explain

Explain Semantica reasoning, decision logic, and graph results with traceability, causal context, and human-readable rationale.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/explain/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized with concrete, API-specific code for both sub-commands, but the examples are not self-contained because key context and variables are left undefined.

Suggestions

Make code snippets copy-paste ready by showing how ctx and the key variables (decision_id, depth, reasoning_result) are obtained before they are used.

In the decision section, clarify when to use ctx.trace_decision_explainability versus ExplanationGenerator, since the two paths are presented without explicit sequencing.

Reconcile the CLI flag '--detail <level>' with the code's 'detail_level=detail' so the binding between the argument and the parameter is explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean: a one-line intro, two compact command sections each with a signature, short code, and expected output, with no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	Code uses real imports and APIs (ExplanationGenerator, ctx.trace_decision_explainability, ctx.get_causal_chain), but ctx and several variables (decision_id, depth, reasoning_result, detail) are undefined, so snippets are not copy-paste ready and miss key setup details.	2 / 3
Workflow Clarity	This is a simple read-only explanation skill with a clear two-command structure (decision vs graph), each showing the call and its expected output; no validation checkpoints are needed for non-destructive operations.	3 / 3
Progressive Disclosure	Under 50 lines with no bundle files present and no need for external references; the content is well-organized into clearly headed sections, satisfying the simple-skill allowance for a top score.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 and distinctively scoped to Semantica, but lacks an explicit 'Use when' trigger clause and natural user-facing phrasings, leaving the 'when to use' question only implied.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks why a Semantica decision was reached, wants a graph relationship traced, or needs causal reasoning explained.'

Include natural trigger terms a user would actually say ('why was this decision made', 'explain this graph connection', 'what caused this') alongside the technical vocabulary.

Trim jargon like 'traceability' and 'human-readable rationale' in favor of concrete verbs the user would recognize.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Explain Semantica reasoning, decision logic, and graph results') with specific qualifiers (traceability, causal context, human-readable rationale), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit 'Use when...' trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'Semantica reasoning', 'decision logic', and 'graph results' are relevant, but 'traceability', 'causal context', and 'human-readable rationale' lean technical and common user phrasings ('why was this decided', 'explain this connection') plus a 'Use when' clause are absent.	2 / 3
Distinctiveness Conflict Risk	Scoped tightly to Semantica reasoning/decision/graph explanations, giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: semantica-agi/semantica
Path: plugins/skills/explain/SKILL.md
Commit: 8406297

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

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.