CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prospect-research

Research a prospective company and prepare a short, source-backed fit assessment.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./api/oss/src/resources/agent_templates/packages/outbound-prospecting/1.0.1/skills/prospect-research/SKILL.md

The canonical home for this skill is prospect-research in Agenta-AI/agenta

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

This is a lean, well-structured instruction-only skill: an unambiguous five-step workflow with built-in sourcing discipline and epistemic hygiene (facts vs. interpretations, known vs. unknown). The only notable gap is that the final assessment's expected format is left implicit, which keeps actionability and workflow clarity at 4 rather than 5.

DimensionReasoningScore

Conciseness

The body is five terse directive lines ("Prefer the company's official website for product and contact facts", "Record facts with source URLs") with zero padding and no explanation of concepts Claude already knows — every token earns its place, matching the 'Lean and efficient' anchor.

5 / 5

Actionability

As an instruction-only skill, the guidance is concrete and directive ("Separate facts from uncertain interpretations", "Explain which criteria match, which do not, and which remain unknown"), with only a minor gap: "Return a short assessment" leaves the deliverable's structure unspecified. Not a 3 because no key details are missing beyond the output format; not a 5 because no template or example of the assessment is given.

4 / 5

Workflow Clarity

A clear five-step sequence runs from reading criteria through sourced fact-gathering to the final assessment, with epistemic checkpoints (source URLs, fact/interpretation separation, matched/unmatched/unknown triage). Not a 5 because there is no explicit verify-and-retry feedback loop; the task is non-destructive, so no validation cap applies.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the single coherent numbered list under one heading is well-organized; per the scoring notes, simple skills in this shape can score 5 without external file references.

5 / 5

Total

18

/

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 concise, in third person, and communicates a clear, non-generic purpose, but it is uniformly at the midpoint across dimensions. Its main weakness is the complete absence of a 'when to use' clause and natural trigger variations, which caps both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to research or qualify a prospect, lead, or target company before outreach."

Add natural synonyms users would actually say — "lead research", "account research", "qualify a prospect", "company profile" — to improve trigger-term coverage and distinctiveness.

Name the concrete deliverables more specifically (e.g. "produce a criteria-by-criteria fit scorecard with source URLs") to lift specificity from two actions to several.

DimensionReasoningScore

Specificity

Quotes: "Research a prospective company", "prepare a short, source-backed fit assessment" — the domain is named with two concrete actions, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. Not a 4 because it does not list several specific actions; not a 2 because the actions named are concrete rather than generic.

3 / 5

Completeness

The 'what' is clear ("Research a prospective company and prepare a short, source-backed fit assessment") but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 4 because 'when' is entirely absent rather than merely implicit; not a 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

Terms like "prospect", "company", and "fit assessment" are relevant natural keywords, but common variations users would say ("lead", "account research", "qualify a lead", "sales prospecting", "due diligence") are absent — the anchor 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

"prospective company" and "fit assessment" carve a sales-research niche, but the phrase "Research a prospective company" still overlaps broadly with general company-research or due-diligence skills and there are no distinct trigger phrases — fitting 'Somewhat specific but could still overlap with similar skills'. Not a 4 because the overlap risk is more than minor.

3 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Agenta-AI/agenta

Path

api/oss/src/resources/agent_templates/packages/outbound-prospecting/1.0.1/skills/prospect-research/SKILL.md

Reviewed

Table of Contents

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.