sales-prospecting

Build targeted prospect lists with verified contact information

Quality

59%

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/sales-prospecting/SKILL.md

Quality

Content

50%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 skill has a clear stepwise structure and concrete commands, but multiple curl examples contain broken JSON that makes them non-executable as written, the pipeline section duplicates the workflow, and batch operations lack any validation or error-recovery checkpoints. All dimensions score at the midpoint.

Suggestions

Fix the malformed curl commands: move "query", "searchParams", and "lead" payloads inside the -d JSON string (Steps 1, 2, 4), remove the stray text after -d in "Discover More", and correct the stray backtick in the olostep example.

Remove the duplicated "Prospecting Pipeline" section or replace it with a one-line pointer to the Workflow steps, cutting roughly 40 lines of repeated commands.

Add validation checkpoints for the batch workflow: check API responses for errors, handle empty search results, and require verified-email status before a contact is added to a sequence.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, command-first text with no padding or basic-concept explanations, but the "Prospecting Pipeline" section duplicates Steps 1-4 of the Workflow and the "Discover More" section is cluttered. It is not a 4 because the duplication is a clear instance of content that could be cut, and not a 2 because there is no conceptual over-explanation.	3 / 5
Actionability	Concrete curl commands appear throughout, but several are malformed and would fail if copy-pasted: Steps 1, 2, and 4 place payload keys ("query", "searchParams", "lead") outside the closed -d JSON string, and the final example has a stray backtick in "/v1/scrapes`". It is not a 4 because broken JSON in multiple commands is more than a minor gap, and not a 2 because most commands (Steps 3, 5, 6, setup) are complete and executable.	3 / 5
Workflow Clarity	Steps 1-6 are clearly sequenced (define companies → find people → get emails → verify → enrich), but the batch list-building workflow has no error handling: no checking of API responses, no guidance on empty results or failed verification, no retry loop. The batch-operation cap of 3 applies; it is not a 2 because the sequence itself is well defined and includes a verification step.	3 / 5
Progressive Disclosure	No bundle files exist, and the single SKILL.md inlines endpoint reference material plus a duplicated pipeline that would fit better in a separate reference file. Section headers do provide real structure, so it is not a 2, but content that should be separate is inline, so it is not a 4.	3 / 5
	Total	12 / 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 is concrete and on-topic but thin: it states a single clear capability without a use-when trigger clause, natural synonyms, or fuller coverage of what the skill actually does. All dimensions land at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. "Use when building lead lists, finding decision-maker emails, or verifying contacts for sales outreach."

Enumerate the concrete capabilities to lift specificity, e.g. "Search companies by ICP, find decision makers, find and verify emails, and enrich with company data."

Include natural synonyms users would say — leads, lead generation, outreach, contact enrichment — to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain and 1-2 concrete actions ("Build targeted prospect lists", "verified contact information") but is not comprehensive, omitting email finding, decision-maker search, and enrichment. It is not a 4 because the coverage gaps are more than minor, and not a 2 because the actions are concrete rather than generic.	3 / 5
Completeness	The "what" is clear (build targeted prospect lists with verified contact information), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3. It is not a 2 because the "what" is concrete, not vague.	3 / 5
Trigger Term Quality	"prospect lists", "targeted", and "verified contact information" are relevant keywords, but common natural variations users would say — "leads", "lead generation", "outreach", "email finding", "sales" — are missing. It reaches anchor 3 rather than 4 because keyword coverage is partial rather than good-with-few-gaps.	3 / 5
Distinctiveness Conflict Risk	"prospect lists" signals a sales niche, but "contact information" is broad and overlaps with contact-enrichment, email-verification, and CRM-type skills, and no trigger phrases distinguish it. It is not a 4 because the overlap risk with closely related skills is more than minor.	3 / 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: gooseworks-ai/goose-skills
Path: skills/lead-generation/capabilities/sales-prospecting/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.