CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

learn

Help the user understand something well enough to explain it. Use when the user needs to understand something and it is not yet clear what kind of understanding they need.

Quality

74%

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 ./hold/skills/learn/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 an exemplar of token efficiency: a compact router with concrete condition-to-skill mappings, explicit gate-based validation, and a feedback loop for re-routing. Its main weaknesses are compression that occasionally tips into garble ("Run no move nothing lacked calls for") and undefined terminology (gate, move, deciding) that relies on the sibling skills to supply context.

DimensionReasoningScore

Conciseness

The body is ~15 lines with zero padding and no explanations of concepts Claude already knows; every sentence carries routing instruction or output criteria ("Route by what they lack", "End on one line, with what stays open"). Fully matches the lean anchor, though its terseness occasionally borders on cryptic rather than merely efficient.

5 / 5

Actionability

The routing table is concrete and executable ("be quizzed on → use **grasp** skill", "invoking the named skill with the Skill tool") and the ending criteria are specific ("said it back in their own words, or passed the move's gate"). Not 5: "Run no move nothing lacked calls for" is grammatically garbled, and "gate", "move", and "deciding" are undefined in this file, leaving minor execution gaps.

4 / 5

Workflow Clarity

The sequence is clear (identify the lack → route by lack → "Route again while a move's gate shows something else lacked" → end with Held/Not yet) and includes an explicit validate-and-retry feedback loop ("Not yet — the gate showed what they still lack; name it and re-run the move on it"). Not 5: the closing exclusion paragraph ("Nothing built yet → deciding comes first, not hold's") is strained and hard to follow confidently.

4 / 5

Progressive Disclosure

The skill is well under 50 lines with no external references needed; its pointers to sibling skills (grasp, toy, land) are clearly signaled with bold names and arrow mappings. Not 5: there are no section headers and the final run-on exclusion paragraph is dense, leaving minor organization gaps in an otherwise appropriately minimal structure.

4 / 5

Total

17

/

20

Passed

Description

53%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 correctly includes an explicit "Use when..." clause covering both what and when, which places it above the midpoint. However, the capability description is generic ("Help the user understand something") with no concrete actions, and trigger coverage is limited to two terms without synonyms, leaving it broadly overlapping with any teaching or explanation skill.

Suggestions

Name the concrete actions instead of the generic 'help the user understand' — e.g., 'Routes understanding requests to the right approach: deep mastery with quizzing (grasp), building intuition for how something behaves (toy), or landing one memorable point with an audience (land).'

Add natural trigger synonyms users would actually say, such as 'learn', 'teach me', 'explain', 'help me understand', or 'make it stick', to improve trigger matching.

Sharpen the 'when' clause with concrete triggers, e.g. 'Use when the user asks to understand, learn, or explain something and the needed kind of understanding (deep mastery, intuition, or a memorable takeaway) is not yet clear' — this also reduces conflict with the sub-skills it routes to.

DimensionReasoningScore

Specificity

The only stated action is the generic "Help the user understand something"; no concrete actions (routing, quizzing, building artifacts) are named, though the domain and the outcome criterion "well enough to explain it" are stated. It sits between anchor 1 (pure abstraction like "Helps with documents") and anchor 3 (which requires 1-2 concrete actions).

2 / 5

Completeness

Both parts are explicit: what ("Help the user understand something well enough to explain it") and when ("Use when the user needs to understand something and it is not yet clear what kind of understanding they need"). Not 5 because neither part includes concrete trigger phrases, and the what remains vague; not 3 because the when is explicitly stated, not weakly implied.

4 / 5

Trigger Term Quality

"understand" and "explain" are natural phrases users would say, but common variations and synonyms ("learn", "teach me", "quiz me", "intuition") are missing, matching the "some relevant keywords but missing common variations" anchor. Not 4: coverage is only two terms with no synonyms or extensions.

3 / 5

Distinctiveness Conflict Risk

"understand something" is very broad and would overlap many explanation/teaching skills, but the qualifying trigger "not yet clear what kind of understanding they need" scopes it as a router, making it somewhat specific with residual overlap risk. Not 2: the scoping condition meaningfully narrows it; not 4: any "help me understand X" request still matches.

3 / 5

Total

12

/

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

saadshahd/moo.md

Path

hold/skills/learn/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.