CtrlK
BlogDocsLog inGet started
Tessl Logo

mendel

Gregor Mendel — genetics mentor, patient experimenter, and gardener-monk. Trigger this skill when users ask about genetics, heredity, inheritance patterns, Mendelian laws, dominant/recessive traits, gene segregation, independent assortment, Punnett squares, classical genetics, or evolution-genetics connections. Also trigger when discussing the philosophy of science, how great ideas get ignored, the relationship between faith and science, or the virtue of patient long-term observation. Even if the user doesn't say "Mendel" explicitly, trigger this skill for questions touching genetics, breeding, trait inheritance, or genomics history. Part of the AIPOCH Science Mentor Skill Hub.

68

Quality

82%

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

78%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.

A well-crafted persona skill body with excellent actionability and clean progressive disclosure — concrete voice examples, adaptive tiers, and verified reference files make it directly usable. The chief weakness is conciseness, driven by a redundant 'Core Reminders' section and repeated character reinforcement.

Suggestions

Remove or sharply condense the 'Core Reminders' section, since every bullet restates content already established in 'Who You Are' or 'The Gardener Voice'.

Consolidate the repeated patient/warm/shy/ratios-beautiful characterizations so each trait is established once rather than echoed across multiple sections.

Trim the 'You are NOT an all-knowing oracle' and 'You are a monk first, a scientist second' framing lines that restate the humility and faith points already made above.

DimensionReasoningScore

Conciseness

The persona detail largely earns its place and avoids explaining concepts Claude already knows, but the 'Core Reminders' section restates beats already covered in 'Who You Are' and 'The Gardener's Voice' (patient, warm, shy, ratios beautiful, bees), and the patient/warm/shy characterization is reinforced redundantly across sections.

3 / 5

Actionability

Highly concrete for an instruction-only persona skill: copy-paste-ready voice models (the brown-eyed-parents ❌/✅ example), explicit adaptive-depth tiers with sample phrasings, an evidence-signaling legend (🟢🟡🔵), a classify-then-structure workflow table, and ready-to-use intellectual-honesty talking points.

5 / 5

Workflow Clarity

The 'Response Workflow' gives a clear three-step sequence (classify → structure → evidence-signal) with a classification table and structure template; checkpoints are implicit rather than explicit, but no destructive or batch operations are present so the strict validation cap does not apply.

4 / 5

Progressive Disclosure

A well-signaled 'Reference Files' table up top lists three one-level-deep references with explicit 'When to read' conditions, the body re-points to them at the relevant workflow steps, and all three referenced files (genetics-guide.md, persona-guide.md, philosophy-of-science.md) exist in ./references/.

5 / 5

Total

17

/

20

Passed

Description

86%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 strong description with explicit, repeated trigger guidance and rich natural keywords that would reliably activate the skill. The main weakness is that capabilities are expressed as trigger topics rather than concrete actions, and the persona/philosophy scope introduces mild conflict risk with sibling hub skills.

Suggestions

Lead with one or two concrete capability verbs (e.g., 'Explains inheritance patterns and walks through Punnett squares in Mendel's voice') before the trigger clauses so the 'what' reads as action, not just persona.

Tighten the philosophy-of-science and faith/science triggers to contexts where the user is clearly engaging a genetics or mentor framing, reducing overlap with general philosophy skills.

Consider dropping or condensing the third 'Even if the user doesn't say Mendel' trigger clause, as its terms largely restate the first clause's keywords.

DimensionReasoningScore

Specificity

Names the domain ('genetics mentor, patient experimenter, and gardener-monk') and many specific engagement topics (Punnett squares, segregation, independent assortment), but the concrete actions are framed as trigger conditions rather than explicit capabilities, leaving coverage implied rather than comprehensively stated.

3 / 5

Completeness

Explicitly answers both 'what' (genetics mentor/experimenter persona engaging these topics) and 'when' with concrete trigger phrases repeated across three trigger clauses ('Trigger this skill when users ask about...', 'Also trigger when...', 'Even if the user doesn't say Mendel explicitly, trigger...').

5 / 5

Trigger Term Quality

Comprehensive natural terms users would actually say — 'genetics, heredity, inheritance patterns, dominant/recessive traits, Punnett squares, breeding, trait inheritance, genomics history' — including synonyms and the explicit case where 'Mendel' is not mentioned.

5 / 5

Distinctiveness Conflict Risk

Clear Mendel/genetics-mentor niche with distinct triggers, but the broadened philosophy-of-science, faith-and-science, and 'patient observation' triggers plus the stated 'AIPOCH Science Mentor Skill Hub' membership create minor overlap risk with sibling mentor skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.