CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rich-modern

Use when you need a full-spec example with rich frontmatter, dynamic injection and substitutions.

Quality

55%

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/skills/rich-modern/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 admirably lean and uses dynamic injection appropriately, but its guidance is incomplete: the helper script is never given as an executable command, the report output is unspecified, and the central reference.md link points to a file that does not exist. The skeleton is good; the executable details are missing.

Suggestions

Give the exact helper invocation, e.g. `bash ${CLAUDE_SKILL_DIR}/scripts/helper.sh ${target:-.}`, instead of the vague 'Run the helper script using ${CLAUDE_SKILL_DIR}'.

Fix or remove the broken reference.md link — either add the file to the bundle or drop the reference and inline the essential material.

Specify what the final report should contain (e.g. sections for tree structure, key files, and observations) so 'Produce a report' is unambiguous.

DimensionReasoningScore

Conciseness

The ~12-line body contains zero padding and no explanations of concepts Claude already knows; the heading, target line, injected command, reference, and three steps all earn their tokens, matching the 'lean and efficient' anchor. It avoids the anchor-4 territory because there is no over-explanation to trim at all.

5 / 5

Actionability

The injected `find ${target:-.} -type f -maxdepth 2 | head -20` command is executable, but 'Run the helper script using ${CLAUDE_SKILL_DIR}' omits the actual command, 'Produce a report' specifies no output format, and the referenced reference.md does not exist — matching anchor 3's 'some concrete guidance but incomplete; missing key details'. It falls short of 4 because two of three steps cannot be executed as written.

3 / 5

Workflow Clarity

A numbered 1-2-3 sequence is present, but the steps are underspecified (no helper invocation command, no report structure) and step 1 points to a nonexistent file, matching anchor 3's 'steps listed but gaps'. This is a non-destructive read/report skill so the validation cap does not apply, but it also does not qualify for the simple-skill exception because the steps are not unambiguous.

3 / 5

Progressive Disclosure

References are one level deep and clearly signaled ('[reference.md](reference.md) and the helper in scripts/'), but the reference.md link is broken — the file does not exist in the bundle — and the body has minimal section organization, matching anchor 3's 'some structure but could be better organized'. It is above anchor 2 because nothing is inlined that belongs in a separate file and references are not buried.

3 / 5

Total

14

/

20

Passed

Description

28%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 provides explicit trigger guidance but almost nothing else: no concrete actions, no natural user phrasings, and only a vague implied capability. It reads as meta-description of a fixture rather than a statement of what the skill does. It sits just above the level of pure fluff like 'Helps with documents'.

Suggestions

State the 'what' explicitly with concrete action verbs, e.g. 'Generates a repository visualization and structure report using an injected file-tree scan and a helper script.'

Replace jargon ('full-spec', 'dynamic injection and substitutions') with natural trigger phrases a user would actually say, such as 'visualize the repo', 'generate a structure map', or 'explore the project layout'.

Add distinguishing qualifiers that separate it from generic example/demo skills so it is unlikely to fire for unrelated requests.

DimensionReasoningScore

Specificity

The description names some concepts ('rich frontmatter, dynamic injection and substitutions') but contains no action verbs describing what the skill actually does, matching anchor 2's 'actions are minimal or generic'. It is above anchor 1 only because the named concepts are more concrete than pure abstraction like 'Helps with documents'.

2 / 5

Completeness

The description is solely a 'Use when you need...' clause with the 'what' only vaguely implied ('a full-spec example'), exactly matching anchor 2 ('only when is present without what'). It is not a 3 because there is no clear statement of capability, and not a 1 because explicit trigger guidance is present.

2 / 5

Trigger Term Quality

'full-spec', 'dynamic injection', and 'substitutions' are technical jargon a user would not naturally say; only 'example' and 'frontmatter' function as quasi-natural keywords, matching anchor 2 ('one or two generic keywords; missing the natural phrases users say'). It does not reach 3 because common user phrasings are entirely absent.

2 / 5

Distinctiveness Conflict Risk

The skill-authoring fixture niche ('full-spec example with rich frontmatter') is somewhat specific, but the generic word 'example' creates overlap risk with other example, demo, or skill-creation skills, matching anchor 3. It lacks the distinct trigger phrases needed for a 4.

3 / 5

Total

9

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

saif-shines/doraval

Path

test/fixtures/skills/rich-modern/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.