CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rhetoric

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

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./rhetoric/SKILL.md
SKILL.md
Quality
Evals
Security

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 a lean, command-first reference with fully executable invocations and a well-organized structure, undermined by one navigation failure: the constitution.md link is dead, and the validate command's input format is undocumented. Fixing the reference and specifying the graph.json schema would lift it substantially.

Suggestions

Fix the broken reference: constitution.md does not exist in the bundle — either create it with the 6 inviolable rules or remove the Constitution section.

Document the graph.json schema expected by `validate` (inline example or a referenced file), since no format specification exists anywhere in the skill.

Trim the decorative Archimedes epigraph, which adds tokens without operational value.

DimensionReasoningScore

Conciseness

The body is efficient: commands are presented with minimal prose, the validation passes are a compact table, and credential requirements are stated in two lines without explaining concepts Claude already knows. Minor trimmable elements remain — the Archimedes epigraph is pure decoration and the Synergies section is tangential — fitting anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') rather than anchor 5's 'every token earns its place'.

4 / 5

Actionability

All three commands are given as full, copy-paste-ready invocations with realistic examples, documented options (--no-bridge, --contradict), and the API-key requirement is explicit. The gap keeping it below 5: the `validate` command's input is never specified — no example graph.json or pointer to its schema exists anywhere in the bundle — so a user cannot actually execute that command end-to-end. This matches anchor 4 ('concrete code or commands with minor gaps').

4 / 5

Workflow Clarity

Each command is a single unambiguous invocation with examples, and validation is built into the tool itself (the four passes are enumerated), so there are no risky manual multi-step sequences to sequence. However, minor gaps remain: the expected graph.json format for `validate` is undocumented and there is no guidance on interpreting or acting on the engine's output, which fits anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5.

4 / 5

Progressive Disclosure

Section structure is good and implementation code is correctly kept in the scripts/ bundle rather than inlined, but the body's only content reference — "See [constitution.md](constitution.md) for 6 inviolable rules" — points to a file that does not exist anywhere in the bundle, and there is no navigation into the actual bundle layout (scripts/toulmin/*.py). This fits anchor 3 ('some structure but could be better organized; references present but not clearly signaled') — the broken reference makes navigation fail at the one place it is attempted.

3 / 5

Total

15

/

20

Passed

Description

57%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 carves out a highly distinctive niche and states a clear 'what', but it is written in technical jargon, omits natural trigger terms users would actually say (fallacy, reasoning, persuasion), and completely lacks a 'when to use' clause. It reads more like a tagline than an invokable skill description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to validate, strengthen, or deconstruct an argument, check reasoning for fallacies, or plan how to present a case to an audience."

Replace jargon ("inferential integrity", "audience-calibrated delivery") with concrete verbs users recognize: "Decomposes arguments into Toulmin graphs (claim, data, warrant, backing), detects fallacies such as hasty generalization, and selects a delivery strategy based on the audience."

Include natural synonyms users would say — "fallacy", "fallacies", "reasoning", "persuasion", "argument" — so the description matches real user phrasing, not just Toulmin terminology.

DimensionReasoningScore

Specificity

The description names the domain ("Toulmin argumentation engine") and 1-2 semi-concrete actions ("symbolic validation of argument structure"), but the remaining phrases — "inferential integrity", "audience-calibrated delivery" — are abstract nominalizations rather than concrete actions, and major capabilities (decomposing arguments into Toulmin graphs, detecting specific fallacies) are absent. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'; it is not level 4 because it does not list several specific actions, and not level 2 because the domain and a concrete validation action are explicitly stated.

3 / 5

Completeness

The 'what' is stated clearly (validates argument structure, inferential integrity, delivery), but there is no 'Use when...' clause or any equivalent trigger guidance — the 'when' is entirely absent, not merely weakly implied. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3, matching the anchor 'Has a clear what but when is missing'.

3 / 5

Trigger Term Quality

Some relevant natural keywords are present ("argumentation", "argument structure", "validation", "delivery"), but common user phrasings like "fallacy", "fallacies", "reasoning", "logic", "persuasion", or "check my argument" are missing, and terms like "inferential integrity" are technical jargon users would not naturally say. This fits anchor 3 ('Some relevant keywords but missing common variations or synonyms'), below anchor 4's 'good keyword coverage with a few natural terms missing'.

3 / 5

Distinctiveness Conflict Risk

"Toulmin argumentation engine — symbolic validation of argument structure" occupies a clear niche (formal argument validation) with distinct trigger terms (Toulmin, argumentation) that virtually no other skill would claim, matching the anchor 'Clear niche with distinct triggers; minimal conflict risk'. Level 4 would require some overlap with closely related skills, which is not the case here.

5 / 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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

Raudbjorn/cognitive-construct

Path

rhetoric/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.