test-fix
Use when tests fail or a bug needs a minimal verified fix with root-cause analysis.
Skill by xmindlab-heicode
Chalk Labs
Need help deploying test-fix?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/xmindlab-heicode-test-fix
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/test-fix
What's inside
- Skill name
test-fix- Description
- Use when tests fail or a bug needs a minimal verified fix with root-cause analysis.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- heicode.skill.json
- common-failures.md · references/
SKILL.md (first lines)
# Test Fix Fix failing tests by finding the root cause first. Do not patch symptoms. ## Workflow 1. Run or inspect the failing test output. 2. Identify the exact failing assertion, error, or timeout. 3. Trace the failing value back to its source. 4. Compare with nearby passing tests or working code. 5. Make the smallest fix that addresses the root cause. 6. Re-run the targeted test. 7. Run the relevant broader test or typecheck command when feasible. ## Rules - Do not weaken assertions unless the assertion is wrong. - Do not delete tests to make the suite pass. - Do not add sleeps for async failures unless timing is truly the behavior under test. - When a dependency is mocked, verify the mock still matches the real contract. ## Output Report: - root cause, - files changed, - verification commands and results, - remaining risk.
From xmindlab-heicode/heicode-sk-hub, MIT.
More from xmindlab-heicode/heicode-sk-hub
- 0.518score
platform-rules
xmindlab-heicode
Use in HeiCode runtimes to apply shared gateway, secret-safety, approval, and change-discipline rules.
SkillBFreshness: BClaude Code +9 - 0.479score
api-design
xmindlab-heicode
Use when designing or reviewing API contracts, authentication boundaries, error models, pagination, idempotency, and versioning.
SkillCFreshness: CClaude Code +9 - 0.479score
pr-summary
xmindlab-heicode
Use when preparing pull request descriptions, change summaries, validation notes, risks, release notes, or reviewer context.
SkillCFreshness: CClaude Code +9 - 0.479score
pricing-copywriter
xmindlab-heicode
Use when drafting pricing pages, billing explanations, plan comparison copy, enterprise plan text, or usage accounting policy.
SkillCFreshness: CClaude Code +9 - 0.479score
security-review
xmindlab-heicode
Use when reviewing authentication, authorization, secret handling, trust boundaries, supply-chain risk, and data exposure.
SkillCFreshness: CClaude Code +9 - 0.479score
code-review
xmindlab-heicode
Use when reviewing code changes for bugs, regressions, security risks, performance issues, maintainability risks, and missing tests.
SkillCFreshness: CClaude Code +9 - 0.478score
docs-generate
xmindlab-heicode
Use when generating or updating user-facing documentation, developer guides, API docs, runbooks, or operational notes.
SkillCFreshness: CClaude Code +9 - 0.478score
frontend-review
xmindlab-heicode
Use when reviewing frontend UI, UX, accessibility, responsiveness, visual quality, and implementation risks.
SkillCFreshness: CClaude Code +9 - 0.478score
incident-debug
xmindlab-heicode
Use when investigating production incidents, regressions, outages, failed integrations, or unexpected behavior.
SkillCFreshness: CClaude Code +9 - 0.476score
deployment-check
xmindlab-heicode
Use before or after deployment to verify artifacts, environment variables, service health, rollback readiness, and public endpoints.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 13, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from xmindlab-heicode
- 0.518score
platform-rules
xmindlab-heicode
Use in HeiCode runtimes to apply shared gateway, secret-safety, approval, and change-discipline rules.
SkillBFreshness: BClaude Code +9 - 0.479score
api-design
xmindlab-heicode
Use when designing or reviewing API contracts, authentication boundaries, error models, pagination, idempotency, and versioning.
SkillCFreshness: CClaude Code +9 - 0.479score
pr-summary
xmindlab-heicode
Use when preparing pull request descriptions, change summaries, validation notes, risks, release notes, or reviewer context.
SkillCFreshness: CClaude Code +9 - 0.479score
pricing-copywriter
xmindlab-heicode
Use when drafting pricing pages, billing explanations, plan comparison copy, enterprise plan text, or usage accounting policy.
SkillCFreshness: CClaude Code +9 - 0.479score
security-review
xmindlab-heicode
Use when reviewing authentication, authorization, secret handling, trust boundaries, supply-chain risk, and data exposure.
SkillCFreshness: CClaude Code +9 - 0.479score
code-review
xmindlab-heicode
Use when reviewing code changes for bugs, regressions, security risks, performance issues, maintainability risks, and missing tests.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get test-fix running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
test-fix skill. Agent Mart. https://agentmart.dev/skills/xmindlab-heicode-test-fix (last updated 2026-10-24)