New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Implementation Plan Generator

by withkynam in withkynam/vibecode-pro-max-kit

Writes a project's one implementation plan at the right depth level, saved into a dated task folder alongside any spec file and reports.

MITAuto-check passedAgent Workflows

Install Implementation Plan Generator

skills CLI
$ npx skills add withkynam/vibecode-pro-max-kit --skill vc-generate-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install withkynam/vibecode-pro-max-kit vc-generate-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/vc-generate-plan .claude/skills/vc-generate-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vc-generate-plan
GitHub stars
1.1k
Token cost
~1.4k tokens
SKILL.md length
647 words
Files
5 (incl. scripts, references)
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

Writes a project's one implementation plan at the right depth level, saved into a dated task folder alongside any spec file and reports.

  • Works in 11 steps: Read references/generate-plan.md for the… → Run date +%d-%m-%y before choosing the… → If complexity is not obvious, ask… → …
  • Turning an approved feature idea or PRD into a saved implementation plan
  • SKILL.md covers Workflow, Important Rules and Required Plan Sections
  • Runs JavaScript scripts from its folder; calls node

What it does

This skill produces the single authoritative plan file for a piece of work, reading a reference contract first and asking whether the plan should be shallow or deep when that isn't already obvious from the request. The plan is saved inside a newly created, dated task folder — under general work or under a named feature — following a fixed naming pattern, and every related file this plan produces, including any spec document and reports, stays in that same folder rather than scattered reference directories.

For large, multi-phase work it instead builds an umbrella plan plus one plan per phase, each with its own report destination. Every plan needs verification gates pulled from the project's own test documentation and explicit sections covering touchpoints, affected contracts, blast radius, verification evidence, and resume instructions, and the finished file gets checked by a bundled validation script before being considered done.

When your agent uses it

  • Turning an approved feature idea or PRD into a saved implementation plan
  • Starting a large, multi-phase program that needs an umbrella plan plus phase plans
  • Updating an existing plan file to reflect a change in scope

Example prompts

  • “Generate a deep-level plan for the new checkout redesign.”
  • “Create a lightweight plan for adding CSV export to the reports page.”
  • “Set up an umbrella plan plus phase plans for the billing migration.”

Requirements

  • Node.js to run the bundled plan-artifact validator

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Read references/generate-plan.md for the full plan contract.
  2. Run date +%d-%m-%y before choosing the filename.
  3. If complexity is not obvious, ask whether the plan is SIMPLE or COMPLEX.
  4. Save the plan inside a task folder: process/general-plans/active/{slug}_{date}/{slug}_PLAN_{date}.md (or…
  5. Read process/context/all-context.md when present to choose relevant context docs.
  6. For complex plans, read .claude/skills/vc-generate-plan/references/example-complex-prd.md before writing.
  7. Include automated and manual verification gates from process/context/tests/all-tests.md.
  8. For new or newly touched direct *_PLAN_*.md plans, include explicit sections for Touchpoints, Public Contracts, Blast Radius, Verification…
  9. Keep resume/dependency notes Markdown-structured for now; do not invent a second machine-only schema.
  10. If the work is a large multi-phase program, create or update a feature folder plan set
  11. Validate the generated artifact

What it can do on your machine

Read from SKILL.md and the folder at commit 3bcb2f9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Implementation Plan Generator loads about 1.4k tokens when it runs, and up to ~29k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 647 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~29k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from withkynam/vibecode-pro-max-kit at commit 3bcb2f9, republished under its MIT licence (© withkynam). 647 words, ~1,355 tokens.

Download SKILL.mdSave it as .claude/skills/vc-generate-plan/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
vc-generate-plan
description
Create or update implementation plans in the repo's SIMPLE or COMPLEX format. Use when turning an idea, PRD, or approved direction into a saved plan artifact.
trigger_keywords
plan, create plan, write plan, generate spec, plan artifact
layer
contract
metadata.author
vibecode-pro-max-kit
metadata.version
1.0.0

Generate Plan

Output style: write the plan answer-first with tables/bullets and a one-line TL;DR per the canonical rule — process/development-protocols/communication-standards.md.

Use this skill to produce the authoritative implementation plan artifact set for the project's work.

This skill is the canonical planning contract for the repo. Planning discipline previously spread across vc-plan now belongs here plus the plan-agent prompt.

Normal output is one plan file.

For large multi-phase programs, this skill instead defines how to create an umbrella plan plus phase-plan set under one feature folder. See process/development-protocols/phase-programs.md.

Optional input: a feature idea plus simple or complex when the user already knows the intended depth.

