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

Change The Spec

ASecurity

How to change the DSoR specification safely — adding, splitting, rewording, or removing a requirement under specs/dsor/, or changing a JSON Schema or example under packages/spec/. Covers id rules (never reuse, never renumber), one MUST per id, regenerating requirements.json, keeping schemas, examples, tests, and history in step. Load before editing anything in specs/dsor/ or packages/spec/schemas/.

6 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add panaversity/dsor --skill change-the-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Change The Spec?

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

Security grade badge for Change The Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/panaversity-change-the-spec/badge)](https://www.skillsdirectory.com/skills/panaversity-change-the-spec)

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

Download Zip
Files
SKILL.md
---
name: change-the-spec
description: How to change the DSoR specification safely — adding, splitting, rewording, or removing a requirement under specs/dsor/, or changing a JSON Schema or example under packages/spec/. Covers id rules (never reuse, never renumber), one MUST per id, regenerating requirements.json, keeping schemas, examples, tests, and history in step. Load before editing anything in specs/dsor/ or packages/spec/schemas/.
metadata:
  version: "1.0.0"
---

# Changing the specification

A requirement id is a promise to everyone who wrote a test against it. These rules
keep that promise.

## The id rules (AGENTS.md → decisions 2, 3, 4)

- **One id, one MUST.** Exactly one `MUST` or `MUST NOT`. No `SHOULD`, no `MAY`.
  Advice goes in an ordinary sentence below the rules, with no id.
- **Never reuse, never renumber.**
  - Splitting `DSOR-DEL-04` gives `DSOR-DEL-04a`, `DSOR-DEL-04b`. The bare `04`
    disappears.
  - A new requirement takes the next free number in its area (`DSOR-DEL-11`).
  - A removed requirement leaves a gap. Say so in `research/history.md`.
- **The line format is exact**, because the guard parses it:

  ```text
  - **[DSOR-AREA-NNx · L2]** One sentence with one MUST.
  ```

  Levels: `L1`, `L2`, `L3`, `RP`, `STACK`. The separator is a middle dot `·`.
- **Rewording that changes meaning is a new requirement.** Rewording that only
  clarifies keeps the id. When unsure, it changed the meaning.

## Steps

1. Edit the prose in `specs/dsor/`. Keep the section shape of the
   `write-for-learners` skill: **In plain words**, **Why it matters**, example,
   **The rules**, **Common mistake**.
2. If a rule now refers to a bound ("within the bound of §44"), add the row to the
   table in §44 with an L2 and an L3 ceiling.
3. If the change touches the shape of an artifact, edit the schema in
   `packages/spec/schemas/` **and** the example in `packages/spec/examples/`, and add
   a rejection case to `packages/spec/src/schemas.test.ts` titled with the
   requirement id. If the schema's meaning changed, the URN version changes too
   (decision 11), and Appendix A's table is updated.
4. If the change touches CEL, update Appendix B and the vectors in
   `packages/spec/examples/control.example.json`, and run the CEL tests.
5. Update the invariants table in §45 and the verification table in §47 if the change
   belongs there.
6. Run `pnpm guard --write`, then `pnpm check`.
   - `one-must` → split the requirement.
   - `known-id` → some document still names an id you removed or mistyped.
   - `link-target` → a heading changed and a link to it did not.
   - `registry-current` → you forgot `--write`.
7. Add a dated paragraph to `research/history.md`: what changed and why. If a decision
   changed, add or supersede an entry in AGENTS.md → Decisions.
8. If tests already name an id you split or removed, update their titles in the same
   pull request.

## Versioning the specification

Editorial change (wording, examples, learner blocks; no requirement text changes):
patch, `1.3.1` → `1.3.2`. Any requirement added, removed, or changed in meaning:
minor, `1.3.x` → `1.4.0`. Update `SPEC_VERSION` in `packages/spec/src/index.ts`, the
`version` in `scripts/guard-spec.mjs`, the front matter of every file in
`specs/dsor/`, and `TARGET_SPEC_VERSION` in `packages/dsor/src/index.ts` when the
implementation follows.

Attribution

panaversitypanaversity
View sourceMore from panaversity →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →