Skip to content
Agentmart
Submit a tool

implementation-quality

Use when implementing or reviewing code changes that need judgment about proportionate testing and verification

Skill by tenecsson

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tenecsson-implementation-quality

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when implementing or reviewing code changes that need judgment about proportionate testing and verification

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/implementation-quality

What's inside

Skill name
implementation-quality
Description
Use when implementing or reviewing code changes that need judgment about proportionate testing and verification
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Protect meaningful behavior with the cheapest reliable evidence.

Choose the evidence by change type:
- Observed bug or correctness invariant: add a focused regression test when it can fail for the actual defect through a stable boundary.
- Risky logic, async flow, state, resource ownership, security, or compatibility: test plausible outcomes and failure modes.
- Refactor: rely on existing behavior tests; add a test only for a real contract that was previously unprotected.
- Visual tuning, configuration, documentation, generated artifacts, or trivial wiring: prefer build, typecheck, lint, artifact inspection, or a manual check unless a durable automated contract is valuable.
- If the user explicitly says not to add tests, honor that and use permitted non-test verification.

Test quality:
- Test observable behavior or a durable interface, not copied constants, source text, exact private structure, or incidental call order unless that is the explicit contract.
- Prefer realistic construction and public entry points. Avoid prototype-only objects or mocks that permit impossible states.
- A test should fail under a plausible regression. Do not keep one solely because it adds coverage or proves the code you just wrote.
- If the harness is larger than the change, the first failure is setup noise, or the expected value is unclear, reconsider the boundary before proceeding.
- Do not change an expectation merely to match the implementation; derive it from requirements or independent evidence.

For a suitable regression, confirm the test fails for the expected reason, make the smallest coherent fix, then rerun the targeted and relevant surrounding checks. For changes unsuited to a new test, implement directly and verify proportionately.

Before completion, run fresh commands that support the claims you will make. Partial checks support partial claims; summaries from agents or tools are not evidence by themselves. Review new tests as production code and remove redundant or brittle ones.

From tenecsson/playbooks, MIT.

More from tenecsson/playbooks

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 28, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tenecsson

Cite this page

implementation-quality skill. Agent Mart. https://agentmart.dev/skills/tenecsson-implementation-quality (last updated 2026-10-24)