CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-add-tests

Generate tests for a completed phase based on UAT criteria and implementation

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 ./pi/package-skills/gsd-add-tests/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

This is a well-built thin dispatch wrapper: concise, platform-aware, and fail-closed with explicit error-handling feedback loops. Its only real weakness is that all task substance (the actual test-generation workflow and its gates) is delegated to an external templated path, so a copy of this file alone cannot execute or verify the task.

DimensionReasoningScore

Conciseness

The body is a lean dispatch wrapper with no padding: the dense paragraphs (gsd_dispatch semantics, Pi not expanding @ includes, fail-closed error handling) convey platform-specific mechanics Claude does not already know, and every sentence changes behavior. It matches anchor 5 (lean and efficient, every token earns its place) rather than 4, since trimming anything would lose dispatch correctness.

5 / 5

Actionability

The orchestration guidance is concrete and executable: call gsd_dispatch with role and task, read every file under <execution_context> before anything else, STOP on unresolved role or child failure, offer to skip when optional, never execute inline. It falls short of anchor 5 because the actual test-generation steps live entirely in an external workflow file and there is no worked example of a gsd_dispatch call.

4 / 5

Workflow Clarity

The orchestration sequence is clear (read includes first, treat <arguments> as data, execute end-to-end, preserve all gates) with explicit error-recovery feedback (STOP and surface errors, offer skip when optional). It matches anchor 4 rather than 5 because the detailed workflow and its checkpoints (classification approval, RED-GREEN verification) are only referenced via the external workflow file rather than specified here.

4 / 5

Progressive Disclosure

The skill is appropriately split: this file is an overview, the full workflow is a single one-level-deep, clearly signaled reference (@__GSD_PI_ENGINE_ROOT__/gsd-core/workflows/add-tests.md) with explicit "read every file listed" navigation. It falls short of anchor 5 because the primary reference is an unsubstituted template placeholder and no bundle files ship alongside the skill, so navigation depends entirely on external substitution.

4 / 5

Total

17

/

20

Passed

Description

50%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 clear and free of fluff, with an accurate statement of what the skill does, but it sits at the midpoint on every dimension. Its main deficits are the complete absence of when-to-use trigger guidance and the lack of natural trigger terms (unit tests, E2E, test plan) that would both raise completeness and reduce conflict risk with generic test-writing skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when a phase's implementation is complete and its VERIFICATION.md asks for unit and E2E tests."

Include the natural trigger terms users would actually say — "unit tests", "E2E tests", "test plan", "write tests" — in the description.

Mention the distinctive parts of the workflow (classify implementation files into TDD/E2E/Skip, RED-GREEN conventions, user-approved test plan) so the description reflects the body's concrete actions and stands apart from generic test-generation skills.

DimensionReasoningScore

Specificity

"Generate tests for a completed phase based on UAT criteria and implementation" names the domain and one concrete action with its input specifications, but does not list the several specific actions the body actually covers (classify files, present a test plan, RED-GREEN conventions, unit and E2E tests). It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, which requires several specific actions.

3 / 5

Completeness

The description clearly answers "what" (generate tests for a completed phase from UAT criteria and implementation) but has no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Relevant keywords like "tests", "UAT criteria", "phase", and "implementation" are present, but natural phrases a user would say — "unit tests", "E2E tests", "write tests", "test plan" — are missing. This fits anchor 3 (some relevant keywords, missing common variations) rather than 4, since keyword coverage is partial rather than good.

3 / 5

Distinctiveness Conflict Risk

"Generate tests" overlaps broadly with any generic test-writing skill, though "completed phase" and "UAT criteria" provide some GSD-workflow specificity. It fits anchor 3 (somewhat specific but could still overlap with similar skills) rather than 4, since overlap risk with closely related test-generation skills is more than minor.

3 / 5

Total

12

/

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

open-gsd/gsd-core

Path

pi/package-skills/gsd-add-tests/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.