Skip to content
Back to skills

Specdd Plan

ASecurity

Use when Claude Code is explicitly asked for a plan, or must resolve unclear SpecDD scope, write authority, public-contract risk, affected files, or verification before safe implementation; do not trigger for ordinary authorized changes.

  • 4 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 12, 2026
businessgotesting

Works with

  • claude code

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 12, 2026

npx -y skills add aibot88/sec_skill_store --skill specdd-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Specdd Plan?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Specdd Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aibot88-specdd-plan/badge)](https://www.skillsdirectory.com/skills/aibot88-specdd-plan)

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

Download with Pro
SKILL.md
---
name: specdd-plan
description: Use when Claude Code is explicitly asked for a plan, or must resolve unclear SpecDD scope, write authority, public-contract risk, affected files, or verification before safe implementation; do not trigger for ordinary authorized changes.
license: Apache-2.0
---

# SpecDD Plan

Use this skill when the user asks for a plan, or when unclear scope, authority,
public contracts, risk, or verification would make immediate implementation
unsafe. Do not edit files while planning.

## Bootstrap Resolution

Before doing anything else in the target project, read bootstrap files in this exact order:

1. `.specdd/bootstrap.md`
2. `.specdd/bootstrap.project.md`, if it exists
3. `.specdd/bootstrap.local.md`, if it exists

Apply them in that order. Later files may narrow or specialize earlier rules, but must not silently weaken project contracts, inherited constraints, or write authority.

## Spec Chain Resolution

Before planning, editing, reviewing, testing, or reporting on a target:

1. Identify the target path, task, behavior, or changed files.
2. Resolve the effective spec chain using the active bootstrap rules.
3. Include same-directory basename specs when applicable.
4. Walk ancestor specs from the selected content root to the target.
5. Read explicit `References` only when they affect the requested work.
6. Identify the nearest local spec that grants write authority before any edit.

Do not infer authority from similar filenames, nearby files, symbols, module names, or conventions unless the active bootstrap or a governing spec explicitly defines that mapping.

## Workflow

1. Summarize the target scope and applicable spec chain.
2. Identify files or specs likely to change.
3. Identify verification and blockers.
4. Summarize the smallest safe implementation path.

## Plan Contents

Include:

- Target scope and applicable spec chain.
- Files or specs likely to change.
- Write authority and any unclear authority.
- Relevant `Must`, `Must not`, `Forbids`, `Scenario`, `Tasks`, and `Done when` constraints.
- Verification likely needed.
- Risks, conflicts, or questions that block safe implementation.

Keep the plan practical. Do not propose broad refactors or new contracts unless
the active specs or user request require them.

Files in this skill

  • SKILL.md2.2 KB
  • source.json744 B

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.