classify-reply

Use when classifying supplied prospect replies for intent, objections, opt-outs, uncertainty, and routing boundaries.

Quality

85%

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

Quality

Content

78%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-structured, actionable instruction-only skill with a clear sequenced workflow and validation checklist. It would benefit from a worked end-to-end example and an explicit re-check feedback loop for the batch case.

Suggestions

Add one short worked example showing a sample reply mapped to the full output (quote, facts/inferences/missing, intent, route, copy) to lift actionability from concrete to copy-paste ready.

Make the feedback loop explicit in the Quality check section: state that if any check fails, Claude should re-classify that reply before returning results, which is especially relevant for the multi-reply batch case.

Tighten the recurring opt-out/stop guidance so it appears once authoritatively in the Guardrails and is only referenced elsewhere, reducing the minor redundancy between Workflow steps 5-6, Guardrails, and Quality check.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining known concepts, though opt-out/stop handling is reinforced across workflow, guardrails, and quality check, adding minor redundancy.	4 / 5
Actionability	Concrete guidance is given via enumerated intent categories, explicit routes (STOP, NEEDS VERIFICATION), and a precise output format, but no worked example maps a sample reply to its output to fully close the loop.	4 / 5
Workflow Clarity	A clearly sequenced 7-step workflow is paired with an explicit Quality check validation section; because verification is present the batch cap does not apply, though an explicit 're-classify on check failure' feedback loop is only implicit.	4 / 5
Progressive Disclosure	The self-contained, ~50-line body is organized into clear sections (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check, Example invocation) with no need for external references.	5 / 5
	Total	17 / 20 Passed

Description

92%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 concise, well-targeted description that explicitly pairs what the skill does with a 'Use when' trigger and enumerates concrete classification actions. Keyword synonyms are the only minor gap.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete classification actions — 'intent, objections, opt-outs, uncertainty, and routing boundaries' — covering the domain comprehensively, matching the anchor for several specific concrete actions.	5 / 5
Completeness	An explicit 'Use when' clause supplies the trigger and the classifying actions state the 'what', so both what and when are answered with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural domain keywords like 'prospect replies', 'opt-outs', 'objections', and 'intent' are present, but coverage lacks synonyms or common phrasings a user might also say, landing just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The prospect-reply classification niche with opt-out/routing triggers is a clear, specialized domain with minimal overlap risk against other skills.	5 / 5
	Total	19 / 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/classify-reply/SKILL.md
Commit: 56ebfd3

Reviewed: ~23 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.