Workflow

  1. Read references/generate-plan.md for the full plan contract.
  2. Run date +%d-%m-%y before choosing the filename.
  3. If complexity is not obvious, ask whether the plan is SIMPLE or COMPLEX.
  4. Save the plan inside a task folder: process/general-plans/active/{slug}_{date}/{slug}_PLAN_{date}.md (or process/features/{feature}/active/{slug}_{date}/{slug}_PLAN_{date}.md). Create the {slug}_{date}/ subfolder first. Per task-folder artefact colocation, every artefact this plan produces — the plan, any {slug}_SPEC_{date}.md, reports, and references — lives INSIDE this same task folder; never write to the deprecated sibling reports/ or references/ dirs.
  5. Read process/context/all-context.md when present to choose relevant context docs.
  6. For complex plans, read .claude/skills/vc-generate-plan/references/example-complex-prd.md before writing.
  7. Include automated and manual verification gates from process/context/tests/all-tests.md.
  8. For new or newly touched direct *_PLAN_*.md plans, include explicit sections for Touchpoints, Public Contracts, Blast Radius, Verification Evidence, Test Infra Improvement Notes, and Resume and Execution Handoff.
  9. Keep resume/dependency notes Markdown-structured for now; do not invent a second machine-only schema.
  10. If the work is a large multi-phase program, create or update a feature folder plan set:
  • one umbrella/orchestration plan
  • one direct plan file per phase
  • one durable report destination per phase
  1. Validate the generated artifact:
bash
node .claude/skills/vc-generate-plan/scripts/validate-plan-artifact.mjs <plan-path>

Important Rules

  • For standard work, create exactly one plan file.
  • For a phase program, create one umbrella plan plus one direct plan file per phase.
  • Prefer process/features/{feature}/active/{slug}_{date}/ task folder when the topic maps to an existing feature folder.
  • Keep phase status honest: code-only completion is CODE DONE, not VERIFIED.
  • Make execution trust explicit inside the plan: what code or data can change, what contracts are exposed, what proof is required, and how EXECUTE should resume after compaction.
  • End with the next instruction for RIPER-5 or Cursor Plan mode.
  • Treat validation failures as blockers before presenting the plan as ready.
  • Fold red-team questions, dependency mapping, verification gates, and ambiguity checks into the generated plan itself instead of relying on a parallel plan-owner workflow.
  • Do not hide a large program inside one giant plan if execution will actually happen phase by phase.
  • Preserve the older complex-plan behavior by keeping pre-phase research and proof gates inside each phase plan; the new protocol changes the artifact shape, not the rigor.
Show full SKILL.md (192 more words)Show less

Required Plan Sections

For new or newly touched direct *_PLAN_*.md files, include all of the following sections:

  • Touchpoints — files, packages, or services that will be changed or read
  • Public Contracts — interfaces, APIs, schemas, or behaviors visible to other packages or callers
  • Blast Radius — the scope of change: how many files, which packages, and what risk class
  • Verification Evidence — table with columns | Gate / Scenario | Strategy | Proves SPEC criterion |; each row maps a test gate to the SPEC acceptance criterion it proves and the strategy (Fully-Automated / Hybrid / Agent-Probe)
  • Test Infra Improvement Notes — placeholder at plan-write time ("(none identified yet)"); updated with test infrastructure gaps found during vc-test-coverage-plan and EVL
  • Resume and Execution Handoff — required sub-fields:
    1. selected plan file path
    2. last completed phase or step
    3. validate-contract status (written / skipped with reason / pending)
    4. supporting context files loaded
    5. next step for a fresh agent picking up mid-execution
  • Validate Contract — written by vc-validate-agent after VALIDATE runs; leave a placeholder heading during PLAN (## Validate Contract\n\n(placeholder — vc-validate-agent writes this section before EXECUTE))

Use Markdown-structured sections, not a second machine-only schema. Markdown sections are stable across all agents (Claude, Codex, future systems) without requiring a parser.

© withkynam, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in .claude/skills/vc-generate-plan of withkynam/vibecode-pro-max-kit.

  • SKILL.md
  • references/example-complex-prd.md
  • references/example-simple-prd.md
  • references/generate-plan.md
  • scripts/validate-plan-artifact.mjs

Open the folder on GitHubat commit 3bcb2f9

Compare with similar skills

Implementation Plan Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Implementation Plan Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implementation Plan Generator this skillwithkynam/vibecode-pro-max-kit1.1k—~1.4kAutomated safety check: PassMIT
Foreman Grill DocsVisionForge-OU/foreman443—~1.6kAutomated safety check: PassCustom licence
Foreman PlanVisionForge-OU/foreman443—~1kAutomated safety check: PassCustom licence
Plan Architecturecoleam00/skills674—~2.4kAutomated safety check: PassMIT
Kiro SkillMicrock/ordinary-claude-skills404—~3.5kAutomated safety check: PassCustom licence
Discoveranombyte93/prd-taskmaster605—~2.4kAutomated safety check: PassMIT

Similar skills

  • Foreman Grill Docs

    VisionForge-OU/foreman

    Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory.

    443 GitHub stars~1.6k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Foreman Plan

    VisionForge-OU/foreman

    Headless implementation-plan authoring for the Foreman planning stage.

