CtrlK
BlogDocsLog inGet started
Tessl Logo

sample-plugin

Phase 1 sample plugin synthesizing a SKILL.md frontmatter for backwards-compat tests.

48

Quality

52%

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 ./apps/daemon/tests/fixtures/plugin-fixtures/sample-plugin/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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 brief, well-organized, clearly sequenced simple workflow that fits the simple-skill exception for workflow clarity and progressive disclosure. Its weaknesses are undefined internal abstractions in the steps and fixture-meta context in the intro that slightly reduce actionability and conciseness.

Suggestions

Define or briefly exemplify 'discovery question form atom' and 'deck artifact' so the workflow steps are self-contained and actionable.

Trim the intro fixture-meta paragraph to only context that aids execution, improving token efficiency.

Optionally add a one-line expected output example for the deck artifact to lift actionability toward 3.

DimensionReasoningScore

Conciseness

The body is short and lean, but the intro paragraph ('This is the SKILL.md half of the Phase 1 e2e fixture... legacy compat tier') is fixture-meta context not needed to execute the workflow, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the every-token-earns-its-place anchor at 3.

2 / 3

Actionability

Steps name a concrete tool ('Use TodoWrite to plan the brief') but rely on undefined abstractions ('discovery question form atom', 'deck artifact') with no examples or commands, matching the 'some concrete guidance but incomplete; missing key details' anchor rather than the copy-paste-ready anchor at 3.

2 / 3

Workflow Clarity

The three steps (acknowledge, plan, emit) are in a clear, unambiguous sequence for a simple non-destructive task; the rubric's simple-skills note allows a 3 for short single-purpose workflows even without explicit validation checkpoints, and this is not a destructive/batch operation that would cap at 2.

3 / 3

Progressive Disclosure

The skill is under 50 lines, has no bundle files and no need for external references, and is organized into clear sections (# Sample Plugin, ## Workflow); the rubric's simple-skills note allows a 3 for well-organized short skills without external file references.

3 / 3

Total

10

/

12

Passed

Description

35%

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 names a concrete domain and action but is framed as internal test-fixture jargon rather than a user-facing capability, with no trigger guidance. It is distinguishable but not written to be triggered naturally by users.

Suggestions

Rewrite the description in user-facing terms that state the capability (e.g., 'Generates SKILL.md frontmatter for Open Design plugins') rather than describing the test fixture.

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, so the completeness dimension can reach 3.

Replace internal jargon ('Phase 1', 'backwards-compat tests') with natural trigger terms a user would actually say.

DimensionReasoningScore

Specificity

Quotes 'synthesizing a SKILL.md frontmatter' name a domain and a single concrete action, matching the anchor that names a domain and some actions but is not comprehensive; it does not list multiple specific actions, so it is not a 3, and it is not vague like 'Helps with documents', so it is above 1.

2 / 3

Completeness

It states a 'what' ('synthesizing a SKILL.md frontmatter') but provides no 'when'/'Use when' trigger guidance, which per the guidelines caps completeness at 2; it is above 1 because a what is present, but below 3 because when is entirely missing.

2 / 3

Trigger Term Quality

Terms like 'Phase 1 sample plugin', 'synthesizing', and 'backwards-compat tests' are internal/infra jargon a user would never naturally say when needing this skill, matching the 'no natural keywords; technical jargon' anchor rather than the partial-coverage anchor at 2.

1 / 3

Distinctiveness Conflict Risk

The niche (SKILL.md frontmatter synthesis for compat tests) is somewhat specific, but the non-natural triggers and generality of 'synthesizing' could overlap with other generation skills, matching the 'somewhat specific but could still overlap' anchor rather than the distinct-trigger anchor at 3.

2 / 3

Total

7

/

12

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.

Validation15 / 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
nexu-io/open-design
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.