CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reframe

Restate a problem off the framing it arrived in. Use when a framing came by default, not by choice — every option inside it loses, or an ask names a step or an artifact and leaves the outcome it serves unnamed.

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

92%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.

An exceptionally lean, single-turn instruction skill: a three-step procedure with an explicit test-and-retry validation loop, a bounded failure exit, delivery format, and clear boundary routing to neighboring skills. The only material gap is the absence of a worked before/after example that would pin down the abstract vocabulary (subject/level/scope).

DimensionReasoningScore

Conciseness

Every sentence is instruction ("Name what the current framing fixes", "Change exactly one and state the problem again... one plain sentence", "Stop there.") with zero padding and no explanation of concepts Claude already knows. This matches "lean and efficient; assumes Claude's competence; every token earns its place" — the ~19-line body is entirely load-bearing.

5 / 5

Actionability

The guidance is concrete and executable for an instruction-only skill: exact transformations ("raise its level to the goal past it", "change its subject to what the artifact must do: the verb, who it acts on, and the limit"), a one-sentence output format, and a bounded retry rule. It falls short of score 5 because the core vocabulary ("subject, its level, its scope") is never defined or shown in a worked before/after example, leaving the reader to infer what "level" means in practice.

4 / 5

Workflow Clarity

Steps 1–3 are clearly sequenced and step 3 is an explicit validation checkpoint with a feedback loop ("Test the new statement before delivering anything... discard it, change a different one of the three, and state and test once more") plus a bounded failure exit ("carry that verdict out as the result instead of a statement"), followed by delivery instructions and edge-case routing. This matches the top anchor: clear sequence, explicit validation, feedback loops for error recovery.

5 / 5

Progressive Disclosure

The skill is a single-purpose, under-50-line body with no need for external references, and no bundle files exist — the simple-skill exception applies: "progressive disclosure can score 5 with just well-organized sections." The body is well organized (preamble, numbered procedure, delivery, fallback, boundary routing) and its cross-references to other skills are clearly signaled by name (**judge**, **explain**), so nothing is buried or inlined that belongs in a separate file.

5 / 5

Total

19

/

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.

A well-formed description with an explicit "Use when" clause and specific trigger conditions, written in an unusually compressed, literary register. Its main weaknesses are a single named action rather than a fuller capability list and trigger phrasing that users would not naturally echo verbatim. It is distinct from typical file-processing skills and carries only minor conflict risk.

Suggestions

Add one or two more named actions to the capability sentence (e.g., "Restate a problem off the framing it arrived in; raise a step-ask to the goal it serves; turn an artifact-ask into what the artifact must do") so specificity reaches several concrete actions.

Include natural user phrasings as trigger terms — e.g., "stuck between bad options", "asking the wrong question", "rethink the approach", "challenge the assumption" — so the description matches what users actually say.

Make the when-conditions more concrete and quotable, e.g., "Use when every option offered loses, when the user names a step (\"run the tests\", \"write the PRD\") but not what it's for, or when an artifact is requested without the outcome it serves."

DimensionReasoningScore

Specificity

The description names the domain (problem framing/reframing) and one concrete action — "Restate a problem off the framing it arrived in" — but does not list several specific actions; the single verb "restate" is specific yet singular, matching the "1-2 concrete actions, not comprehensive" anchor. It is not score 4 because that anchor requires several specific actions, and not score 2 because the action named is neither minimal nor generic.

3 / 5

Completeness

Both parts are present: the what ("Restate a problem off the framing it arrived in") and an explicit "Use when" clause with three distinct trigger conditions ("every option inside it loses", "an ask names a step", "an artifact and leaves the outcome it serves unnamed"). It falls short of score 5 because the when-conditions are stated abstractly (e.g., "leaves the outcome it serves unnamed") rather than as plain, concrete trigger phrases a user would echo.

4 / 5

Trigger Term Quality

"framing", "options", "step", "artifact", and "outcome" are relevant keywords, but common natural variations users would say — reframe, rethink, stuck, "asking the wrong question", assumptions — are absent. This lands on "some relevant keywords but missing common variations or synonyms"; it exceeds score 2 because "framing" is a genuinely central natural term for this task.

3 / 5

Distinctiveness Conflict Risk

The reframing niche is clear and the triggers (defaulted framing, all-losing options, step/artifact asks without named outcomes) are specific enough to mostly distinguish it from general reasoning or planning skills — "mostly distinct; minor overlap risk with closely related skills". It is not score 5 because the description itself gives no contrast with neighboring skills (the judge/explain disambiguation lives in the body, and the rubric scores only what is stated), leaving minor overlap risk.

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/reframe/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.