CtrlK
BlogDocsLog inGet started
Tessl Logo

endurance-reminder-practice

Use when maintaining long-term motivation after humiliation or defeat. Based on Goujian's 'tasting gall' (卧薪尝胆) practice: physical reminders, daily verbal affirmations of past shame, personal austerity, and sharing hardships with the people to build loyalty for eventual recovery.

66

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_107/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-structured instruction-only skill with clear sequencing and a verification section. Its weaker dimensions are actionability (placeholder-dependent, historically framed steps) and workflow_clarity (soft checkpoints without feedback loops).

Suggestions

Replace the '[your defeat]' placeholder with an explicit instruction to substitute the user's specific setback, and translate historical artifacts (e.g., 'gall bladder') into a modern actionable equivalent so each step is directly executable.

Tighten the Verification section into checkable criteria with a feedback loop — e.g., if loyalty/support is not measurably increasing, specify which step to revisit — to lift workflow_clarity toward a score-3 feedback pattern.

DimensionReasoningScore

Conciseness

The body is lean at roughly 20 lines with no padding or explanation of concepts Claude already knows, matching the score-3 'every token earns its place' anchor rather than the score-2 'could be tightened' case.

3 / 3

Actionability

Steps like 'Place a bitter object (gall bladder) in living space' and 'Ask yourself: Have you forgotten the shame of [your defeat]?' are concrete but rely on a placeholder and historical artifacts, fitting the score-2 'some concrete guidance but incomplete' anchor rather than fully executable instructions.

2 / 3

Workflow Clarity

Steps are sequenced 1–6 and a Verification section exists, but the checkpoints are soft ('building measurable loyalty') with no error-recovery feedback loop, matching score-2 'sequence present but checkpoints missing or implicit' rather than the score-3 explicit-validate-and-retry pattern.

2 / 3

Progressive Disclosure

Per the rubric's simple-skill guidance, an under-50-line single-task skill with well-organized sections (Overview, Steps, Core Principle, Expected Outcomes, Verification) and no need for external references scores 3 on progressive disclosure.

3 / 3

Total

10

/

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.

A strong, distinctive description with explicit 'Use when' triggers and a concrete action list. Its main weakness is trigger-term naturalness — the literary framing narrows the range of phrases a user would actually say.

Suggestions

Add plainer user-spoken trigger variations (e.g., 'when feeling defeated', 'recovering motivation after a setback', 'rebuilding after failure') alongside the literary 'tasting gall' framing to broaden trigger coverage.

Keep the historical reference but lead with the everyday terms so the description reads as a natural trigger rather than a niche citation.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'physical reminders, daily verbal affirmations of past shame, personal austerity, and sharing hardships with the people' — matching the score-3 anchor of listing several specific actions rather than the score-2 single-domain naming.

3 / 3

Completeness

It explicitly answers both 'when' ('Use when maintaining long-term motivation after humiliation or defeat') and 'what' (the enumerated practice actions), satisfying the score-3 anchor of clear triggers plus capability description.

3 / 3

Trigger Term Quality

Natural terms like 'long-term motivation', 'humiliation', and 'defeat' are present, but the phrasing leans literary ('tasting gall') and lacks common user-spoken variations, falling short of broad score-3 coverage.

2 / 3

Distinctiveness Conflict Risk

The Goujian 'tasting gall' framing is a highly distinctive niche with triggers unlikely to overlap with other skills, matching the score-3 clear-niche anchor rather than the score-2 generic 'works with X' pattern.

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.