CtrlK
BlogDocsLog inGet started
Tessl Logo

yes

SB Leader 夸夸模式 — ENFP 型领导,懂情绪有节奏。底层行为不变(三条红线、方法论),旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/yes/SKILL.md
SKILL.md
Quality
Evals
Security

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 a well-structured, example-rich tone/persona guide that is concise and highly actionable, with concrete templates covering the common cases. The main improvements are removing minor repetition, adding a fallback rule for unmatched scenarios, and making the tone-selection logic explicit.

Suggestions

Add a brief fallback rule for situations not covered by the seven example scenarios (e.g., 'default to the 任务接收 template, then escalate to 严肃提醒 if a verification gap appears') so tone selection is explicit rather than implied.

De-duplicate the 70/20/10 ratio: state it once in 人格特质 and reference it from 注意 instead of restating it.

If the skill grows further, move the eight-flavor table and tease library into a reference file linked from the body, which would keep SKILL.md under the ~50-line lean-skill threshold and lift progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and example-driven with no explanation of concepts Claude already knows; it loses one point only for minor padding such as the 70/20/10 ratio being restated in the 注意 section after already appearing in 人格特质.

4 / 5

Actionability

Provides concrete, copy-paste tone templates for seven scenarios, an eight-flavor table, a tease library, and an explicit 70/20/10 rule — highly actionable for an instruction-only skill; the small gap is the absence of guidance for scenarios that do not match the listed examples.

4 / 5

Workflow Clarity

As a single-purpose tone skill with no destructive or batch operations, the simple-skill exception applies and the single action (respond in ENFP cheerleader tone) is well-specified; it stays at 4 because the selection logic for which tone template to apply in a given moment is implicit rather than an explicit decision rule.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; content is organized into clearly headed sections (人格特质, 语气示范, 味道×ENFP, 戏谑吐槽库, 注意). At ~70 lines it slightly exceeds the under-50 simple-skill threshold, so it sits at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

75%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 clearly states what the skill does and when to trigger it, with a strong set of natural Chinese trigger synonyms. Its main weakness is the highly generic 'yes' trigger/name, which raises conflict risk, and the capability list reads as behavior patterns rather than concrete actions.

Suggestions

Remove or qualify the bare 'yes' trigger (and consider renaming the skill) to avoid firing on ordinary affirmative replies; keep the more distinctive '/pua:yes', '夸夸模式', '鼓励模式', '夸我' as triggers.

Add one or two concrete capability verbs up front (e.g., 'Provides empathetic, encouraging code-review narration with a 70/20/10 praise-to-tease ratio') to lift specificity beyond behavior-pattern phrasing.

Tighten the 'what' into a single declarative sentence before listing triggers, so the capability is unambiguous even before the behavior changes are described.

DimensionReasoningScore

Specificity

Names the domain ('SB Leader 夸夸模式') and several concrete behavior changes ('共情+鼓励+偶尔戏谑吐槽', '底层行为不变(三条红线、方法论)'), but as a tone/persona skill the actions are behavior patterns rather than a comprehensive capability list, matching the score-3 anchor of domain + 1-2 concrete actions without full coverage.

3 / 5

Completeness

Explicitly answers both 'what' (ENFP-tone behavior shift) and 'when' via a 'Triggers on:' clause listing concrete phrases, satisfying the score-5 anchor; the missing-trigger cap does not apply because explicit trigger guidance is present, and the voice is third-person.

5 / 5

Trigger Term Quality

Rich natural synonyms users would say ('夸夸模式', '鼓励模式', '夸我', '唠嗑模式', '情绪价值') plus command forms ('/pua:yes'); good coverage but the bare 'yes' trigger is not a natural need-phrase, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

It is a distinct persona variant, but the trigger 'yes' and the skill name 'yes' are extremely generic, so a user saying 'yes' in ordinary conversation could fire the wrong skill — fitting the score-3 anchor of somewhat specific but with real overlap risk.

3 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tanweai/pua
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.