CtrlK
BlogDocsLog inGet started
Tessl Logo

partial-package-example

Fixture for truncated package review. Invoke only in skill-reviewer calibration.

36

Quality

32%

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/public/skill-reviewer/evals/fixtures/partial-package/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

40%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 content is a near-empty stub: one vague instruction that depends on a reference file which is absent from the bundle. It is token-efficient but lacks actionable guidance, a real workflow, and valid progressive-disclosure structure.

Suggestions

Add the missing references/large-reference.md file or remove the dangling reference so the one navigation pointer actually resolves.

Replace the vague 'before making a decision' directive with concrete, executable steps or a minimal code/command example.

Provide at least a basic sequenced workflow with a validation checkpoint so a reader knows how to act, not just what to read.

DimensionReasoningScore

Conciseness

The body is a single terse instruction with no padding or over-explanation, fitting the efficient anchor; it is not a 5 only because the brevity leaves the actual task underspecified rather than cleanly assumed.

4 / 5

Actionability

"Read references/large-reference.md before making a decision" is a high-level hint with no concrete steps, and the referenced file does not exist, leaving no executable guidance.

2 / 5

Workflow Clarity

No sequenced steps or validation checkpoints are present, only a rough single-action directive; this fits the rough-sequence-but-gaps anchor rather than the incoherent level 1 because one action is named.

2 / 5

Progressive Disclosure

The body points to references/large-reference.md, but no references/ directory exists, so the reference is a broken, buried pointer with minimal structure, fitting the minimal-structure anchor.

2 / 5

Total

10

/

20

Passed

Description

25%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 functions as an internal fixture label rather than a user-facing capability statement: it names a niche domain but provides no concrete actions, natural trigger terms, or an explicit Use-when clause. Its one strength is being narrowly scoped, which keeps conflict risk low.

Suggestions

Replace the fixture-label framing with concrete actions a user would recognize (e.g., 'Reviews partial skill packages and reports missing bundle files').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say, instead of internal jargon like 'skill-reviewer calibration'.

Include file extensions or synonyms (e.g., 'SKILL.md', 'bundle files') to improve trigger term coverage.

DimensionReasoningScore

Specificity

The phrase "truncated package review" names a domain but offers no concrete actions, matching the anchor for naming a domain with minimal or generic actions; it is not a 3 because no concrete capabilities are listed.

2 / 5

Completeness

"Fixture for truncated package review" gives only a vague what and "Invoke only in skill-reviewer calibration" a weak implied when with no explicit "Use when..." clause, capping it below a clear-what level 3.

2 / 5

Trigger Term Quality

"skill-reviewer calibration" and "truncated package review" are internal jargon a user would never naturally say, matching the no-natural-keywords anchor; no synonyms or file extensions appear.

1 / 5

Distinctiveness Conflict Risk

The calibration-only framing is a narrow niche unlikely to fire for unrelated skills, fitting mostly-distinct with minor overlap risk; it is not a 5 because no concrete trigger phrases distinguish it further.

4 / 5

Total

9

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
bytedance/deer-flow
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.