inbound-lead-enrichment

Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record. Produces enriched lead data ready for qualification or outreach. Tool-agnostic.

Quality

61%

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/composites/inbound-lead-enrichment/SKILL.md

Quality

Content

55%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 thorough, well-sequenced enrichment workflow with strong actionability via concrete rules and schemas. It is held back by significant verbosity (re-explaining familiar concepts and inlining material that belongs in separate reference files) and limited validation/feedback loops for a batch operation that writes to a CRM.

Suggestions

Tighten the body by removing explanations Claude already knows (e.g., why buying committees matter, how LinkedIn disambiguation works) and trimming repeated field/source tables; move full JSON schemas and edge-case catalogues into reference files.

Add explicit validation/feedback loops for the batch CRM update — e.g., a dry-run/duplicate-check step before writing, and a post-write verification pass — since the Update Protocol currently only says 'don't overwrite existing data'.

Split the per-step JSON output schemas and the field source/fallback tables into a single references/ file (e.g., SCHEMAS.md) with clearly signaled one-level-deep links from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose at ~490 lines, re-explaining well-known concepts (what a buying committee is, why multi-threading improves win rates, how to disambiguate LinkedIn matches) and repeating the field/source tables and JSON schemas that Claude could infer, with several sections padded beyond what the task requires.	2 / 5
Actionability	Provides concrete, executable guidance — explicit seniority inference rules, deduplication logic, field-by-field source/fallback tables, and full JSON output schemas per step — with only minor gaps (e.g., no concrete command for the CSV write, and tool names like SixtyFour/Orthogonal are placeholders).	4 / 5
Workflow Clarity	A clearly sequenced 6-step pipeline with an architecture diagram and explicit human checkpoint in Step 1; however, despite this being a batch/destructive operation (bulk CRM writes, duplicate creation risk) the validation/verification is only a single checkpoint and the Update Protocol lacks a verify-before-write feedback loop, so it stops short of a 5.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and the entire detailed spec — per-field source tables, JSON schemas, edge cases — is inlined into one ~490-line SKILL.md rather than split into one-level-deep reference files, so structure is present but content that should be separate is inline.	3 / 5
	Total	13 / 20 Passed

Description

67%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 specific, action-oriented description that clearly conveys what the skill does across the full enrichment pipeline. Its main weakness is the absence of an explicit 'Use when...' trigger clause in the description itself and the lack of natural user-spoken trigger phrases, which limit completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause to the description with concrete trigger phrases (e.g., 'Use when enriching inbound leads, filling in missing lead data, or researching companies and stakeholders for lead qualification').

Include natural user-spoken keywords in the description such as 'enrich these leads' and 'fill in the missing data' rather than relying on the body for trigger guidance.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record' — with comprehensive coverage of the enrichment workflow.	5 / 5
Completeness	Clearly answers 'what' (fills gaps, researches company/person/stakeholders, checks CRM, updates record) but has no 'when/Use when...' clause in the description itself; the trigger guidance lives only in the body's 'When to Auto-Load' section, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Uses relevant terms ('inbound leads', 'enriched lead data', 'CRM', 'qualification or outreach') but omits the natural trigger phrases a user would actually say ('enrich these leads', 'fill in missing data') which only appear in the body, not the description.	3 / 5
Distinctiveness Conflict Risk	The inbound-lead-enrichment niche is fairly distinct — the combination of company research, stakeholder discovery, and CRM relationship checks is specific — though 'researches the company / checks CRM' could lightly overlap with adjacent lead-qualification or CRM skills.	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/composites/inbound-lead-enrichment/SKILL.md
Commit: 2523432

Reviewed: 6 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.