lead-hand-skill

Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation

Quality

66%

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 ./crates/openfang-hands/bundled/lead/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, highly actionable reference for the lead-generation pipeline with concrete patterns, scoring rules, and output templates, but it explains some general business concepts Claude already knows, lacks validation checkpoints in its batch/dedup workflow, and keeps all detail inline with no progressive disclosure. Tightening the explanatory sections and adding verification steps would most improve it.

Suggestions

Remove general-knowledge padding (e.g., the 'Typical Budget' and 'Sales Cycle' columns of the company-size table, the verbose ICP sub-questions) and keep only domain-specific guidance.

Add explicit validation checkpoints for batch/destructive steps — e.g., 'review fuzzy-match pairs before merging' in dedup and 'flag enriched fields with low confidence for human review' in scoring.

Move the detailed scoring rubric and full output-format templates into reference files (e.g., SCORING.md, OUTPUT_FORMATS.md) linked from a concise overview, so the main body acts as a navigable hub.

Dimension	Reasoning	Score
Conciseness	Most sections are dense and actionable (search patterns, scoring rubric, normalization rules, format templates), but the ICP question list and the company-size table explain general business concepts (typical budgets, sales cycles for startup/SMB/enterprise) Claude already knows, matching 'mostly efficient but includes some unnecessary explanation'. Not a 3 because those explanatory tokens do not earn their place.	2 / 3
Actionability	Provides copy-paste-ready search-query patterns, a point-valued scoring rubric, ordered email-pattern templates, concrete dedup rules (e.g., 'Levenshtein distance < 2'), and full CSV/JSON/Markdown output examples, matching 'specific examples; copy-paste ready'. Not a 2 because guidance is concrete and complete rather than pseudocode, and absence of executable code is not penalized for a prompt-only instruction skill.	3 / 3
Workflow Clarity	Sections are topic-ordered (ICP → research → enrichment → scoring → dedup → output → compliance) giving an implicit pipeline, but there are no explicit validation/verification checkpoints for batch enrichment or destructive dedup merges, so workflow clarity is capped at 2 per the guidelines. Not a 1 because a sequence is present; not a 3 because checkpoints are entirely missing.	2 / 3
Progressive Disclosure	The body is well-organized with clear headers and tables, but it is a monolithic ~228-line file with no external references at all, and detailed material (full scoring rubric, output templates, normalization rules) that could be split into reference files is inline, matching 'some structure but content that should be separate is inline'. Not a 1 because organization is clear; not a 3 because nothing is split or signaled as a one-level-deep reference.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly conveys a distinct lead-generation niche and enumerates several concrete pipeline actions, but it omits any explicit 'Use when…' trigger guidance and leans on some domain jargon over natural user phrasings. Adding a trigger clause and everyday synonyms would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when…' trigger clause (e.g., 'Use when the user needs to find, enrich, score, or deduplicate B2B sales leads or build a prospect list').

Replace or supplement jargon with natural phrasings users actually say: 'find leads', 'prospect list', 'B2B sales leads', 'find decision-makers'.

Drop the 'Expert knowledge for' framing and lead with a third-person verb (e.g., 'Generates and enriches AI lead lists…') to match the good-example style.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — 'web research, enrichment, scoring, deduplication, and report generation' — matching the 'lists multiple specific concrete actions' anchor. Not scored lower because the actions are specific and domain-grounded; the 'Expert knowledge for' framing is mild fluff but does not reduce the count of concrete actions.	3 / 3
Completeness	Clearly states what the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the judging guidelines. Not a 1 because the 'what' is clearly and comprehensively stated.	2 / 3
Trigger Term Quality	'AI lead generation' is a natural user term, but 'enrichment', 'deduplication', and 'scoring' are domain jargon and common variations like 'find leads', 'prospecting', and 'B2B sales leads' are missing, matching 'some relevant keywords but missing common variations'. Not a 3 because coverage of natural phrasings is incomplete.	2 / 3
Distinctiveness Conflict Risk	'AI lead generation' plus scoring/deduplication forms a clear, distinct niche unlikely to conflict with unrelated skills, matching the 'clear niche with distinct triggers' anchor. Not a 2 because the combined pipeline framing is specific enough to avoid meaningful overlap.	3 / 3
	Total	10 / 12 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: RightNow-AI/openfang
Path: crates/openfang-hands/bundled/lead/SKILL.md
Commit: acf2587

Reviewed: about 7 hours 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.