CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

stand-scenarios

Turn docs/product/SCENARIOS.md into testable claims for the deployed-stand suite — QA scenario design for Insight. Pick a scenario (S-1…S-10), a persona (EXEC/LEAD/IC/ADMIN), an invariant (§5 rules 1-12) or an Appendix A question (A1…G4), ground it in the seeded roster, and emit claims with an oracle, a layer and a priority that stand-api-test / stand-ui-test can implement. Use when the task is deciding WHAT to test: 'what should we test for S-9', 'design e2e scenarios from the product doc', 'which product rules are unverified', 'is the IC boundary covered', 'plan coverage for the reach matrix', 'convert the scenarios doc into tests'. Not for writing test code — that is stand-api-test and stand-ui-test; for scoping tests from a GitHub issue or an unbuilt feature use scope-feature-tests instead.

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A high-quality, expert-level body: actionable, well sequenced, and free of generic filler, with excellent decision tables and a worked claim template. Its one real defect is that the two pattern files it leans on are missing from the bundle, which breaks both navigation and Procedure step 3.

Suggestions

Ship persona-reach.md and invariants.md alongside SKILL.md (or move them into references/ and update the ./ links) — the Pattern files section and Procedure step 3 currently point at files that do not exist in the bundle.

State the SCENARIO-COVERAGE.md §2 shortcut once (in question 5, where it is most useful) and drop the repetitions in the Procedure tail and closing paragraph.

Trim rhetorical asides such as "and that is the point" / "that is the whole opportunity here" — the surrounding rules already carry the emphasis.

DimensionReasoningScore

Conciseness

The body is dense and project-specific (fixture names, route tables, refusal-code decision table) with no explanation of concepts Claude already knows. Minor trimmable material keeps it at 4 rather than 5: the SCENARIO-COVERAGE.md §2 shortcut is stated three times (question 5, Procedure step 9's context, and the closing paragraph), and a few rhetorical asides ("and that is the point") could go.

4 / 5

Actionability

Fully executable for an instruction-only skill: copy-paste grep commands, exact file paths (src/backend/services/{analytics,identity-resolution}/src/api/, tests/stand/api/operations.py, tests/lib/insight_stand/coverage.py), a worked claim-form example with the exact markdown template, a precise ID scheme, and a first-trigger-fires priority rubric. Specific examples cover the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

The ten-step Procedure is clearly sequenced with explicit validation checkpoints: question 2's four-verdict gate ("Stop where it does not"), a coverage inventory before designing (question 5), and step 8's self-check against the Design discipline checklist. Explicit gates plus a checklist match the 5 anchor; not 4, because checkpoints are not merely implicit.

5 / 5

Progressive Disclosure

The structure is well signaled — a "Pattern files" section with one-level references to persona-reach.md and invariants.md, each described — but neither file (nor the referenced ./SCENARIO-COVERAGE.md) exists in the provided bundle, and Procedure step 3 depends on persona-reach.md. Scored against the actual bundle structure, the split is broken rather than a minor gap, so this sits at 3 rather than 4.

3 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary description: it states a concrete what, an explicit when with quoted trigger phrases, and explicit boundaries against sibling skills. Every clause carries information; there is no padding or over-claiming.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline — "Pick a scenario (S-1…S-10), a persona (EXEC/LEAD/IC/ADMIN), an invariant (§5 rules 1-12) or an Appendix A question (A1…G4), ground it in the seeded roster, and emit claims with an oracle, a layer and a priority" — with named input, output, and consumers. Comprehensive with no coverage gaps, so it matches the 5 anchor rather than 4.

5 / 5

Completeness

Both halves are explicit: the "what" (turn SCENARIOS.md into testable claims with oracle, layer, and priority) and the "when" ("Use when the task is deciding WHAT to test:" followed by concrete trigger phrases), plus an explicit not-for clause. This is the anchor-5 pattern exactly.

5 / 5

Trigger Term Quality

Six natural user phrasings are quoted verbatim ("what should we test for S-9", "design e2e scenarios from the product doc", "is the IC boundary covered", "plan coverage for the reach matrix", "convert the scenarios doc into tests"), covering synonyms like test, coverage, scenarios, boundary, and e2e. Matches the comprehensive-synonym 5 anchor; not 4, since common variations are well represented.

5 / 5

Distinctiveness Conflict Risk

"Not for writing test code — that is stand-api-test and stand-ui-test; for scoping tests from a GitHub issue or an unbuilt feature use scope-feature-tests instead" explicitly disambiguates sibling skills. A clear niche with distinct triggers and minimal conflict risk, matching the 5 anchor.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 7 missing, 1 suspicious

Warning

Total

14

/

16

Passed

Repository

constructorfabric/insight

Path

.claude/skills/stand-scenarios/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.