CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minimal-skill

Minimal example skill for plugin-eval tests. Use when the user wants a compact demonstration of a well-structured skill.

Quality

73%

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 ./plugins/plugin-eval/fixtures/minimal-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 an exemplar of token efficiency and correct progressive disclosure for a minimal skill: terse, well-sectioned, and pointing to a real one-level-deep reference file. Its only real weakness is actionability — the workflow steps are generic and would leave an executor guessing about the target file and the expected shape of the summary.

Suggestions

Make the workflow steps specific: name the target file (e.g. "Read the SKILL.md under evaluation") and what the summary should cover (sections, frontmatter fields, reference layout).

Annotate the reference with its purpose, e.g. "- `references/details.md` — deferred supporting context, load only if deeper detail is required," instead of a bare path.

Add a lightweight completion check (e.g. "the summary is done when structure, frontmatter, and references are all accounted for") to give the workflow a validation checkpoint.

DimensionReasoningScore

Conciseness

The body is ~13 lean lines: a one-sentence purpose statement ("Use this fixture to verify that skill evaluation works on a small but valid example"), three terse workflow steps, and a single reference path. Nothing explains concepts Claude already knows and every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

The steps "Read the target file" / "Summarize the important structure" form a real ordered procedure but omit key specifics — which target file, what counts as important structure, and what the summary should contain. Concrete-but-incomplete guidance fits the middle anchor, above high-level hints only and below mostly-executable guidance.

3 / 5

Workflow Clarity

The three-step workflow is clearly and correctly sequenced (read, summarize, defer details), and no destructive or batch operations exist, so no validation cap applies. It stays below the top anchor because the steps carry no checkpoints or specifics (e.g., how to know the summary is sufficient), fitting the clear-sequence-with-minor-gaps anchor.

4 / 5

Progressive Disclosure

Scored against the actual bundle: `references/details.md` exists, is exactly one level deep, and is listed under a dedicated "## Reference" section, with nothing inlined that belongs in a separate file. It falls just below the top anchor because the reference is a bare path with no annotation of what it contains, so it is not fully "well-signaled".

4 / 5

Total

16

/

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 is concise, third-person, and honest about its niche as a test fixture, with an explicit "Use when" clause. Its main weaknesses are low action specificity (it describes what it is, not what it does), a circular trigger clause, and missing natural synonym terms users would actually say.

Suggestions

Replace the circular trigger with concrete phrases a user would naturally say, e.g. "Use when the user asks for an example skill, demo skill, or test fixture for skill evaluation."

State the skill's concrete actions rather than its identity, e.g. "Provides a compact, well-structured SKILL.md template with a deferred reference file for testing skill evaluation pipelines."

Add natural synonyms and file-oriented terms ("example skill", "fixture", "boilerplate") to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description names a concrete domain ("Minimal example skill for plugin-eval tests") but lists no concrete actions — the capability is only "a compact demonstration of a well-structured skill". This matches the anchor for naming the domain with minimal or generic actions.

2 / 5

Completeness

Both parts are explicitly present: what ("Minimal example skill for plugin-eval tests") and when ("Use when the user wants a compact demonstration of a well-structured skill"). The "when" clause is explicit but circular — it restates the what rather than giving concrete trigger phrases — so it sits below the top anchor but above a merely implied when.

4 / 5

Trigger Term Quality

"Use when the user wants a compact demonstration" and "plugin-eval tests" provide some relevant keywords, but common natural variations users would say ("example skill", "demo", "test fixture", "template") are missing. Some relevant keywords without synonym coverage fits the middle anchor.

3 / 5

Distinctiveness Conflict Risk

The plugin-eval test fixture niche is clear and largely distinct, but the trigger "wants a compact demonstration of a well-structured skill" could also fire on genuine skill-authoring or skill-structure requests, creating minor overlap risk. Third-person voice is used correctly, so no penalty applies.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

openai/plugins

Path

plugins/plugin-eval/fixtures/minimal-skill/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.