agentleFS
Sign inStart free
vibe-cokitvibe-cokit/claude-code/skills/vk-plan-fast/SKILL.md

vk-plan-fast

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

⚡⚡ No research. Only analyze and create an implementation plan

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use planner subagent to:

    line 19
  2. Very specific:

    Create a directory named plans/YYYYMMDD-HHmm-plan-name (eg.

    line 21
  3. Distinctive:

    Make sure you pass the directory path to every subagent during the process.

    line 22
  4. Very specific:

    Follow strictly to the "Plan Creation & Organization" rules of planning skill.

    line 23
  5. Very specific:

    Run the Automatic Plan Validation Loop (see workflows/plan-validation-loop.md §1-§7) against the full plan bundle (§1) — unconditional, …

    line 26
  6. Distinctive:

    Ask user to review the plan.

    line 29
  7. Very specific:

    After the Automatic Plan Validation Loop completes (workflows/plan-validation-loop.md §7), plan.md MUST include an ## Automatic Validation …

    line 50
  8. Distinctive:

    IMPORTANT: Ensure token efficiency while maintaining high quality.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan Fast

Think. Activate the planning skill. No research stage — codebase reading only.

Your mission

<task> $ARGUMENTS </task>

Workflow

Use planner subagent to:

  1. Create a directory named plans/YYYYMMDD-HHmm-plan-name (eg. plans/20251101-1505-authentication-and-profile-implementation). Make sure you pass the directory path to every subagent during the process.
  2. Follow strictly to the "Plan Creation & Organization" rules of planning skill.
  3. Analyze the codebase by reading codebase-summary.md, code-standards.md, system-architecture.md and project-overview-pdr.md file.
  4. Gathers all information and create an implementation plan of this task.
  5. Run the Automatic Plan Validation Loop (see workflows/plan-validation-loop.md §1-§7) against the full plan bundle (§1) — unconditional, runs before review.
  6. Ask user to review the plan.

Output Requirements

Plan Directory Structure

plans/
└── YYYYMMDD-HHmm-plan-name/
    ├── reports/
    │   ├── XX-report.md
    │   └── ...
    ├── plan.md
    ├── phase-XX-phase-name-here.md
    └── ...

Plan File Specification

  • Structure of plan.md + phase-XX-*.md: follow skills/planning/references/plan-organization.md (SSOT, not restated here).
  • Lane-conditional phase sections: Test Strategy & Quality Gate (normal/high-risk lanes, workflows/quality-gate.md §6; tiny lane exempt per §8) and ADR Rationale (high-risk only) — on this fast path the rationale must come from code-reading, no external research is available.
  • After the Automatic Plan Validation Loop completes (workflows/plan-validation-loop.md §7), plan.md MUST include an ## Automatic Validation section recording round-by-round outcomes.

Important Notes

  • IMPORTANT: Ensure token efficiency while maintaining high quality.
  • IMPORTANT: Do not start implementing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free