CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

test-driven-development

Build or fix software with a focused red-green-refactor loop

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 ./resources/skills/general/test-driven-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean process skill: a tight red-green-refactor procedure with explicit validation checkpoints, a pitfalls section for error recovery, and a verification checklist, all with zero token waste. The only minor gap is the absence of any example command or sample regression-test shape that would make the guidance fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is ~28 lean lines across four tight sections with zero padding and no explanation of concepts Claude already knows (no "what TDD is" preamble). Every step and pitfall adds non-obvious guidance, matching the "lean and efficient; every token earns its place" anchor.

5 / 5

Actionability

The guidance is concrete and specific for an instruction-only skill ("Write the smallest regression test that demonstrates the requested behavior", "Make the smallest production change that makes the test pass"), with no pseudocode or vague hand-waving. It stops short of 5 because nothing is copy-paste ready — there are no example commands for running the focused test or a sample regression-test shape — and steps like "Review the diff for unrelated changes" remain abstract.

4 / 5

Workflow Clarity

Seven numbered steps are clearly sequenced with explicit validation checkpoints (step 3's "confirm it fails for the expected reason, not because the test setup is broken", step 5's focused-then-module suite runs, step 6's diff review), backed by a Pitfalls section covering error recovery and a Verification checklist. It is not 4 because the checkpoints are explicit and complete rather than having minor gaps; the skill is not destructive/batch so no cap applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized into four clearly headed sections (When to Use, Procedure, Pitfalls, Verification). Per the rubric guideline, a sub-50-line skill with no need for external files and well-organized sections scores 5.

5 / 5

Total

19

/

20

Passed

Description

42%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 has a concrete "what" anchored by the red-green-refactor methodology, but it omits any "when to use" trigger guidance and lacks the natural keywords (test, testing, bug, regression) a user would say when needing this skill. Its broad "build or fix software" framing also creates overlap risk with general coding skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when implementing a feature, fixing a bug, or when the user asks for test-driven development or regression tests."

Include natural trigger terms users would actually say — "write tests", "test-driven development", "TDD", "regression test", "bug fix" — rather than only the jargon term "red-green-refactor".

Narrow the scope from "build or fix software" to testing-centric changes so it is distinguishable from general coding and code-review skills.

DimensionReasoningScore

Specificity

"Build or fix software" is generic, but "with a focused red-green-refactor loop" names a concrete, well-known methodology, matching the anchor for domain plus 1-2 concrete actions. It falls short of 4 because it does not list several distinct specific actions.

3 / 5

Completeness

The description clearly answers "what" ("Build or fix software with a focused red-green-refactor loop") but contains no "Use when..." clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3. It is not 2 because the "what" half is concrete, not vague.

3 / 5

Trigger Term Quality

The only keywords are the generic "Build", "fix", "software" plus the jargon term "red-green-refactor"; the natural phrases a user would actually say ("test", "write tests", "testing", "bug", "regression test", "TDD") are entirely absent. This matches anchor 2 (one or two generic keywords, missing the natural phrases users say), not 3, since even the most common variation ("test") is missing.

2 / 5

Distinctiveness Conflict Risk

"red-green-refactor loop" gives the skill a recognizable niche distinct from generic coding helpers, but "Build or fix software" is very broad and would overlap with many development, debugging, and code-review skills. This fits anchor 3 (somewhat specific but could still overlap with similar skills); it is not 4 because the trigger surface covers almost any coding task.

3 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

odysseus-dev/odysseus

Path

resources/skills/general/test-driven-development/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.