implementation-quality
Use when implementing or reviewing code changes that need judgment about proportionate testing and verification
Skill by tenecsson
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.
About
Use cases: testing
Reviews
Write a reviewNo 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
- 0.529score
human-editor
tenecsson
Use when editing or reviewing existing prose for LLM writing habits, rhetorical padding, or fidelity to an author's voice.
SkillBFreshness: BClaude Code +9 - 0.524score
using-git-worktrees
tenecsson
Use when the user requests a worktree or parallel, experimental, or high-risk work needs isolation from the current checkout
SkillBFreshness: BClaude Code +9 - 0.524score
writing-skills
tenecsson
Use when creating, editing, or validating a reusable skill and you need to keep it concise, discoverable, and behavior-changing
SkillBFreshness: BClaude Code +9 - 0.519score
code-review
tenecsson
Use when the user requests code review, review feedback must be evaluated, or a high-risk change warrants an independent technical pass
SkillBFreshness: BClaude Code +9 - 0.518score
brainstorming
tenecsson
Use when a request has material product, behavior, or architecture choices that must be resolved before implementation
SkillBFreshness: BClaude Code +9 - 0.518score
planning-and-execution
tenecsson
Use when a multi-step implementation needs a durable plan or an existing approved plan needs coordinated execution
SkillBFreshness: BClaude Code +9 - 0.518score
systematic-debugging
tenecsson
Use when any bug, failing test, build break, or unexpected behavior needs root-cause analysis before fixes
SkillBFreshness: BClaude Code +9 - 0.498score
supervised-subagent
tenecsson
Use when the user asks to delegate implementation to a subagent
SkillBFreshness: BClaude Code +9 - 0.493score
improve-coverage
tenecsson
Use when the user asks to improve test coverage or uncovered behavior needs a focused coverage pass
SkillBFreshness: BClaude Code +9 - 0.408score
dispatching-parallel-agents
tenecsson
Use when 2 or more tasks are independent enough to investigate or implement in parallel
SkillDFreshness: DClaude Code +9
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
- Repository
- github.com/tenecsson/playbooks
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tenecsson
- 0.529score
human-editor
tenecsson
Use when editing or reviewing existing prose for LLM writing habits, rhetorical padding, or fidelity to an author's voice.
SkillBFreshness: BClaude Code +9 - 0.524score
using-git-worktrees
tenecsson
Use when the user requests a worktree or parallel, experimental, or high-risk work needs isolation from the current checkout
SkillBFreshness: BClaude Code +9 - 0.524score
writing-skills
tenecsson
Use when creating, editing, or validating a reusable skill and you need to keep it concise, discoverable, and behavior-changing
SkillBFreshness: BClaude Code +9 - 0.519score
code-review
tenecsson
Use when the user requests code review, review feedback must be evaluated, or a high-risk change warrants an independent technical pass
SkillBFreshness: BClaude Code +9 - 0.518score
brainstorming
tenecsson
Use when a request has material product, behavior, or architecture choices that must be resolved before implementation
SkillBFreshness: BClaude Code +9 - 0.518score
planning-and-execution
tenecsson
Use when a multi-step implementation needs a durable plan or an existing approved plan needs coordinated execution
SkillBFreshness: BClaude Code +9
Cite this page
implementation-quality skill. Agent Mart. https://agentmart.dev/skills/tenecsson-implementation-quality (last updated 2026-10-24)