buiducnhat/cobrew/quick-implement

Claude Code and agent skill by buiducnhat/cobrew

Trust tier 3
  • community
Source check pending

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

Rapid implementation for small, low-risk, well-defined changes. Use when the task is narrow in scope, has clear acceptance criteria, and can be completed safely without a formal multi-phase plan.

Install

npx vskill@latest install buiducnhat/cobrew/quick-implement

SKILL.md

Quick Implement

Scope Gate (Required Before Coding)

Treat a task as quick-implement eligible only if all conditions below are true:

  1. Clear requirement
  • Expected behavior is explicit
  • No major product/architecture ambiguity
  1. Small change surface
  • Usually touches a small number of files (rough guideline: <= 5 files)
  • No broad cross-module refactor
  1. Low architectural risk
  • No foundational redesign
  • No migration-heavy change
  • No multi-phase rollout dependency
  1. Straightforward verification
  • Can validate with targeted tests/checks quickly
  • No long exploratory debugging loop required

If any condition fails, escalate to write-plan.

Hard Stop Escalation Criteria

Immediately stop quick implementation and switch to planning when any of these appear:

  • Requirement ambiguity that needs design decisions
  • Unexpected coupling across multiple subsystems
  • Significant data model or schema changes
  • Security-sensitive or compliance-critical changes
  • Performance work requiring benchmarks/design trade-offs
  • Refactor growing beyond original small scope
  • Repeated failed attempts without a clear root cause
  • Need for phased delivery, feature flags, or migration strategy

Escalation action:

  1. Stop all coding activities immediately.
  2. Output the exact message: "This change exceeds rapid-implementation safety limits. Recommend write-plan first to define phased execution and risk controls."
  3. Use input/question to ask the user if they want to initiate a handoff to the write-plan skill.

Workflow

Step 1: Analyze and Contextualize
  1. Understand the user request and define acceptance criteria.
  2. Load only the project context relevant to the request:
  • If docs/SUMMARY.md exists, read it first.
  • Load only task-relevant detail docs.
  • Prioritize Code Standard docs for implementation conventions.
  • If docs conflict with code or user intent, use the available input/question before broad changes.
  1. Inspect only the minimum necessary code paths.
  2. Confirm the task still passes the Scope Gate.
  3. If ambiguity remains, ask clarifying questions before coding.
Step 2: Implement
  1. Make the smallest correct change to satisfy requirements.
  2. Reuse existing patterns and conventions.
  3. Avoid opportunistic refactors unrelated to the request.
  4. Keep changes idempotent and safe to rerun when applicable.
Step 3: Verify

Run proportional validation for the change using the appropriate execution tools:

  1. Targeted tests related to modified behavior
  2. Relevant lint/type checks for touched areas
  3. Build or runtime verification if applicable

If verification fails unexpectedly:

  • Attempt focused fixes if clearly local.
  • If failures suggest broader impact, recommend escalate to write-plan.
Step 4: Complete
  1. Summarize what changed and why.
  2. List modified files.
  3. Report verification commands and outcomes.
  4. Update documentation if minor behavior or domain rules changed

Execution Boundaries

  • Do not expand scope without explicit user approval.
  • Do not assume unspecified behavior; clarify instead.
  • Do not force completion when risk increases—escalate early.
  • Escalate to write-plan when complexity or risk exceeds quick-implement limits.
  • Use fix when the task is primarily debugging an issue.

Output Checklist

Before final response, confirm:

  • Scope Gate was satisfied
  • No hidden architectural changes were introduced
  • Verification was run and reported
  • Escalation was used if safety limits were exceeded

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

Repository stars
48
Repository forks
3
7-day trend score
19

Stars and forks are for the whole GitHub repository, not this skill alone. 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/buiducnhat/cobrew/quick-implement/badge)](https://verified-skill.com/skills/buiducnhat/cobrew/quick-implement)

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