CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

snapshot-skill

Exercise project skill discovery and loading in snapshot tests.

Quality

56%

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/snapshot-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

37%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 lean but nearly empty of substance: it defers to 'snapshot-only instructions' that are never provided and tells Claude to resolve referenced resources without naming any. As written, a consumer of this skill cannot determine what to actually do. It needs its actual snapshot-test instructions spelled out.

Suggestions

Replace 'Follow these snapshot-only instructions' with the actual instructions: the concrete steps or commands the snapshot tests should perform (e.g., how to discover skills, what to load, what to assert).

Either list the specific referenced resource paths to resolve relative to the skill directory, or delete the 'Resolve referenced resources' line since no reference files exist in the bundle.

Organize the body into at least a minimal section header structure (e.g., '## Instructions') so the content is clearly delineated once real guidance is added.

DimensionReasoningScore

Conciseness

The two-line body contains zero padding, zero explanations of concepts Claude already knows, and no filler — every token present is directive. Not 4: there are no instances of over-explanation at all to trim.

5 / 5

Actionability

'Follow these snapshot-only instructions' directs Claude to instructions that are never stated anywhere in the body; no concrete code, commands, or specific steps exist. Matches anchor 1 ('entirely vague or abstract; only describes rather than instructs'). Not 2: even a high-level hint of specific executable steps is missing.

1 / 5

Workflow Clarity

No steps or sequence of any kind are present; the only quasi-directive ('Resolve referenced resources relative to this skill directory') points at resources that are not identified. The simple-skill exception does not apply because the single action is not unambiguous — the 'snapshot-only instructions' it says to follow do not exist in the file. Not 2: there is not even a rough sequence with gaps.

1 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist), so the 5-level would require well-organized sections — but the body has no sections or headers, and it contains a dangling directive about 'referenced resources' when none are referenced. Not 4/5: no organization to speak of and a reference pointer with no target; not 2: nothing is inlined that belongs in a separate file, and no deeply nested references exist.

3 / 5

Total

10

/

20

Passed

Description

53%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 and names a specific niche (snapshot testing of skill discovery/loading), but it reads more like a fixture label than a capability description: it lacks any 'Use when...' trigger guidance and offers only two thin actions. It would rarely be selected naturally because no trigger phrases are provided.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running or updating the snapshot test suite for project skill discovery and loading.'

Enumerate the concrete capabilities, e.g. 'Exercises project skill discovery, frontmatter parsing, and bundle loading in snapshot tests.'

Include natural keyword variations users would type ('snapshot tests', 'skill discovery tests', 'SKILL.md loading') to improve trigger matching.

DimensionReasoningScore

Specificity

The description names its domain ('snapshot tests') and two actions ('project skill discovery and loading'), which is more than the minimal/generic level of 'Processes PDF files' but far short of the several comprehensive actions of a 4 or 5. Not 4: only two thin actions are listed; not 2: the domain is named and the actions, while sparse, are stated.

3 / 5

Completeness

The 'what' is stated ('Exercise project skill discovery and loading in snapshot tests') but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4: the 'when' is entirely absent rather than merely imprecise; not 2: the 'what' is clear, not vague.

3 / 5

Trigger Term Quality

'snapshot tests' is a relevant keyword a maintainer of this test suite might naturally say, but there are no variations or synonyms ('skill discovery', 'skill loading', 'SKILL.md tests') to broaden matching. Not 4: coverage is a single term with several natural phrases missing; not 2: it is more specific than the purely generic 'Works with files'.

3 / 5

Distinctiveness Conflict Risk

The 'snapshot tests' niche is fairly distinct and unlikely to collide with general skills, though adjacent testing skills could overlap. Not 5: the description is too terse to establish a clearly staked-out niche with distinct triggers; not 3: 'snapshot tests' is more specific than the broadly overlapping 'Works with document files'.

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

river666/deepseek-harness-enterprise

Path

examples/acp-agent/tests/snapshots/skill-load/workspace/.dsh/skills/snapshot-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.