    443 GitHub stars~1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

  • Plan Architecture

    coleam00/skills

    Interactively explore HOW to approach an intent (a PRD, epic, brief, or free-form idea) and decide the high-level architecture — the approach, stack, libraries, data shape, and risks the intent left…

    674 GitHub stars~2.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Kiro Skill

    Microck/ordinary-claude-skills

    Interactive feature development workflow from idea to implementation.

    404 GitHub stars~3.5k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Discover

    anombyte93/prd-taskmaster

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery.

    605 GitHub stars~2.4k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Alignment

    Ovid/paad

    A skill your agent uses when verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope…

    131 GitHub stars~4.9k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from withkynam/vibecode-pro-max-kit

All 32 skills in this repo

  • Library Documentation Seeker

    withkynam/vibecode-pro-max-kit

    Looks up library and framework documentation through Context7 first, with bundled Node scripts as a fallback that fetch and analyze llms.txt files.

    1.1k GitHub starsUsed in 1 repo~1k tokens
    Auto-check: notes

  • Vc Sequential Thinking

    withkynam/vibecode-pro-max-kit

    Apply step-by-step analysis for complex problems with revision capability.

    1.1k GitHub starsUsed in 1 repo~854 tokens
    Auto-check passed

  • Agent Browser Automation

    withkynam/vibecode-pro-max-kit

    Drives a browser through the agent-browser CLI, using compact snapshots with element refs to keep context small in long sessions, plus video recording and cloud browsers.

    1.1k GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Context Routing Audit

    withkynam/vibecode-pro-max-kit

    Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report.

    1.1k GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Active Plan Audit

    withkynam/vibecode-pro-max-kit

    Reviews a codebase's active plan files for staleness and completion, then archives only the ones confirmed done or obsolete against the real code.

    1.1k GitHub stars~757 tokensUpdated 3 mo ago
    Auto-check passed

  • Systematic Debugging and Investigation

    withkynam/vibecode-pro-max-kit

    Forces root-cause investigation before any fix, combining a four-phase debugging method with log, CI and performance investigation techniques and a rule against unverified completion claims.

    1.1k GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Implementation Plan Generator

What does Implementation Plan Generator do?

Writes a project's one implementation plan at the right depth level, saved into a dated task folder alongside any spec file and reports. This skill produces the single authoritative plan file for a piece of work, reading a reference contract first and asking whether the plan should be shallow or deep when that isn't already obvious from the request. The plan is saved inside a newly created, dated task folder — under general work or under a named feature — following a fixed naming pattern, and every related file this plan produces, including any spec document and reports, stays in that same folder rather than scattered reference directories.

When should I use Implementation Plan Generator?

Implementation Plan Generator fits situations like: turning an approved feature idea or PRD into a saved implementation plan; starting a large, multi-phase program that needs an umbrella plan plus phase plans; updating an existing plan file to reflect a change in scope.

How do I install Implementation Plan Generator in Claude Code?

Run `npx skills add withkynam/vibecode-pro-max-kit --skill vc-generate-plan -a claude-code`. Or copy the skill folder (.claude/skills/vc-generate-plan in withkynam/vibecode-pro-max-kit) into .claude/skills/vc-generate-plan in your project. Claude Code loads it when a task matches its description.

How do I install Implementation Plan Generator in Codex?

Run `npx skills add withkynam/vibecode-pro-max-kit --skill vc-generate-plan -a codex`. Or copy the skill folder (.claude/skills/vc-generate-plan in withkynam/vibecode-pro-max-kit) into .agents/skills/vc-generate-plan in your project. Codex loads it when a task matches its description.

Can I use Implementation Plan Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add withkynam/vibecode-pro-max-kit --skill vc-generate-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vc-generate-plan, .gemini/skills/vc-generate-plan, .github/skills/vc-generate-plan and .opencode/skills/vc-generate-plan in your project.

What does Implementation Plan Generator need to run?

Going by SKILL.md and its folder, Implementation Plan Generator needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js to run the bundled plan-artifact validator.

Does Implementation Plan Generator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Implementation Plan Generator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Implementation Plan Generator use?

Implementation Plan Generator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Implementation Plan Generator use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 28k tokens, read only when the agent opens those files.

What are the alternatives to Implementation Plan Generator?

Skills that share tags, products or a category with Implementation Plan Generator: Foreman Grill Docs (VisionForge-OU/foreman, 443 stars), Foreman Plan (VisionForge-OU/foreman, 443 stars), Plan Architecture (coleam00/skills, 674 stars) and Kiro Skill (Microck/ordinary-claude-skills, 404 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implementation Plan Generator?

withkynam (a GitHub user) maintains it in withkynam/vibecode-pro-max-kit, which has 1,145 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on June 21, 2026.

Source: withkynam/vibecode-pro-max-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.