score-intent

Use when validating an intent classifier or ranking independently eligible account and contact records from supplied evidence.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/score-intent/SKILL.md

Quality

Content

92%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 content is a tightly written, well-structured decision procedure with explicit validation checkpoints and guardrails; its only shortfall is the absence of concrete code, which is acceptable for an instruction-only skill but keeps actionability at 4.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanation Claude already knows; every section (Purpose, inputs, workflow, output, guardrails, quality check) earns its tokens with actionable instruction.	5 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill (exact STOP decisions, required input fields, a full output table format), but there is no copy-paste code or command, keeping it just below a 5.	4 / 5
Workflow Clarity	The 7-step workflow is clearly sequenced with explicit validation checkpoints (STOP on tolerance exceeded, STOP on calibration drift), NOT CALIBRATED feedback handling, and a Quality check checklist for the batch scoring process.	5 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized into clearly signaled sections with no need for external references, satisfying the simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

62%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 specific and distinct with a clear 'Use when...' trigger covering both what and when, but its keyword coverage lacks synonyms and the when-clause is not as explicitly elaborated as top-anchor examples.

Suggestions

Add natural-language synonyms and file/extension-style variants a user might actually say (e.g. 'intent scoring', 'rank eligible leads', 'score intent rubric') to broaden trigger-term coverage.

Separate the 'what' (validates a gate classifier and ranks eligible records by an intent rubric) from an explicit 'when' trigger list so the use conditions read more clearly.

Dimension	Reasoning	Score
Specificity	Names two concrete actions — 'validating an intent classifier' and 'ranking independently eligible account and contact records' — but coverage is not comprehensive, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	An explicit 'Use when...' clause answers both what and when, but the when-clause is entangled with the what rather than a separately expanded trigger list, placing it just below a 5.	4 / 5
Trigger Term Quality	Domain keywords like 'intent classifier' and 'eligible account and contact records' are relevant, but natural user synonyms and variations are missing, fitting the 'some relevant keywords' anchor.	3 / 5
Distinctiveness Conflict Risk	The narrow intent-scoring niche on 'independently eligible account and contact records' is clearly distinct from general skills, with only minor overlap risk with closely related eligibility skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: llaskin/AI-SDR-Skill-Pack
Path: skills/score-intent/SKILL.md
Commit: 56ebfd3

Reviewed: ~24 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.