CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

c

Nested skill under packages/x/skills, used to test recursive discovery.

Quality

49%

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 ./test/fixtures/agentskills-repo/packages/x/skills/c/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%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 maximally concise and appropriately avoids progressive-disclosure overhead, but its single instruction is a placeholder that provides no actionable guidance. Whatever 'the nested thing' is, the skill never tells Claude how to do it.

Suggestions

Replace the placeholder 'Do the nested thing.' with a concrete, executable instruction or code/command showing exactly what action to perform.

Define what 'the nested thing' actually consists of — even for a simple skill, the single action must be unambiguous to score well on workflow clarity.

If the action involves any batch or destructive operation, add an explicit validation/verification step; otherwise a one-line confirmation of expected output would make the workflow complete.

DimensionReasoningScore

Conciseness

The body is two lines with zero padding, no explanation of concepts Claude already knows, and no filler — every token present is minimal. This matches the anchor for lean and efficient content.

5 / 5

Actionability

The single instruction is "Do the nested thing.", an entirely vague placeholder with no concrete code, commands, or specifics. This matches the lowest anchor of entirely vague or abstract guidance that describes rather than instructs.

1 / 5

Workflow Clarity

A single numbered step is nominally present but it is incoherent as an instruction and undefined, matching the anchor for a rough sequence that is poorly defined with validation absent. The simple-skill exception (score 5 for a single unambiguous action) does not apply because the action is ambiguous, and it cannot be 1 since a step structure does exist.

2 / 5

Progressive Disclosure

The skill is under 50 lines, no bundle files (references/, scripts/, assets/) exist, and no external references are needed, so per the simple-skill exception well-organized minimal structure earns the top score. The heading and single step are as organized as content this trivial can be.

5 / 5

Total

13

/

20

Passed

Description

21%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 reads as an internal test-fixture label rather than a capability description: it names its location and purpose but gives no concrete actions, no natural trigger terms, and no usage guidance. A user would never naturally invoke this skill based on what is written.

Suggestions

Add a 'Use when...' clause or equivalent explicit trigger guidance naming the natural phrases a user would say when they need this skill.

Replace the meta-purpose ('used to test recursive discovery') with 1-2 concrete actions describing what the skill actually does.

Include natural trigger keywords or synonyms (not just technical jargon like 'recursive discovery' or the packages/x/skills path) so the skill is discoverable and distinguishable from other test skills.

DimensionReasoningScore

Specificity

The description names its domain ("Nested skill under packages/x/skills", "used to test recursive discovery") but lists no concrete actions or capabilities, matching the anchor for naming the domain with minimal or generic actions. It is not pure abstract language (so not 1), and it lacks the 1-2 concrete actions needed for 3.

2 / 5

Completeness

It offers only a vague meta-purpose ("used to test recursive discovery") as the 'what' and contains no 'when' guidance at all, matching the anchor for a vague 'what' with no 'when'. The missing 'Use when...' clause also caps completeness at 3, and the vague 'what' places it below that.

2 / 5

Trigger Term Quality

Only technical jargon appears ("recursive discovery", "packages/x/skills"); there are no natural keywords or phrases a user would say when needing this skill. This matches the lowest anchor of only technical jargon or generic language.

1 / 5

Distinctiveness Conflict Risk

The niche (testing recursive discovery of nested skills) is somewhat specific, but the description provides no distinct natural trigger phrases, so it could still overlap with similar tooling/test skills. Not 4 because overlap risk with other test-related skills remains unaddressed.

3 / 5

Total

8

/

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

saif-shines/doraval

Path

test/fixtures/agentskills-repo/packages/x/skills/c/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.