funding-signal-outreach

End-to-end funding signal composite. Takes any set of companies, detects recent funding events, qualifies against your company context, finds relevant people (buyers, champions, users), and drafts personalized outreach. Tool-agnostic — works with any company source, contact finder, and outreach platform.

Quality

79%

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/outreach/composites/funding-signal-outreach/SKILL.md

Quality

Content

77%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 well-sequenced, highly actionable multi-step workflow with typed data contracts and human validation checkpoints at every step — exemplary on workflow clarity. Its weaknesses are the monolithic single-file structure with no progressive disclosure to reference files, and minor padding (mock tables, ASCII diagram) that inflates token cost.

Suggestions

Move the Step 0 configuration questionnaires and per-tool specifics (search recipes, outreach-tool CSV formats) into reference files (e.g. references/config.md, references/tools.md), keeping SKILL.md as an overview with one-level-deep, clearly signaled references.

Trim the mock checkpoint output tables with "..." placeholder rows and the ASCII architecture diagram — the pipeline is already conveyed by the step headers and contracts.

Flesh out the remaining high-level tool instructions (e.g. the Apollo enrichment endpoint, Crunchbase funding rounds API) with the concrete endpoint/parameters, or point to a reference file where they are specified.

Dimension	Reasoning	Score
Conciseness	The body is instructional throughout — no explaining concepts Claude already knows — and the contract tables earn their tokens (e.g. the qualification criteria table with weights). But the ASCII architecture diagram, mock checkpoint tables with "..." placeholder rows, and repeated tier-1 example blocks are padding that could be trimmed, matching "efficient; minor instances of over-explanation" rather than "every token earns its place".	4 / 5
Actionability	Quotes: "Query \"{company_name}\" AND (\"raised\" OR \"funding\" OR \"Series\") AND \"2026\"", per-tool handoff table rows ("Smartlead \| Chain to cold-email-outreach Phase 4"), typed output contracts, and word-count rules per touch ("Touch 1: 50-90 words"). Mostly executable guidance with concrete specifics, but a few tool steps stay high-level ("Apollo: Use company enrichment endpoint") without the actual call or parameter, so not fully copy-paste ready.	4 / 5
Workflow Clarity	Quotes: a 6-step sequence (Step 0 Config through Step 5 Handoff), each with an input/output contract and a "Human Checkpoint"; feedback loops are explicit — "You can promote, demote, or drop any company", "Iterate? Tell me what to change (tone, length, angle, CTA)", and "Ready to launch? (This is the final gate...)". The batch email operation has validation at every step, so the missing-validation cap does not apply; this matches the anchor with clear sequence, explicit validation, and error-recovery loops.	5 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but no references/, scripts/, or assets/ bundle exists and the entire ~530-line implementation is inlined in SKILL.md — content that clearly belongs in separate files (the five config questionnaires, per-tool search recipes, tool-specific handoff formats) is all inline. This matches "some structure but content that should be separate is inline"; it is not a 4 because SKILL.md functions as the full implementation doc rather than an overview pointing to detailed materials.	3 / 5
	Total	16 / 20 Passed

Description

75%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 strong, concrete description that enumerates the full pipeline in third-person voice with a clear niche. Its main deficiency is the absence of any explicit "Use when..." trigger clause, which caps completeness and slightly weakens trigger coverage despite otherwise specific language.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user mentions recently funded companies, funding announcements, or wants to act on funding signals with a target company list."

Add natural user phrasings as trigger terms — "recently funded", "raised a round", "Series A/B", "funding announcement" — to improve trigger_term_quality.

State the trigger condition in terms of the input the user has ("Use when you have a list of target companies") to strengthen the when-side of completeness.

Dimension	Reasoning	Score
Specificity	Quotes: "detects recent funding events", "qualifies against your company context", "finds relevant people (buyers, champions, users)", "drafts personalized outreach" — four concrete pipeline actions in third-person voice covering the full chain. This matches the anchor for multiple specific concrete actions with comprehensive coverage; anchor 4 (minor gaps) does not apply since no step of the pipeline is missing.	5 / 5
Completeness	The "what" is explicit and detailed, but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description — the judging guideline caps completeness at 3 for a missing when-clause. Not a 2 because the what-side is fully concrete rather than vague.	3 / 5
Trigger Term Quality	Quotes: "funding events", "recent funding", "funding signal", "outreach", "companies" — good natural keyword coverage. Common variations a user would actually say ("raised funding", "recently funded companies", "Series A", "prospect") are missing, so it falls just below the comprehensive-synonyms anchor 5.	4 / 5
Distinctiveness Conflict Risk	Quotes: "funding signal composite", "detects recent funding events", "drafts personalized outreach" — a clear niche (funding-signal-triggered outreach) with distinct triggers and minimal overlap risk against generic outreach or contact-finding skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (548 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/outreach/composites/funding-signal-outreach/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.