anchor 4 ('good structure; minor organization gaps') rather than anchor 5's well-signaled external references or anchor 3's poorly organized inline bulk.	4 / 5
	Total	18 / 20 Passed

Description

66%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.

A concrete, third-person description that clearly states what the skill does and what it returns, with specific provider names giving it good distinctiveness. Its main weakness is the complete absence of any 'when to use this' trigger guidance, which caps completeness at 3.

Suggestions

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

Include common synonyms users would naturally say — "leads", "prospects", "find people at [company]" — alongside "decision-makers".

Optionally mention disambiguation inputs (company LinkedIn URL) in the description to further distinguish it from generic people-search skills.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("Find decision-makers at a specific company") and concrete outputs ("contacts with name, title, LinkedIn URL, and location") plus the four providers, but covers only one core action rather than multiple, matching anchor 4 ('several specific actions; minor gaps') better than anchor 5's comprehensive multi-action coverage or anchor 3's 1-2 actions.	4 / 5
Completeness	The 'what' is clearly answered (find decision-makers, return contacts with specified fields) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; it is not a 4 because the 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	"decision-makers", "company", "target titles", "contacts", and "LinkedIn URL" are natural phrases users would say when needing this skill, but common synonyms like "leads", "prospects", or "find people at" are missing, placing it at anchor 4 rather than anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Naming the exact providers ("Apollo, Crustdata, Fiber, and PDL... via Gooseworks MCP") and the decision-maker/contact niche makes it mostly distinct with only minor overlap risk against other lead-generation or LinkedIn-lookup skills, fitting anchor 4 rather than anchor 5's fully distinct trigger set.	4 / 5
	Total	15 / 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: gooseworks-ai/goose-skills
Path: skills/lead-generation/capabilities/company-contact-finder/SKILL.md
Commit: cc3e518

Reviewed: 7 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.