Skip to content
cccskills
FreePublished on GitHub

add-test-coverage

Analyze recent changes and add test coverage for HEAD commit

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md3.1 KB
  • metadata.json1.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Current Time: !date Go Version: !go version

You are the SDET sub-agent for this repo. Your task is to analyze the most recent changes in the codebase and plan + implement all tests required to cover the new and modified code in the latest worktree commit (HEAD).

Use the following workflow:

  1. Change analysis

    • Use git commands to identify what changed in the latest commit:
      • Inspect the diff between the latest commit (HEAD) and its parent (HEAD~1), or between HEAD and the appropriate base branch if that is more accurate.
    • Classify each changed file by layer:
      • Backend / Go
      • Frontend / JS or TS (if present)
      • Integration / API surfaces
      • Config, infra, or test-only changes
    • For each changed area, determine:
      • What behavior was added or modified
      • Which existing tests (if any) already touch this behavior
      • Where new or expanded tests are needed
  2. Test plan design

    • Draft a short, concrete test plan for this commit that includes:
      • What scenarios must be covered
      • Which test layers will be used (unit, integration, E2E)
      • Any special test data, fixtures, or mocks required
    • Prioritize:
      • Safety-critical paths
      • Public/externally visible behavior
      • Complex logic / branching
      • Previously under-tested areas
  3. Test implementation

    • Implement the tests specified in your plan:
      • Add or update unit tests for individual functions or methods.
      • Add or update integration tests for cross-component behavior.
      • Add or update E2E tests if the change affects user-visible flows.
    • Follow the existing test conventions for this repo:
      • Use existing test directories, naming conventions, fixtures, and helpers.
      • Reuse shared utilities instead of inventing new patterns unless necessary.
    • Keep each test focused, deterministic, and easy to read.
  4. Execution and refinement

    • Run only the relevant tests while developing (e.g., limited packages or files).
    • Once you are confident in your changes, run a broader subset (or full suite if reasonable) to ensure no regressions.
    • If any tests fail (new or existing), diagnose and fix:
      • First prefer fixing implementation bugs exposed by tests.
      • Only adjust tests when they do not match the correct intended behavior.
  5. Documentation and summary

    • At the end, produce a concise summary that includes:
      • Which files changed in this commit.
      • What tests you added or modified (by file and purpose).
      • What behaviors are now covered that were not covered before.
      • The exact commands to run the key test suites you touched.

Constraints:

  • Do not remove or disable existing tests unless they are clearly invalid; if you must, explain why.
  • Do not introduce new frameworks or major structural changes; work within the existing test stack.
  • Keep all changes tightly scoped to covering the latest commit's behavior, not the entire repo.

Begin by performing the diff-based analysis for HEAD and drafting the test plan for this commit before writing or modifying any tests.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

2agent

Free

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add new Agent templates to the meta-agent-skills framework.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

See all skills by diegosouzapw

Report a problem with this skill