CtrlK
BlogDocsLog inGet started
Tessl Logo

bian-que-six-incurable-conditions

Use when screening patients before committing treatment resources. Applies Bian Que's 六不治 framework to identify six incurable conditions (arrogance, greed, poor self-care, yin-yang chaos, extreme weakness, trust in shamans over physicians).

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 lean, well-structured instruction-only skill: it defines the six conditions with concrete observable signs, gives a clear decision rule, and closes with an explicit verification checklist. It earns full marks because it is concise, actionable, clearly sequenced, and appropriately self-contained for a simple single-purpose skill.

DimensionReasoningScore

Conciseness

The body is lean (~57 lines) with no padding explaining concepts Claude already knows — each condition is just Chinese term, translation, signs, and prognosis, plus a compact IF/ELSE and a 3-item verification checklist. It is not below 3 because there is no unnecessary explanation; the repeated 'Prognosis: Cannot be treated' lines are a deliberate scannable structure rather than concept-fluff.

3 / 3

Actionability

As an instruction-only skill it gives concrete, actionable guidance: six named conditions with specific observable signs ('Patient refuses to listen to reason', 'Unwilling to spend money on treatment'), a clear IF/ELSE decision rule, and a verification checklist requiring documentation 'with specific observed signs (not assumptions)'. Per the code_vs_instruction note, the absence of code is not penalized because the guidance is actionable.

3 / 3

Workflow Clarity

The screening workflow is unambiguous — assess the six conditions, then the IF/ELSE ('Decline treatment or set expectations appropriately' vs 'Proceed with standard diagnosis'), followed by a 3-step verification checklist that serves as explicit checkpoints. Per the simple_skills note, a clear single-action screening decision can score 3, and no feedback loop is required since this is not a destructive/batch operation.

3 / 3

Progressive Disclosure

No bundle files exist and none are referenced, so there is nothing to verify; the single self-contained file is well-organized into clear sections (Overview, Six Conditions, Decision Framework, Clinical Application, Verification) with no nested references. Per the simple_skills note, a small single-purpose skill with no need for external references earns 3 from well-organized sections alone.

3 / 3

Total

12

/

12

Passed

Description

85%

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 strong: it explicitly states what the skill does and when to use it, names a distinctive niche, and lists concrete actions in third person. The main weakness is trigger-term quality, which leans on specialized framework vocabulary over the everyday phrasings a user would naturally say.

Suggestions

Add natural-language trigger variants users would actually say, e.g. 'Use when deciding whether to accept or decline a patient for treatment, assessing if a case is treatable, or screening before committing resources'.

Soften the specialized terms in the trigger clause ('yin-yang chaos', 'trust in shamans') toward phrasings a non-specialist clinician might use, keeping the precise framework name as a distinctive keyword.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — 'screening patients before committing treatment resources' and 'identify six incurable conditions' — and enumerates the six specific conditions, matching the 'lists multiple specific concrete actions' anchor; it is not vague like 'Helps with documents'. Voice is third person ('Applies...'), so no specificity penalty applies.

3 / 3

Completeness

It explicitly answers both what ('Applies Bian Que's 六不治 framework to identify six incurable conditions...') and when ('Use when screening patients before committing treatment resources') with an explicit 'Use when' trigger, matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

It has some natural keywords a clinician would say ('screening patients', 'incurable conditions', 'treatment resources'), but the parenthetical list (arrogance, greed, yin-yang chaos, trust in shamans over physicians) is domain content rather than natural trigger phrasings, and common variations ('is this patient treatable', 'should I take this case') are missing — closer to 'some relevant keywords but missing common variations' than to full natural-term coverage.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific — 'Bian Que's 六不治 framework' with six named conditions — giving it distinct triggers unlikely to overlap with other skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor rather than the generic 'would conflict with many skills' case.

3 / 3

Total

11

/

12

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
baojie/shiji-kb
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.