CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

explain

Explain what was just implemented in this conversation in plain English for a junior dev, so the user can understand the full picture and make a decision. Default output is exactly two paragraphs; the argument "more" gives a longer, detailed version. Not for questions about how existing code works when nothing was changed in this conversation; answer those directly.

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 ./skills/explain/SKILL.md
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.

The body is a tight, unambiguous instruction contract for a simple skill: precise output format, per-argument behavior, edge cases, and tone rules, all within ~25 lines and with no unnecessary explanations. The only improvement is trimming the repeated junior-dev/plain-English framing stated in three places.

DimensionReasoningScore

Conciseness

Lean and well-structured with no over-explanation of known concepts, but the junior-dev/plain-English register is stated three times ("written for a junior developer who has not been following along", "Write as if to a capable junior dev", "Same plain-English, junior-dev register") and the intro paragraph overlaps the Output contract. Matches anchor 4's 'minor instances that could be trimmed'; the redundancy keeps it below anchor 5.

4 / 5

Actionability

The output contract is fully executable instruction guidance: "Exactly two paragraphs. Not one, not three. No headers, no bullet points", explicit per-paragraph content assignments, and per-argument behavior for "more", "<topic>", and "more <topic>". Covers all common cases including the nothing-changed edge case, so anchor 5 applies.

5 / 5

Workflow Clarity

Single-purpose skill with an unambiguous contract and explicit edge-case handling ("If nothing was built or changed and no topic was given, say so in one sentence"), so the simple-skill exception applies. No destructive or batch operations, so the validation cap is irrelevant.

5 / 5

Progressive Disclosure

Under 50 lines, no external references needed, and well-organized sections ("Output contract (default: no arguments)", "With arguments") with no bundle files to reference. Per the guideline, a short single-purpose skill with well-organized sections scores 5.

5 / 5

Total

19

/

20

Passed

Description

58%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 is specific, third-person, and communicates a clear output contract, but it lacks an explicit positive 'Use when...' trigger clause and natural trigger-phrase coverage, leaving the 'when' only weakly implied through a negative boundary. Adding when-to-use guidance with user-phrase triggers would raise completeness and trigger-term quality.

Suggestions

Add an explicit positive trigger clause, e.g. "Use when the user asks to explain or summarize what was just built/changed in this conversation" — the current 'when' is only implied by the negative "Not for questions..." clause.

Include natural user phrases as trigger terms ("explain what you just did", "summarize the change", "in plain English") so the description matches how users actually ask for this.

Mention the topic-scoping behavior ("<topic>: scope the explanation to a named change") in the description so capability coverage is comprehensive.

DimensionReasoningScore

Specificity

Names several concrete behaviors — "Explain what was just implemented in this conversation in plain English", "Default output is exactly two paragraphs", "the argument 'more' gives a longer, detailed version" — in third person, with minor coverage gaps (the topic argument is absent from the description). It exceeds anchor 3's 1-2 actions but isn't comprehensive enough for anchor 5.

4 / 5

Completeness

The 'what' is clear and specific, but the only when-guidance is the negative clause "Not for questions about how existing code works when nothing was changed in this conversation" — an exclusion rather than a 'Use when...' trigger, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains some genuinely natural terms ("Explain", "plain English", "more") but misses common variations users would say such as "what did you just do" or "summarize the change". Matches anchor 3's 'some relevant keywords but missing common variations', not 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"what was just implemented in this conversation" plus the explicit negative boundary carves out a mostly distinct niche with only minor overlap risk against generic explain/summarize skills. Lacks the distinct positive triggers of anchor 5.

4 / 5

Total

14

/

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

bezmoradi/knackpack

Path

skills/explain/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.