CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is discernment-nudge in anthropics/skills

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 delivers an instruction-only skill with exemplary actionability — exact output format, worked examples for every prompt type, and a fully specified qualify/skip decision procedure with no validation-requiring operations. Its weakness is conciseness: roughly 185 lines where tightened prose (and possibly a reference file for the boundary case-law) could cut a third without losing any decision-relevant signal.

Suggestions

Compress each of the four "user has already told you not to" patterns to its rule plus one short example; several currently spend 4-5 sentences restating the same rationale (e.g., "This wins even when the answer is full of statistics…" duplicates the preceding sentence).

Merge the duplicated educational carve-out material: the "When not to" bullet and the Roth IRA elaboration cover the same ground twice; state the rule once with the single best example.

Consider moving the extended boundary case-law (the four opt-out patterns plus the boundary calls) into a references file, keeping SKILL.md to the core qualify list, prompt-writing rules, and output format.

DimensionReasoningScore

Conciseness

The body runs ~185 lines for a skill whose action is "append 2-3 formatted follow-up questions". The boundary policy is genuinely load-bearing, but several sections restate their own rule: "The user asked you to verify, cite, or flag uncertainty" spends five sentences on one rule, the educational carve-out is explained both in "When not to" and again through the Roth IRA elaboration, and "This wins even when the answer is full of statistics…" repeats the preceding sentence. This matches anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened") rather than anchor 4, where only minor trims would be needed.

3 / 5

Actionability

For an instruction-only skill the guidance is fully concrete and copy-paste ready: exact lead-in line ("A few things worth a second look:"), exact format rules ("append it after a blank line", "plain bullets", "No blockquote, no heading", "Plain text only — no HTML, no headings, no emoji", "under ~120 characters", "first person, conversational, question form"), three worked example prompts covering all three prompt types, and a complete example output block. Nothing is left to inference, so this is the anchor-5 case rather than anchor 4's "minor gaps".

5 / 5

Workflow Clarity

The single action is unambiguous and completely sequenced: answer the question fully first ("Always answer the question completely first. The nudge comes after"), apply the enumerated qualify/skip decision including the once-per-conversation rule ("Offer the nudge at most once in a conversation… if you have already offered it on an earlier turn, stay silent"), then append the nudge in the exact format and stop ("The nudge is the closer"). There are no destructive or batch operations, so no validation cap applies, and per the rubric's simple-skill exception a single unambiguous action scores 5; it does not fall to 4 because the decision and output sequence contain no gaps.

5 / 5

Progressive Disclosure

The body is well-sectioned ("Why this exists", "When to offer the nudge", "When not to", "Writing the prompts", "Output format") and appropriately self-contained for a policy the model must apply at reply time — there are no bundle files and no API-reference-style bulk content to split out. However, at ~185 lines of prose with the boundary case-law as the bulk, it exceeds the under-50-lines clean case, and the extended boundary discussion (e.g., the four "user already told you" patterns) could partly live in a reference file. This matches anchor 4 ("good structure; most content is appropriately placed; minor organization gaps") rather than anchor 5.

4 / 5

Total

17

/

20

Passed

Description

91%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 very strong description: it explicitly states both what the skill does and exactly when to invoke or skip it, with comprehensive natural trigger terms and concrete coverage of qualifying answer types. Its only deductions are the second-person voice (mandated −1 specificity penalty) and minor trigger-domain overlap with artifact-drafting skills.

Suggestions

Rewrite the description in third person (e.g., "Appends 2-3 follow-up questions after a substantive answer…") to satisfy the voice rule and recover the specificity penalty.

Tighten the long skip-condition list into a shorter third-person clause, since the body already explains the boundaries in full.

DimensionReasoningScore

Specificity

The description comprehensively lists concrete actions — "append 2-3 short follow-up questions, each tied to something specific in what you just produced" to "check key facts, probe the reasoning or assumptions, and notice missing context" — plus an enumerated list of qualifying artifacts and six explicit skip conditions, which matches the anchor-5 comprehensive coverage. However, it is written in second person ("After you give a substantive answer", "Skip it when the user asked…"), and the rubric's voice rule mandates reducing the specificity score by 1 for second-person voice, so it lands at 4 rather than 5.

4 / 5

Completeness

Both what and when are explicitly and concretely answered: what — "append 2-3 short follow-up questions… that help the user check key facts, probe the reasoning or assumptions, and notice missing context"; when — "After you give a substantive answer or draft that the user may act on… invoke this skill BEFORE finalizing your reply", with "Do this at most once per conversation" and explicit skip conditions. This is the anchor-5 case, clearly above anchor 4's "when could be more explicit".

5 / 5

Trigger Term Quality

Natural trigger terms are covered comprehensively with synonyms: "advice or recommendations", "goals, plans, pitches, proposals, or emails", "estimates or projections", "analysis or interpretation of data", "factual claims", "multi-step argument" — these are exactly the words users say when requesting such outputs. This matches the anchor-5 comprehensive coverage; no file extensions are relevant to this skill's trigger domain.

5 / 5

Distinctiveness Conflict Risk

The niche (post-answer discernment prompts) and the action are clearly distinct from other skills, but the trigger surface — "advice", "plans", "pitches", "proposals", "emails", "estimates", "analysis of data" — spans the domains of many drafting and analysis skills, creating minor overlap risk. This fits anchor 4 ("mostly distinct; minor overlap risk with closely related skills") rather than anchor 5's minimal conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

BigSimmo/PsychSift

Path

.claude/cloud-profile/skills/discernment-nudge/SKILL.md

Reviewed

Table of Contents

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.