Name: pypict-skill
Rating: 37.6 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

pypict-skill

Pairwise test generation

Quality

35%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/pypict-skill/SKILL.md

The canonical home for this skill is pypict-skill in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

22%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 near-empty stub: it restates the description, gives no actionable guidance or workflow, and delegates everything to an external repository link. It fails as a self-contained skill instruction set.

Suggestions

Add a concrete Quick Start with an executable pypict snippet (install command, parameter definition, test-case generation call).

Inline the actual instructions from the source repository so the skill is usable without an external round-trip, or create local reference files (e.g. references/USAGE.md) and link them one level deep.

Define a short workflow with a validation step, e.g. define parameters → generate pairwise set → verify coverage of every parameter pair.

Dimension	Reasoning	Score
Conciseness	The body is short and does not over-explain concepts Claude knows, but it spends tokens on circular filler like "This skill provides guidance and patterns for pairwise test generation" that adds no information. It is not a 4+ because the sentences that exist do not earn their place.	3 / 5
Actionability	There is no concrete code, command, API, or executable guidance — only "provides guidance and patterns" which describes rather than instructs. This matches the entirely-vague/abstract anchor and cannot rise above it.	1 / 5
Workflow Clarity	No steps or sequence are given for the pairwise-generation process (define parameters, run tool, verify output). The simple-skill exception does not apply because the single action is not stated unambiguously, so this stays at the missing-steps anchor.	1 / 5
Progressive Disclosure	Sections (Overview, When to Use, Instructions) and a clearly signaled external link exist, but there is no real overview content to disclose and the actual instructions are offloaded to an external GitHub URL rather than one-level-deep local bundle files. It is not a 2 because some structure and a visible reference are present; not a 4 because the SKILL.md itself carries no useful overview.	3 / 5
	Total	8 / 20 Passed

Description

48%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 a terse domain label that conveys what the skill does but provides no concrete actions, no use-when trigger guidance, and no synonyms. It is distinguishable but underspecified relative to the good examples.

Suggestions

Add concrete actions, e.g. "Generate pairwise test cases from parameter sets; output combinatorial test suites."

Append an explicit trigger clause: "Use when the user asks for pairwise/combinatorial/all-pairs test generation or needs to reduce test combinations."

Include natural synonyms and file/CLI hints (all-pairs, n-wise, combinatorial testing) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Pairwise test generation" names the domain but gives no concrete actions, matching the anchor that names a domain with minimal/generic actions. It is not a 1 (entirely vague) since it specifies a real domain, but lacks the multiple concrete actions needed for 3+.	2 / 5
Completeness	It conveys a clear-enough 'what' (generates pairwise tests) but has no 'when'/Use-when clause, so it is capped at 3 per the missing-trigger-guidance rule. It is not a 2 because the 'what' is more precise than the vague one-word examples in anchor 2.	3 / 5
Trigger Term Quality	"pairwise" and "test generation" are natural terms a user might say, but no synonyms or variations (combinatorial testing, all-pairs, n-wise, parameter combinations) are present. It is above 2 (which expects only generic keywords) but below 4 (which expects good coverage with few gaps).	3 / 5
Distinctiveness Conflict Risk	"Pairwise test generation" targets a fairly distinct niche with low conflict risk versus unrelated skills, but lacks explicit trigger phrases that would lock in the niche. It is not a 5 because anchor 5 expects clear distinct triggers that this description omits.	4 / 5
	Total	12 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/pypict-skill/SKILL.md
Commit: 57c135b

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.