Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Dr Plan Steps

ASecurity

Convert an approved SPEC.md into an ordered, checkable step list (CHECKLIST.md) where each step has one done-criterion. Use after SPEC.md, and again (partial re-plan) after a validation failure.

142 stars
0 votes
0 copies
0 views
Added 9/19/2026
testingpythongogitdocumentation

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add AHepi/DeepReason --skill dr-plan-steps --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dr Plan Steps?

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

Security grade badge for Dr Plan Steps
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ahepi-dr-plan-steps/badge)](https://www.skillsdirectory.com/skills/ahepi-dr-plan-steps)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: dr-plan-steps
description: Convert an approved SPEC.md into an ordered, checkable step list (CHECKLIST.md) where each step has one done-criterion. Use after SPEC.md, and again (partial re-plan) after a validation failure.
---

# Plan the steps

Input: SPEC.md (re-read REQUEST.md and SPEC.md in full first). Output:
CHECKLIST.md — the complete ordered path from the current tree to the
accepted change. Execution will do NOTHING that is not a step here, so
missing steps here means missed work later. Plan against that.

## Ordering rules

1. Dependencies first, verification interleaved: a step that writes a
   test precedes the step whose change it guards; a step that runs a
   check follows immediately after the change it checks — not batched
   at the end where failures lose their cause.
2. One step = one action with ONE done-criterion (a command and its
   expected output, or "file exists containing <marker>"). If a step
   needs the word "and", split it.
3. Include the boring steps that get forgotten — they are the point of
   this skill: creating directories, `chmod +x`, updating the ladder
   or docs SPEC says to update, retiring an occupied run root (rename
   commit FIRST), the subsystem test ring, the FULL gate
   (`pytest tests/ -q -n 4`, expect 0 failed), the tranche commit
   with its message, the push with retry, and the final
   `git status --porcelain` cleanliness check.
4. Every step cites its spec item (S-number). A step with no S-number
   is scope creep — delete it or send it to PARKED.md.
5. **Scope from the map before planning steps.** Open
   `docs/map/INDEX.md`, resolve the change to `DR-SUB-`/`DR-CON-`/
   `DR-SEAM-` ids, and read the seam document before the subsystem
   ones — the file is `docs/map/SEAM-<a>-x-<b>.md`, sides in
   alphabetical order, and the worked recipe for a seam change is
   `docs/map/REC-change-a-seam.md`. Name those ids in CHECKLIST.md's
   header so execution starts from the same map the plan was built on.
   A change whose ids you cannot name is a change you have not scoped.
6. **Plan the map update as part of the step that changes behaviour**,
   never as a trailing "update docs" step. A trailing documentation
   step is the one that gets dropped when a tranche runs long. If a
   seam document must be CREATED, that is its own step, and it comes
   BEFORE the code steps — writing down the agreement is how you find
   out whether you understand it.
7. Mark checkpoint steps `[COMMIT]` at natural boundaries (at minimum:
   after tests-written, after each spec item lands, after the gate) —
   rationale canonical in `dr-drive-harness` §1.

## CHECKLIST.md template

    # Checklist for: <request headline>
    State: next=<step n> blockers=<none | one line>   <- refreshed at
    every commit; a fresh session resumes from this line alone
    Re-read REQUEST.md + SPEC.md before every step. Execute strictly
    in order. One step per dr-execute-step invocation.

    - [ ] 1. (S1) <action>
          done-when: <command> -> <expected>
    - [ ] 2. (S1) [COMMIT] <action>
          done-when: ...
    - [ ] 3. (S2) ...
    ...
    - [ ] N-2. (all) Map check: python tools/docs_verify.py
          done-when: 0 failed, and --audit reports 0 findings
    - [ ] N-1. (all) Full gate: pytest tests/ -q -n 4
          done-when: output ends "N passed, 0 failed" (paste it)
    - [ ] N. (all) [COMMIT] push and confirm clean tree
          done-when: git status --porcelain is empty AND branch head
          is on origin

## Re-planning after a validation failure

Touch only the steps implicated by the failure: append new steps
(N+1...) that correct course; never rewrite history of checked steps —
their pasted outputs are the audit trail.

## Exit criteria

- CHECKLIST.md committed and pushed; every S-number covered by >=1
  step; every step has a done-criterion.
- No code changed in this phase.
- Return to the orchestrator.

Attribution

AHepiAHepi
View sourceMore from AHepi →
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

Screen Reader Testing

Practical guide to testing web applications with screen readers for comprehensive accessibility validation.

393431 votes

Python Testing

使用pytest、TDD方法、夹具、模拟、参数化和覆盖率要求的Python测试策略。

2456590 votes

Tdd Workflow

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。

2456590 votes

Springboot Tdd

使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。

2456590 votes

Eval Harness

克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则

2456590 votes
View all in testing →