CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

model-only-skill

Prove user-disabled skills remain available to the model.

Quality

50%

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 ./examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/model-only-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 but substantively empty: one sentence that points to 'model-only snapshot instructions' that are neither in the body nor in any bundle file. There is nothing actionable, no workflow, and no navigation structure — it functions as a placeholder rather than skill content.

Suggestions

Either inline the actual 'model-only snapshot instructions' or place them in a referenced file (e.g. references/snapshot.md) with an explicit link — the current pointer resolves to nothing.

Add at least one concrete, executable instruction (a command or specific check to run) so the skill gives the model something to act on rather than a circular directive.

Add a minimal section header (e.g. '## Instructions') so even a short body has clear structure, and state any validation step for whatever the snapshot process involves.

DimensionReasoningScore

Conciseness

The body is a single line — "Follow these model-only snapshot instructions." — with zero padding and no explanation of concepts Claude already knows. It fully matches 'lean and efficient; every token earns its place'.

5 / 5

Actionability

The body provides no concrete code, commands, or specific guidance; 'Follow these model-only snapshot instructions' is a circular pointer to instructions that exist nowhere in the body or any bundle file. This matches 'entirely vague or abstract; only describes rather than instructs'.

1 / 5

Workflow Clarity

No steps, sequence, or checkpoints of any kind are present — matching 'steps missing or incoherent'. Even under the simple-skill exception, a single unambiguous action could score 5, but this action is ambiguous because the referenced 'snapshot instructions' are never provided.

1 / 5

Progressive Disclosure

There is no structure (no sections or headers) and the phrase 'these model-only snapshot instructions' dangles — no bundle files exist, so the implied reference points nowhere. This matches 'minimal structure... or references are buried' rather than anchor 3, which presumes at least some organizing structure.

2 / 5

Total

9

/

20

Passed

Description

41%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 states a clear, distinct purpose but is a single terse claim with no concrete actions, no natural trigger terms, and no 'Use when' guidance. It reads as a test artifact rather than a skill description that would help a user or Claude decide when to invoke it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when testing whether user-disabled skills remain visible to the model' — this alone would raise completeness from 3 toward 4-5.

Replace the abstract verb 'Prove' with the concrete actions the skill performs, e.g. 'Verify that skills with user-invocable: false still load and execute for the model'.

Include the natural terms a user would say (e.g. 'disabled skill', 'hidden skill', 'model-only skill', 'user-invocable false') so the description surfaces on relevant requests.

DimensionReasoningScore

Specificity

The description names a domain ("user-disabled skills remain available to the model") but the only action is the generic verb "Prove", with no concrete capabilities listed — matching 'names the domain but actions are minimal or generic'. It is not entirely vague (not a 1), but it does not list the 1-2 concrete actions needed for a 3.

2 / 5

Completeness

A clear 'what' is present ("Prove user-disabled skills remain available to the model") but the 'when' is entirely missing — matching anchor 3, and per guidelines the missing 'Use when...' clause caps completeness at 3. It is not a 2 because the 'what' is stated clearly, not vaguely; not a 4 because no trigger guidance exists at all.

3 / 5

Trigger Term Quality

Only technical phrasing like "user-disabled skills" and "available to the model" appears; there are one or two quasi-natural keywords but none of the natural phrases a user would actually say when needing this skill, and no synonyms or trigger guidance. It sits just above anchor 1 (pure jargon) but well below the good keyword coverage of a 4.

2 / 5

Distinctiveness Conflict Risk

The niche (model-only availability of user-disabled skills) is quite distinct from ordinary task skills, creating only minor overlap risk with closely related skill-configuration skills — matching anchor 4. It is not a 5 because there are no explicit trigger phrases to lock in the distinction.

4 / 5

Total

11

/

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

river666/deepseek-harness-enterprise

Path

examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/model-only-skill/SKILL.md

Revision

54e2a39

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill