CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

toml

Create and review TOML configuration with strict typing and predictable structure. Use when editing tool configuration files that require schema-safe TOML.

Quality

72%

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/agent-ops/toml/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A lean, well-structured instruction-only skill with a clear procedure, explicit fail-fast validation gate, and exemplary progressive disclosure to a verified reference file. Its weaknesses are verbatim duplication of inputs/deliverables across three sections and the absence of any concrete validation command or TOML example.

Suggestions

Remove the "Inputs:" and "Deliverables" bullets from the "When to use" section since the "Required inputs" and "Deliverables" sections already state them, and consider dropping the 13-item TOC for a ~90-line body.

Make the Validation section executable by naming actual commands, e.g. `python -c "import tomllib,pathlib; tomllib.load(pathlib.Path(f).read_bytes())"` or `taplo check <file>`, instead of "Run the relevant parser/schema/tool checks".

Add a fix-and-revalidate loop to the Validation section (on failure: fix, re-run the same check, only then close out) to complete the feedback loop the fail-fast rule currently stops short of.

DimensionReasoningScore

Conciseness

The body is short and rule-dense, but the "When to use" section ("Inputs: target files, owning tool, expected key paths..." / "Deliver valid TOML with minimal key-path churn...") duplicates the "Required inputs" and "Deliverables" sections almost verbatim, and a 13-item TOC plus a one-line "Philosophy" section add padding that could be tightened. It is not a 2 because nothing explains concepts Claude already knows and the rules themselves are terse.

3 / 5

Actionability

Editing rules are concrete ("Do not mix inline tables and expanded tables for the same object path", "Quoting numeric values can silently change type semantics"), but there is no executable artifact anywhere: "Run the relevant parser/schema/tool checks" never names a parser or command (e.g. tomllib, taplo), and no TOML snippet illustrates the rules. This lands between the high-level-hints and pseudocode anchors, closer to 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

"1. Confirm the consumer schema and current key paths. 2. Make the smallest compatible edit. 3. Validate before closeout" is a clear sequence with an explicit validation checkpoint reinforced by the Validation section's fail-fast rule. It is not a 5 because there is no fix-and-revalidate feedback loop and the validation step itself lacks a concrete command.

4 / 5

Progressive Disclosure

The body is a concise, well-sectioned overview (TOC, clear headers) that delegates spec-level validity detail to a single one-level-deep, real bundle file ("Deep guidance: references/deep-guidance.md", verified present in references/), and that file's own "Read when" line signals its purpose. Content is appropriately split and navigation is easy, matching the top anchor.

5 / 5

Total

15

/

20

Passed

Description

70%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 solid description with a clear what, an explicit "Use when" clause, and a well-defined TOML niche. Its main weaknesses are limited action coverage (only create and review) and a trigger clause lacking synonyms and file extensions.

Suggestions

Add one or two more concrete actions to the what clause, e.g. "Create, review, and validate TOML configuration ... and diagnose parser errors".

Broaden the when clause with natural trigger phrases and the file extension, e.g. "Use when editing .toml files such as pyproject.toml or Cargo.toml, or when the user mentions TOML or schema-safe config".

DimensionReasoningScore

Specificity

"Create and review TOML configuration" names the domain with two concrete actions, matching the anchor for 1-2 actions that are not comprehensive. It is below the several-actions anchor because no other capabilities (validate, migrate, debug parse errors) are listed.

3 / 5

Completeness

The what is clear ("Create and review TOML configuration with strict typing and predictable structure") and the when is explicit ("Use when editing tool configuration files that require schema-safe TOML"), so both are present. It is not a 5 because the when clause is a single condition without concrete trigger phrases or synonyms (no mention of TOML files or .toml).

4 / 5

Trigger Term Quality

"TOML configuration", "tool configuration files", "schema-safe TOML", and "editing" give good natural keyword coverage. It falls short of the comprehensive anchor because the ".toml" extension and common user phrasings (e.g. named config files like pyproject.toml) are missing.

4 / 5

Distinctiveness Conflict Risk

"TOML" and "schema-safe TOML" pin a clear niche distinct from JSON/YAML skills, and a sibling yaml skill covering similar config-review ground creates only minor overlap risk (a generic "fix my config" request could match either).

4 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Skills/agent-ops/toml/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.