CtrlK
BlogDocsLog inGet started
Tessl Logo

investor-research

Research VCs, angels, and investors - portfolio, thesis, contact info

52

Quality

66%

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 ./skills/research/capabilities/investor-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 four-step structure and concrete endpoint-level intent, but every curl example is syntactically invalid JSON-in-shell that would fail if executed, which undercuts its core value as a copy-paste playbook. Validation and step-chaining are absent, and the tail sections add duplication rather than progressive disclosure.

Suggestions

Fix all curl payloads so the full JSON body (api, path, and searchParams/query/lead) sits inside a single quoted -d '...' string; as written, every example breaks shell quoting and would not execute.

Add validation checkpoints and chaining: check each response for errors or empty results, and use Step 1's investor/firm output to parameterize Steps 2-4 instead of hardcoded Sequoia examples.

Merge the redundant "Example Usage" into the workflow steps as parameter variations, and clean up the "Discover More" section (remove the stray "api show fiber" token and the misquoted olostep example) or move endpoint discovery into a reference file.

DimensionReasoningScore

Conciseness

The body is lean and code-forward with no over-explanation of known concepts ("Find investors in your space", "Get contact info for partners"), matching 'efficient; minor instances that could be trimmed'. It is not 5 because the "Example Usage" section re-runs the Step 1 and Step 2 commands with only parameter variations, which is redundant.

4 / 5

Actionability

Commands name concrete endpoints (/v1/investor-search, /v1/people-search, /find-email) with realistic parameters, but every curl payload is syntactically broken: the JSON closes after '"path":"..."' and the "searchParams"/"query" object sits outside the quoted -d string with stray unmatched '}' tokens (and '"path":"/v1/scrapes`"}' misquotes in Discover More), so nothing is copy-paste executable. This matches 'concrete guidance but incomplete; pseudocode instead of executable code'.

3 / 5

Workflow Clarity

Steps 1-4 are clearly headed and sequenced, but there are no validation checkpoints (no error or empty-result handling on API responses) and steps do not chain (Step 2 hardcodes "Sequoia Capital" instead of using Step 1 output), matching 'sequence present but checkpoints missing or implicit'. It is not 4 because checkpoint gaps are pervasive, and not 2 because the sequence itself is well defined.

3 / 5

Progressive Disclosure

The single file has reasonable section headers, but the ~130-line body inlines endpoint-discovery material in a muddled "Discover More" section (with a stray "api show fiber" token) and duplicates workflow content in "Example Usage", matching 'some structure but could be better organized'. No bundle files exist to provide one-level-deep references.

3 / 5

Total

13

/

20

Passed

Description

61%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 names a clear niche with natural trigger terms and concrete deliverables, but lacks a 'Use when...' trigger clause and lists only one action verb, limiting completeness and specificity. It is serviceable but sits noticeably below the exemplar descriptions that pair multiple concrete actions with explicit usage triggers.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user mentions VCs, angel investors, fundraising, or wants to research a firm's portfolio or partners before outreach."

Expand the action verbs to cover the actual workflow: "Search investors by stage and industry, pull portfolio companies, find partner contacts and emails" rather than a single 'Research' verb.

Include common synonyms such as "venture capital firms" and "fundraising" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Research VCs, angels, and investors" names the domain with one concrete action, and "portfolio, thesis, contact info" are deliverables rather than distinct actions, matching the '1-2 concrete actions but not comprehensive' anchor. It is not 4 because no additional specific actions (e.g., find emails, analyze investment patterns) are listed, and not 2 because the domain is named with concrete outputs.

3 / 5

Completeness

The description clearly answers 'what' (research investors' portfolio, thesis, contact info) but has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

Terms like "VCs", "angels", "investors", "portfolio", and "thesis" are natural phrases users would say, giving good keyword coverage. It is not 5 because common variations such as "venture capital firms", "fundraising", or "LPs" are missing, and not 3 because the terms present are specific and natural rather than generic.

4 / 5

Distinctiveness Conflict Risk

Investor research is a distinct niche with terms unlikely to trigger unrelated skills, matching 'mostly distinct; minor overlap risk'. It is not 5 because overlap with generic research or contact-lookup skills remains possible given the absent trigger phrasing.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
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.