verify-before-done
Use this skill before reporting code changes as complete to run repository verification checks and ensure no generated files were manually edited.
Skill by dekart-xyz
Chalk Labs
Need help deploying verify-before-done?
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/dekart-xyz-verify-before-done
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
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/verify-before-done
What's inside
- Skill name
verify-before-done- Description
- Use this skill before reporting code changes as complete to run repository verification checks and ensure no generated files were manually edited.
- License
- AGPL-3.0
- Instructions
- 18 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Verify Before Done Skill ## Trigger Use before reporting a code change as complete. ## Checklist 1. `go test ./...` passes for affected Go packages. 2. `npm test` passes for affected frontend code. 3. `npm run lint` passes for affected frontend code. 4. No generated files were edited manually. 5. When asked, behavior validated in the real runtime path (not just unit tests). 6. Any changed unit-test coverage protects meaningful behavior under the unit-test policy in `AGENTS.md`; it is not coverage-only, an implementation duplicate, or a trivial copied-text assertion. 7. Nothing in the change is unnecessary for the current scope. 8. For dark-library changes, regenerate each affected library's `README.md`, run `make dark-check` and the relevant unit contract tests (including executable examples), and confirm any `README.md` diff is listed under `Dark API changes` in the PR description. Bootstrap these checks with the first real dark library per `skills/dark-library/SKILL.md`.
From dekart-xyz/dekart, AGPL-3.0.
More from dekart-xyz/dekart
- 0.804score
code-style
dekart-xyz
Use this skill when implementing/refactoring frontend/backend code and you need Dekart-specific conventions for naming, code organization, architecture…
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
release-notes
dekart-xyz
Use this skill when asked to write versioned release notes and you need repo-specific structure, ordering, and scope filtering.
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
cypress-balance
dekart-xyz
Manually invoked Cypress maintenance to balance CI matrix lanes and refactor overlapping test coverage.
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
cypress-quick-start
dekart-xyz
Use this skill when running, debugging, reproducing, or validating Cypress E2E tests in this repo, including the required ELECTRON_RUN_AS_NODE override.
SkillAFreshness: A★ 436Claude Code +9 - 0.800score
dark-library
dekart-xyz
Use when creating or changing anything under src/client/dark/ or src/server/dark/, or when a new feature has self-contained logic/UI that can live there.
SkillAFreshness: A★ 436Claude Code +9 - 0.799score
dev-runtime
dekart-xyz
Use this skill when starting local development, setting up runtime dependencies, or debugging frontend/backend runtime issues in this repository.
SkillAFreshness: A★ 436Claude Code +9
Signals
- Stars
- 436
- Forks
- 62
- Open issues
- 34
- Last commit (this folder)
- Sep 30, 2026 (1 month ago)
- Last release
- Oct 6, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/dekart-xyz/dekart
- Website
- dekart.xyz
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dekart-xyz
- 0.804score
code-style
dekart-xyz
Use this skill when implementing/refactoring frontend/backend code and you need Dekart-specific conventions for naming, code organization, architecture…
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
release-notes
dekart-xyz
Use this skill when asked to write versioned release notes and you need repo-specific structure, ordering, and scope filtering.
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
cypress-balance
dekart-xyz
Manually invoked Cypress maintenance to balance CI matrix lanes and refactor overlapping test coverage.
SkillAFreshness: A★ 436Claude Code +9 - 0.804score
cypress-quick-start
dekart-xyz
Use this skill when running, debugging, reproducing, or validating Cypress E2E tests in this repo, including the required ELECTRON_RUN_AS_NODE override.
SkillAFreshness: A★ 436Claude Code +9 - 0.800score
dark-library
dekart-xyz
Use when creating or changing anything under src/client/dark/ or src/server/dark/, or when a new feature has self-contained logic/UI that can live there.
SkillAFreshness: A★ 436Claude Code +9 - 0.799score
dev-runtime
dekart-xyz
Use this skill when starting local development, setting up runtime dependencies, or debugging frontend/backend runtime issues in this repository.
SkillAFreshness: A★ 436Claude 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 verify-before-done 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
verify-before-done skill. Agent Mart. https://agentmart.dev/skills/dekart-xyz-verify-before-done (last updated 2026-10-24)