Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Implementation Plan

ASecurity

Plan implementation, research an API or architecture choice, or challenge a plan.

10 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentspythongotestinggitapisecuritydocumentation

Works with

api

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/7/2026

$npx -y skills add fmind/dot --skill implementation-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Implementation Plan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Implementation Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-implementation-plan/badge)](https://www.skillsdirectory.com/skills/fmind-implementation-plan)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: implementation-plan
description: "Plan implementation, research an API or architecture choice, or challenge a plan."
license: MIT
metadata:
  kind: task
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/implementation-plan
  created: "2026-08-08"
  updated: "2026-10-07"
---

# Implementation Plan

Design the smallest sequence of independently verifiable vertical slices that satisfies accepted requirements, or challenge an existing plan before it is executed; implementation follows the accepted scope and applicable stack skills.

## Workflow

To write a plan, follow the steps below. To challenge an existing plan, read only [plan-review](references/plan-review.md); to settle an unfamiliar API or architecture choice first, read [research-brief](references/research-brief.md).

1. **Read the accepted scope**: identify the outcome, constraints, authorization, and unresolved decisions; stop planning when material options still need a user decision.
1. **Inspect the implementation**: verify relevant paths, interfaces, dependencies, tests, and current work; preserve user changes and reuse existing mechanisms.
1. **Choose useful slices**: order the smallest independently verifiable changes by dependency; identify shared files and real compatibility or migration risks.
1. **Specify proof**: each slice names its outcome, affected files, dependencies, implementation steps, focused checks with expected results, and objective acceptance criteria. Record decisions (signatures, files, test names and assertions, spec values), not implementation bodies; write code only where an algorithm would otherwise be ambiguous.
1. **Review the plan**: map every requirement to a slice, verify unfamiliar APIs, remove speculative flexibility, and state any decision that truly blocks execution. Name the input classes or failure modes the requirements imply but no slice tests, and add each test to its owning slice.
1. **Deliver at the right scale**: use a compact task table for linear work; add interface contracts, concurrency, rollout, or rollback details where needed, retaining every applicable risk and proof boundary. A plan much longer than its requirements is transcribing the program; replace bodies with signatures and assertions.
1. **Hand off**: identify the first executable slice and the full project gate.

## Gotchas

- **Planning is read-only by default**: Do not edit source, create issues, install dependencies, or deploy while planning unless the user explicitly asked.
- **Apply the deletion test**: An abstraction earns its place only when removing it would spread meaningful complexity or violate a real seam; delay a generalized adapter until a second concrete variation exists.
- **Prefer deep modules**: Prefer modules that hide decisions over pass-through layers, and put tests and callers across the same real seam.

## Task guides

<!-- guides:start -->

- [plan-review](references/plan-review.md): Challenge a product or implementation plan: assumptions, failure modes, trade-offs, and a GO or NO-GO verdict.
- [research-brief](references/research-brief.md): Decision-ready research brief for an unfamiliar API or architecture choice: evidence table, options, and proof boundaries.

<!-- guides:end -->

## Documentation

- Adapted from [Superpowers writing-plans](https://github.com/obra/superpowers/blob/8ca22dba9a94f28898bbce59f2537ff4d87c747d/skills/writing-plans/SKILL.md), [Spec Kit plan template](https://github.com/github/spec-kit/blob/684b3d8e05263a7c1948d3d0699ab1cb4f77c3d5/templates/plan-template.md), [codebase design](https://github.com/mattpocock/skills/blob/84fdeffd12f2ee307994d1eb6feb48173b6e0502/skills/engineering/codebase-design/SKILL.md), [domain modeling](https://github.com/mattpocock/skills/blob/84fdeffd12f2ee307994d1eb6feb48173b6e0502/skills/engineering/domain-modeling/SKILL.md).
- Companion skills: [python-testing](../python-testing/SKILL.md) (red-green proof), [threat-model](../threat-model/SKILL.md) (security design risk).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →