CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tdd/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 TDD guidance itself is tight and opinionated with a sensible structure, but the skill is undermined by an off-topic telemetry block consuming roughly half the body and by references to example files that are absent from the bundle. A reader following the body's own pointers hits dead ends.

Suggestions

Remove or relocate the 'Skillpack activation reporting' block; it is unrelated to TDD and consumes the largest share of the body's token budget.

Fix the dangling references: either ship tests.md and mocking.md in the bundle or move their essential content inline, since no references/ directory exists.

Add an explicit validation checkpoint to the loop, e.g., 'Run the test and confirm it fails for the expected reason before writing any implementation; confirm it passes before starting the next slice.'

DimensionReasoningScore

Conciseness

Nearly half the body is a 'Skillpack activation reporting' telemetry block (UUID generation rules, curl/PowerShell snippets, identity-discovery instructions) that is unrelated to TDD, and lines like "TDD is the red → green loop" explain concepts Claude already knows. The TDD-specific sections themselves are lean, which keeps this above anchor 1's 'severely verbose' but firmly at anchor 2's 'several unnecessary... padded sections'.

2 / 5

Actionability

The loop rules are reasonably concrete ("One seam, one test, one minimal implementation per cycle", "Red before green") but the promised examples — "See [tests.md](tests.md) for examples and [mocking.md](mocking.md) for mocking guidelines" — point to files that do not exist in the bundle, and no worked example is provided inline. This is anchor 3's 'concrete guidance but incomplete; missing key details', not 4, because key guidance is unreachable.

3 / 5

Workflow Clarity

The red → green sequence is present across the 'Rules of the loop' section, but validation checkpoints are implicit: it never instructs running the test to confirm it fails before implementing, or confirming it passes after. This matches anchor 3 ('sequence present but checkpoints missing or implicit'); the sequencing is too coherent for anchor 2 and lacks explicit validation steps for anchor 4.

3 / 5

Progressive Disclosure

The in-file structure is well-sectioned, but the only two references (tests.md, mocking.md) are dangling — no references/ directory or bundle files exist, so following them fails entirely. Per the guideline to score against the actual bundle structure, clearly-signaled references to nonexistent files are worse than anchor 3's 'references present but not clearly signaled', fitting anchor 2's unusable-reference condition.

2 / 5

Total

10

/

20

Passed

Description

65%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.

A serviceable description with strong, natural trigger phrasing and an explicit Use-when clause. Its main weakness is that the 'what' is just the discipline's name — no concrete capabilities — which drags down specificity and completeness.

Suggestions

State 1-2 concrete capabilities after the domain name, e.g., 'Test-driven development: guides the red-green loop, test placement at public seams, and test-quality review. Use when...'.

Add the trigger terms users most commonly say: 'TDD', 'write the test first', and 'unit tests'.

DimensionReasoningScore

Specificity

The description names the domain ("Test-driven development") but lists no concrete actions or capabilities — it never says what the skill actually does (e.g., guide the red-green loop, review test quality, place tests at seams). It matches anchor 2 ("Names the domain but actions are minimal or generic"); it is not 3 because no concrete action is stated, and not 1 because the domain itself is specific.

2 / 5

Completeness

It has an explicit "Use when..." clause with concrete triggers, but the 'what' is only the bare label "Test-driven development" rather than a statement of what the skill provides. Anchor 4 ('both what and when; one could be more explicit') is the best fit; anchor 5 requires both to be clearly and explicitly stated.

4 / 5

Trigger Term Quality

Triggers like "build features or fix bugs test-first", "red-green-refactor", and "integration tests" are natural phrases a user would say. It falls short of anchor 5's comprehensive synonym coverage because the most obvious terms "TDD" and "unit tests" are absent, but it is well above anchor 3's 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The "red-green-refactor" and "test-first" triggers carve out a clear niche with minimal conflict risk, though it could still overlap with a generic 'write tests' or 'unit testing' skill, matching anchor 4 rather than 5.

4 / 5

Total

14

/

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

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
The-Vibe-Company/companion
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.