CtrlK
BlogDocsLog inGet started
Tessl Logo

wtf

Explain the last message, or a supplied file, link, or passage, in plain language a person follows on the first read. Use when the user invokes wtf because they did not follow something. Use ce-explain to investigate how or why code works, and ce-noslop to rewrite prose.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is wtf in EveryInc/compound-engineering-plugin

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 exemplary lean instruction-only skill: terse, directive, and self-contained, with a clear target-selection workflow and a testable completion criterion. The single improvement would be a brief example showing what a good explanation looks like.

Suggestions

Add a one-or-two-line example of a well-formed explanation (source sentence followed by the two-sentence plain-language version) to make the output shape concrete as well as the rules.

DimensionReasoningScore

Conciseness

Every line is directive ("Open with the point in one or two sentences... Write no preamble and no apology", "If the target is still unclear, ask one short question instead of guessing"); there is zero explanation of concepts Claude already knows and no padding. Matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: a decision table for targets, a defined fallback (ask one short question), an ordered structure (point first, then implications), and a checkable Done criterion. Not 5 because no worked example of a good explanation is provided, which is a minor gap against 'specific examples cover the common cases'; not 3 because nothing is vague or pseudocode-like.

4 / 5

Workflow Clarity

A simple single-purpose skill where the action is unambiguous: the 'What to explain' section sequences target identification with an explicit fallback, and the **Done:** line acts as an end-state checkpoint. The simple-skill exception applies (no destructive or batch operation, so no validation cap), so the unambiguous single action scores 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed, and the body is organized into clear sections (What to explain, How to explain) with a bolded Done criterion. Per the under-50-lines exception, well-organized sections alone merit 5; there are no buried or nested references.

5 / 5

Total

19

/

20

Passed

Description

87%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: it states what the skill does with concrete enumerated targets, gives an explicit 'Use when' trigger, and cleanly boundaries two neighboring skills. The only gap is modest synonym coverage in the trigger phrasing.

Suggestions

Broaden the trigger phrasing with natural synonyms users say in this moment, e.g. "Use when the user invokes wtf because they did not follow, are confused by, or lost the thread of something."

Name one or two more concrete explain-targets users would mention (e.g., a command's output, an error message) to lift specificity from several-actions to comprehensive coverage.

DimensionReasoningScore

Specificity

Enumerates concrete targets ("the last message, or a supplied file, link, or passage") and a precise, measurable outcome ("plain language a person follows on the first read"), matching the 'several specific actions; minor gaps' anchor. Not 5 because it describes one core action applied to enumerated variants rather than multiple distinct concrete capabilities; not 3 because the targets and outcome standard are specific and largely comprehensive for this domain.

4 / 5

Completeness

Explicitly answers what ("Explain the last message, or a supplied file, link, or passage, in plain language a person follows on the first read") and when ("Use when the user invokes wtf because they did not follow something") with a concrete trigger phrase, matching the top anchor exactly.

5 / 5

Trigger Term Quality

The natural trigger phrase "Use when the user invokes wtf because they did not follow something" plus "plain language" gives good keyword coverage a user would actually say. Not 5 because common synonyms (e.g., "confused", "what does this mean", "lost me") are absent; not 3 because the core natural phrasing around not-following something is explicit and well-targeted.

4 / 5

Distinctiveness Conflict Risk

Clear niche (plain-language explanation on user confusion) with minimal conflict risk: it explicitly partitions adjacent skills ("Use ce-explain to investigate how or why code works, and ce-noslop to rewrite prose"), and the skill is user-invocation-only per frontmatter, so it cannot fire on the wrong skill.

5 / 5

Total

18

/

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.

Validation — 15 / 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
crdant/compound-engineering-plugin
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.