Tessl • The management layer for AI agent skills

SkillPublic

testing

Testing and code quality context for Jest, React Testing Library, ESLint, and test patterns. Use when writing tests or fixing linting issues.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./fleet-skills/testing/SKILL.md

Quality

Content

57%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 a genuinely useful, concrete reference — real commands, real env-var behavior, and reusable test patterns — but it is a monolithic inline dump rather than a progressive-disclosure structure, and it mixes in a dated, partially off-topic repo-notes section. Adding a decision guide (which test tier when) and trimming/splitting the inline pattern catalogs would raise it substantially.

Suggestions

Split the E2E integration patterns (ingest token, runtime token, multi-agent) and frontend/backend pattern catalogs into references/ files (e.g. references/e2e-patterns.md, references/frontend-patterns.md), keeping SKILL.md as an overview with well-signaled one-level links.

Remove or move the time-sensitive "Current Repo Notes (2026-02-08)" content: the non-testing lines (skill catalog, gateway registry, HEARTBEAT.md) are off-topic noise, and dated notes belong in a deprecated/old-patterns section or the repo's own docs.

Add a short decision workflow — which test tier to write/run (unit with in-memory DBs by default vs integration with real services vs contract) and what to check when a test run fails — to give the command sequences explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, non-padded reference material (commands, env vars, executable code patterns) with no explanations of concepts Claude already knows, but the dated "Current Repo Notes (2026-02-08)" section carries time-sensitive information outside any old-patterns/deprecated section and drifts off the testing topic (skill catalog, gateway registry, HEARTBEAT.md).	3 / 5
Actionability	Highly concrete throughout — executable bash commands including the exact integration invocation ("INTEGRATION_TEST=true npm --prefix backend test -- --forceExit") and complete copy-paste JS patterns (ingest token creation, runtime token flow, multi-agent polling) — but the Multi-Agent pattern contains placeholders ("scopes: [...]", "payload: {...}") and undeclared fixtures (testUser, testPod), leaving minor gaps.	4 / 5
Workflow Clarity	Command sequences include an explicit prerequisite checkpoint ("Requires `./dev.sh up` to be running first") and the INTEGRATION_TEST mode switch is clearly explained, but there is no guidance on which test tier to choose (unit vs integration vs contract) or any feedback loop for what to do when tests fail, so checkpoints remain largely implicit.	3 / 5
Progressive Disclosure	The three docs/development references are clearly signaled in a one-level table, but with no references/ bundle, ~230 lines inline several separable domains (backend patterns, frontend patterns, ~80 lines of E2E patterns, ESLint config, misc repo notes) that belong in dedicated reference files.	3 / 5
	Total	13 / 20 Passed

Description

70%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 solid explicit trigger clause and names specific technologies, but it tells rather than shows: "context for" is a weak capability statement that never says what the skill actually provides (commands, patterns, setup modes). It is serviceable but leaves the reader inferring its value.

Suggestions

Replace the vague capability noun ("Testing and code quality context for...") with concrete actions, e.g. "Provides repo-specific Jest/React Testing Library test commands, integration-test setup (INTEGRATION_TEST, in-memory vs real services), and E2E test patterns".

Broaden trigger coverage with natural variations users would say: "unit tests", "test coverage", "frontend or backend tests", "fixing lint errors".

Distinguish from generic testing skills by signaling repo specificity (e.g. "Use when writing or running tests in this repo") to reduce overlap with a general test-writing skill.

Dimension	Reasoning	Score
Specificity	The description names the domain with concrete tools ("Jest, React Testing Library, ESLint, and test patterns") and two actions appear via the trigger clause ("writing tests", "fixing linting issues"), but the stated capability is the generic noun "context" with no action verbs for what the skill itself does.	3 / 5
Completeness	Both parts are present: an explicit "Use when writing tests or fixing linting issues" trigger clause and a what-clause naming the toolchain, but the "what" is the vague "context for..." rather than a concrete statement of what the skill provides, keeping it below a 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage — "writing tests", "fixing linting issues", "Jest", "ESLint", "linting" — but common variations like "unit tests", "test coverage", "TDD", or "frontend/backend tests" are missing, so it falls short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The named toolchain (Jest, React Testing Library, ESLint) carves a mostly distinct niche with clear triggers, with only minor overlap risk against a generic test-writing skill triggered by "writing tests".	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Team-Commonly/commonly
Path: fleet-skills/testing/SKILL.md
Revision: 931b8ff

Reviewed: 3 days ago

Discovery Implementation Validation

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.

testing

Table of Contents

Is this your skill?