CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/test-case-ideation-from-story

Takes a user story or feature spec and emits a markdown test-case matrix - one row per case (id, title, precondition, steps, expected, tier) covering happy path, alternate paths, boundaries, and negative paths - before any test code is written. Output is the human-reviewable matrix that goes into TestRail / Qase / Xray. Emits the human-reviewable case matrix itself - not Gherkin scenarios written against locked acceptance criteria, and not executable test code. Use as the first artifact a manual tester or three-amigos session produces from a story, ahead of automation.

75

Quality

94%

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

Overview
Quality
Evals
Security
Files

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with a clear sequenced workflow and an explicit validation gate. Its only weakness is mild verbosity in the Overview and a statistic repeated across two sections.

Suggestions

Tighten the Overview framing (e.g. trim 'A user story is not a test plan. The three-amigos hand-off from product to QA needs an intermediate artifact…') so the section leads with what the matrix is and when to produce it.

Cite the PractiTest 70%/40.7% statistic once — either in Overview or in Anti-patterns — rather than restating it in both sections.

Consider collapsing the Hand-off targets and Limitations sections' overlapping cross-references (gherkin-from-stories, manual-test-script-author, ai-test-generator each appear in both) into one consolidated hand-off list.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes competence (ISTQB techniques are named and linked, not re-explained), but discursive framing ("A user story is not a test plan. The three-amigos hand-off…") and the PractiTest statistic repeated in both Overview and Anti-patterns add padding that could be tightened.

2 / 3

Actionability

Highly concrete: Step 1 enumerates exact fields with a halt rule, Step 2 gives a parameter-class table and boundary formula (min, min-1, max, max+1), Step 3 specifies required columns with a stable ID format, and a full five-row worked example plus tool-specific import endpoints make it copy-paste ready.

3 / 3

Workflow Clarity

A clearly sequenced four-step process with an explicit validation checkpoint ("If any of (1)–(5) is missing, stop and request clarification") and defined escalation/hand-off paths, giving a feedback loop for incomplete input.

3 / 3

Progressive Disclosure

No bundle files exist, so the single well-organized SKILL.md with clearly labeled sections (Overview, When to use, Steps 1–4, Anti-patterns, Limitations, Hand-off targets, References) and one-level-deep external URL references meets the bar for a self-contained skill.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what it produces, when to use it, and how it differs from neighboring automation skills. Trigger terms are natural to the QA domain and the what/when pair is explicit.

DimensionReasoningScore

Specificity

Lists concrete actions with specific output fields ("id, title, precondition, steps, expected, tier") and enumerates the coverage paths (happy, alternate, boundaries, negative) — multiple specific concrete actions rather than vague language.

3 / 3

Completeness

Explicitly answers what ("emits a markdown test-case matrix") and when ("Use as the first artifact a manual tester or three-amigos session produces from a story, ahead of automation"), satisfying both halves with explicit triggers.

3 / 3

Trigger Term Quality

Uses natural QA-domain terms a user would actually say ("user story", "feature spec", "manual tester", "three-amigos", "TestRail / Qase / Xray") rather than technical jargon; coverage spans common variations.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche and explicitly differentiates from adjacent skills ("not Gherkin scenarios written against locked acceptance criteria, and not executable test code"), making overlap with sibling skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents