CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

shift

Restate the problem in a distant domain's terms. Use when a problem circles inside its own vocabulary.

Quality

79%

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 ./hope/skills/shift/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

This is an exemplary lean instruction-only skill: a precise method with a built-in validation test, a bounded retry, and explicit fallback behavior, all in under 15 lines. The only meaningful gap is the absence of one worked example of a successful shift, which would make the one-to-one mapping test concrete.

DimensionReasoningScore

Conciseness

The body is lean and imperative — 'Restate the problem entirely in that domain's terms — no mixed vocabulary, every home term replaced' — with no re-explanation of anything Claude already knows. Minor stylized flourishes ('nothing waits on the user', 'Nothing more rides along: one restatement, one exposure line') could be trimmed, which keeps it just below 'every token earns its place'.

4 / 5

Actionability

Concrete executable guidance for a reasoning procedure: a 3-step method with a testable acceptance criterion ('if each borrowed term lands one-to-one on a home term, the shift bought nothing'), a bounded retry rule, and a defined fallback verdict. Not 5 only because there is no worked example showing a real problem shifted into a distant domain, which the top anchor's 'specific examples cover the common cases' calls for.

4 / 5

Workflow Clarity

Clear numbered sequence with an explicit validation checkpoint ('Test the mapping before delivering anything'), a genuine feedback loop (one-to-one mapping → 'Pick a more distant domain and run the restatement and this test once more'; second failure → emit the verdict), and full delivery/edge-case handling including the direct-answer and 'explain' skill fallbacks. Matches the anchor with explicit validation steps and error-recovery loops.

5 / 5

Progressive Disclosure

A 13-line, single-purpose skill with no bundle files and nothing that belongs in a separate reference. The rubric's simple-skill exception applies: under 50 lines with no need for external references, well-organized content scores 5 — the numbered method, delivery contract, and fallback branches are cleanly separated with no buried references.

5 / 5

Total

18

/

20

Passed

Description

62%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 cleanly answers both what and when in two terse sentences with a distinctive trigger, but it relies on a single abstract action and a single trigger phrase. Adding one more concrete capability and a few natural trigger synonyms would move it from solid to comprehensive.

Suggestions

Expand the what-clause with one or two more concrete actions, e.g. 'Restate a problem in a distant domain's terms and expose what its home vocabulary hid.'

Add natural trigger variations users would actually say, e.g. 'Use when a problem circles inside its own vocabulary, when you keep rephrasing it in the same terms, or when an analogy from another field would shake it loose.'

Sharpen distinctiveness by naming the mechanism up front, e.g. contrasting a one-to-one renaming (no movement) from a true domain shift, so it cannot be confused with a general 'explain' or paraphrase skill.

DimensionReasoningScore

Specificity

"Restate the problem in a distant domain's terms" names one concrete action, but nothing beyond it — no secondary actions or coverage of what the restatement includes. Matches 'Names domain and 1-2 concrete actions, but not comprehensive'; not 4 because a single action falls short of 'several specific actions', not 2 because the action is concrete rather than generic.

3 / 5

Completeness

Both halves are explicit: "Restate the problem in a distant domain's terms" (what) and "Use when a problem circles inside its own vocabulary" (when). Matches 'Has both what and when; when could be more explicit or specific'; not 5 because the when lacks concrete trigger phrases and synonyms, not 3 because neither half is missing or weakly implied.

4 / 5

Trigger Term Quality

The trigger phrase "a problem circles inside its own vocabulary" is a natural way a user might describe being stuck, but there are no synonyms or common variations ("stuck in the same terms", "reframe", "outside the box", "analogy"). Matches 'Some relevant keywords but missing common variations or synonyms'; not 4 because coverage is one phrase only, not 2 because that phrase is genuinely natural rather than generic.

3 / 5

Distinctiveness Conflict Risk

"Restate the problem in a distant domain's terms" carves a clear niche (analogical domain-shifting) with an unusual trigger that no generic skill would claim. Matches 'Mostly distinct; minor overlap risk' — the body's own reference to the **explain** skill shows adjacency to explanation/reframing skills; not 5 because of that overlap risk, not 3 because the niche and trigger are unmistakable.

4 / 5

Total

14

/

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

hope/skills/shift/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.