rhetoric

Toulmin argumentation engine — symbolic validation of argument structure, inferential integrity, and audience-calibrated delivery.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./rhetoric/SKILL.md

Quality

Content

71%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 concise, actionable, and clearly structured with executable command examples and a tabulated validation pipeline, but it suffers from a broken reference to a non-existent constitution.md and lacks a documented output/error-handling loop.

Suggestions

Add the missing constitution.md file (or remove the reference) so the promised '6 inviolable rules' are actually reachable — currently the only one-level-deep reference is a dead link.

Show the expected graph.json schema for the `validate` command, either inline or via a referenced file, so users can prepare a valid input.

Document what the commands return and a brief error-recovery step (e.g. how to interpret a failed pass and re-run) to close the workflow checkpoint gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized — overview, command table, validation-passes table, credentials, synergies — with no padding or explanation of concepts Claude already knows; the only minor flourish is the Archimedes epigraph, which keeps it just below the every-token-earns-its-place anchor.	4 / 5
Actionability	Provides copy-paste-ready bash commands with real arguments and flags for plan, validate, and demo, but the validate/demo examples omit the expected graph.json shape, a minor gap against the fully-executable-common-cases anchor.	4 / 5
Workflow Clarity	The engine's four validation passes are explicitly tabulated and the plan flow (decompose -> validate -> strategy -> analogy) is sequenced, but there is no documented user-facing error-recovery or output-verification loop, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	Sections are well-organized and the constitution reference is clearly signaled, but the referenced [constitution.md](constitution.md) does not exist in the bundle, so the one outbound reference points to nothing and the '6 inviolable rules' content is unreachable.	3 / 5
	Total	15 / 20 Passed

Description

53%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 clearly identifies a distinct niche and several capabilities, but it is written in academic jargon without natural trigger phrases and lacks any "Use when" guidance, leaving a user unsure when to invoke it.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when analyzing, validating, or strengthening an argument, or when the user mentions reasoning, logic, Toulmin, or argument structure.'

Replace abstract terms ('inferential integrity', 'audience-calibrated delivery') with plainer actions a user would recognize ('detects fallacies', 'checks evidence', 'tailors delivery to the audience').

Include the keyword 'Toulmin' and natural synonyms like 'argument', 'reasoning', 'fallacy' so the skill surfaces for everyday phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ("Toulmin argumentation engine") and three capabilities ("symbolic validation of argument structure, inferential integrity, and audience-calibrated delivery"), but the actions are abstract/academic rather than concrete executable operations, fitting the 1-2 concrete-actions anchor rather than the several-specific-actions anchor.	3 / 5
Completeness	Provides a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ("argumentation", "argument structure", "validation") but misses natural phrases a user would actually say (e.g. "check my reasoning", "is my argument sound", "Toulmin"), matching the some-relevant-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	"Toulmin argumentation engine" is a clear niche unlikely to trigger for unrelated skills; it is mostly distinct with only minor overlap risk, though the missing explicit triggers keep it just below the clear-distinct-triggers anchor.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Raudbjorn/cognitive-construct
Path: rhetoric/SKILL.md
Commit: 319f646

Reviewed: 6 days 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.