CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

antithesis-review-inputs

Review a workload's input generation for state space exploration: how well it uses randomness to drive the system under test into diverse regions of behavior.

Quality

73%

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 ./antithesis-review-inputs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-structured, actionable playbook: a clear six-step workflow with concrete review questions, tiering rules, a defined report format, and disciplined scope boundaries. Its one real reference is properly disclosed and carries the detailed catalog, leaving the overview lean. The main improvement space is minor redundancy in the framing/tone prose and the absence of a sample report.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence: workflow steps are terse bullet questions with no basic-concept explanation. Minor trimming opportunities exist — the 'a workload exhibiting anti-patterns may still be productive/finding bugs' framing appears nearly verbatim in both Purpose and Tone, and the Tone section spans three paragraphs where one would do. Matches 'efficient; minor instances of over-explanation that could be trimmed'.

4 / 5

Actionability

Concrete, executable guidance for an instruction-only skill: specific locations to check ('antithesis/test/'), precise structural questions (fixed vs per-run subsetting, hardcoded bounds, payload-size spread), tier definitions with examples, and a good-vs-better finding example. Not 5 because there is no sample report and the examples don't cover the common end-to-end output case.

4 / 5

Workflow Clarity

A clearly sequenced six-step workflow with most checkpoints present: 'If the workload location isn't obvious, ask the user' (error recovery), 'When you can't assess a finding's severity... say so' (domain-knowledge guard), and the report's model-correction preamble. Not 5 because verification of the reviewer's workload model happens only inside the final report rather than as a mid-process validation step.

4 / 5

Progressive Disclosure

Clear overview with a single, well-signaled, one-level-deep reference: the body instructs reading 'references/anti-patterns.md' before examining any workload, describes what it contains, and a closing Reference Files table states when to read it; the file exists and holds the bulk catalog (338 lines) appropriately split from the overview. Matches the top anchor.

5 / 5

Total

17

/

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 communicates a specific, well-scoped capability but reads as half-finished: it answers 'what' clearly while omitting 'when' entirely, and it lacks the most natural trigger term (Antithesis) its target users would say. It is distinct within a skill library yet generic within its own testing domain.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when an Antithesis workload isn't finding bugs and you want to assess whether input generation is limiting exploration, or as a periodic health check on workloads.'

Include natural trigger terms users would actually say: 'Antithesis', 'workload', 'fuzzing', 'input generation', 'not finding bugs', 'state space'.

Consider naming the concrete outputs of the skill (a tiered findings report on unexplored state space) to strengthen the what-side beyond a single 'review' action.

DimensionReasoningScore

Specificity

Names the domain clearly ('workload's input generation', 'state space exploration') and one concrete action ('Review... how well it uses randomness to drive the system under test into diverse regions of behavior'), but does not list several distinct actions, matching the '1-2 concrete actions, not comprehensive' anchor. Not 4 because the single review action is elaborated rather than complemented by additional specific capabilities.

3 / 5

Completeness

The 'what' is clear (review input generation quality for state space exploration), but there is no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the 'what' half is specific and concrete.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'workload', 'input generation', 'randomness', and 'state space', but omits the most natural user phrasings — 'Antithesis' (the tool this skill is built around) never appears, nor variants like 'fuzzing' or 'not finding bugs'. Matches 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'Review a workload's input generation for state space exploration' carves a distinct niche with low conflict risk against unrelated skills. Not 5 because without the tool name ('Antithesis') it could mildly overlap with generic testing or fuzzing review skills.

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

antithesishq/antithesis-skills

Path

antithesis-review-inputs/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.