discernment-nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

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/anthropic-discernment-nudge/SKILL.md

Quality

Content

75%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 body is highly actionable with a precise output format and well-structured sections. It is somewhat verbose in its boundary discussion and lacks explicit decision checkpoints, which are the weakest dimensions.

Suggestions

Tighten the "When not to" section by collapsing repetitive parentheticals and the trailing "Boundary calls" note into a compact table or shorter bullets.

Trim the "Why this exists" framing to a few lines so the operational guidance starts sooner.

Add a brief decision checkpoint (e.g., "If none of the offer-when cases apply, stop — do not nudge") to make the workflow's validation explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of irrelevant concept explanations, but the boundary section is padded with lengthy parentheticals, repeated edge-case disquisitions ("one more that's easy to miss", "Boundary calls"), and philosophical framing in "Why this exists" that could be tightened.	3 / 5
Actionability	Gives fully executable guidance: the exact lead-in ("A few things worth a second look:"), 2-3 plain bullets, three concrete prompt types with verbatim example questions, and a 120-character length constraint, copy-paste ready for the common cases.	5 / 5
Workflow Clarity	The sequence is clear (answer completely first, decide via the when-to/when-not-to criteria, append the nudge after a blank line with the exact format) with the once-per-conversation rule, but there are no explicit validation/checkpoint steps for the decision itself, leaving minor gaps.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Why, When to offer, When not to, Writing the prompts, Output format) with no nested references; the very long boundary section could arguably be split into a reference file, which is the minor organization gap keeping it from 5.	4 / 5
	Total	16 / 20 Passed

Description

80%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 comprehensive on what, when, and boundaries, with strong distinctiveness. Its main weakness is second-person voice (a specificity penalty) and trigger phrasing that, owing to the skill's meta nature, is not phrased as natural user keywords.

Suggestions

Rewrite the description in third person (e.g., "Appends 2-3 follow-up questions after substantive answers") to avoid the voice penalty and tighten specificity.

Surface a few natural user-side trigger phrases (e.g., "advice", "recommendation", "estimate", "should I...") as explicit keywords so the trigger reads as something a user would say.

Consider a short "Use when..." clause to make the trigger phrasing more conventional and scannable.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions and artifact types ("append 2-3 short follow-up questions", "check key facts, probe the reasoning or assumptions, and notice missing context", plus goals/plans/pitches/proposals/emails/estimates/projections), which is comprehensive coverage at a 5 anchor; reduced by 1 because the description uses second person ("you give", "your reply") per the voice penalty.	4 / 5
Completeness	Explicitly answers both what ("append 2-3 short follow-up questions...help the user check key facts, probe the reasoning or assumptions, and notice missing context") and when ("After you give a substantive answer or draft that the user may act on" plus a concrete skip list), with explicit trigger guidance, matching the 5 anchor.	5 / 5
Trigger Term Quality	Contains some relevant trigger phrases ("advice or recommendations", "trivial how-to or simple lookup", "double-check, cite, or review") but the trigger is inherently meta (Claude's own behavior after a substantive answer) rather than user utterances, so it misses natural variations and synonyms users actually say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (post-answer reflection prompts) with distinct triggers and an extensive boundary list, making conflict with other skills minimal.	5 / 5
	Total	17 / 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: boisenoise/skills-collections
Path: skills/anthropic-discernment-nudge/SKILL.md
Commit: 652629d

Reviewed: ~11 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.