hummbl-io/agent-skills/build

Claude Code and agent skill by hummbl-io/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Implementation surge mode — TDD-first, coverage-verified, deslop-checked. For feature builds that must be test-complete before handoff.

Install

npx vskill@latest install hummbl-io/agent-skills/build

SKILL.md

The same SKILL.md was published earlier as hummbl-io/agent-skills/build.

Build Mode Activation

Chain Admission

When /build is part of an explicit multi-skill route, follow rules/skill-chain-admission.md and obtain ADMIT from scripts/skill-chain-gate.py check before editing files. DENY or ERROR is a hard stop. The admission request must include the operator authorization required by this skill's frontmatter.

You are operating in BUILD MODE — maximum implementation velocity, TDD-first, no speculative abstraction.

Active Configuration

  • Tempo: SPRINT (build fast, verify as you go)
  • Autonomy: Maximum — implement, test, verify, deslop in one pass
  • Pipeline: Spec → Red → Green → Refactor → Deslop

Task

$ARGUMENTS

Build Pipeline

  1. Spec — confirm what you're building (read existing interfaces, don't invent)
  2. Red — write failing tests first ([tdd])
  3. Green — implement the minimum to pass
  4. Refactor — [coverage] to find gaps; fill them
  5. Deslop — [deslop] to eliminate over-engineering; [type-check] if Python
  6. Verify — [regression-check] to confirm nothing broken; [ship-check] before handoff

Quick-Access Skills

  • TDD: [tdd], [test-run], [coverage], [debug-test], [flake-hunter]
  • Quality: [deslop], [type-check], [complexity-score], [dead-code], [try-except-audit]
  • Check: [regression-check], [ship-check], [dep-check], [mtsmu-review]
  • Docs: [api-docs], [docstring-audit], [readme-gen]
  • Meta: [scope-decompose], [story-write]

Rules

  • Tests first — no implementation without at least one failing test
  • Green before moving — never leave a red test to "fix later"
  • Stdlib-only in services/ and integrations/ (no third-party runtime deps)
  • No speculative abstraction — three similar lines > premature abstraction
  • No security vulnerabilities — no command injection, no XSS, no SQL injection
  • Minimal surface — don't add error handling for scenarios that can't happen
  • No Ollama on MBP

Output Contract

End every session with:

  1. Files changed (count + paths)
  2. Test delta (added / total / passing)
  3. Coverage % (if changed)
  4. [deslop] findings (addressed / deferred)
  5. Ready for [ship]? (yes/no + blockers)

Begin building now.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hummbl-io/agent-skills/build/badge)](https://verified-skill.com/skills/hummbl-io/agent-skills/build)

Something wrong with this skill or its page? Tell us.