writing-nova-skill

writing-nova-skill is a skill for Claude Code, Codex from TeamSPWK/nova. It costs 59 tokens per session (1,126 once invoked), scanned A, original, MIT.

A writing guide for creating or revising Nova skills, which are reusable instructions for an AI coding agent.

In plain words
What is it for?
Use it when adding a new SKILL.md file, changing a skill description, or adding or revising a Nova skill.
Why use it?
It keeps the skill’s trigger description focused on when it should run, while putting working rules in the main instructions. It also requires a test prompt for checking that the skill activates correctly.

Skill for Claude CodeCodex

Part of the nova plugin — 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/teamspwk/nova/writing-nova-skill
Any agent
npx skills add TeamSPWK/nova --skill writing-nova-skill
Clone the repo
git clone --depth 1 https://github.com/TeamSPWK/nova

Made for: Claude Code, Codex.

Or install nova, the plugin that ships this one along with the rest of its 14 skills, 19 commands, 6 agents, 5 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing-nova-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/teamspwk/nova/writing-nova-skill.svg)](https://agentmods.dev/skills/teamspwk/nova/writing-nova-skill)
Your own site
<a href="https://agentmods.dev/skills/teamspwk/nova/writing-nova-skill"><img src="https://agentmods.dev/badge/skills/teamspwk/nova/writing-nova-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.01126
Opus 5 $0.00030 $0.00563
Sonnet 5 $0.00012 $0.00225
Haiku 4.5 $0.00006 $0.00113

Measured 5d ago against content hash 0ecce29b710c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-nova-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/writing-nova-skill/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing a Nova Skill

Nova 스킬을 작성/수정할 때 따라야 할 규약. Jesse Vincent(obra/superpowers)의 실측 발견"description이 workflow를 요약하면 Claude가 본문 대신 description을 따라간다" — 을 Nova에 흡수한 메타-스킬.

핵심 규약

1. Description = When-to-use only

description은 언제 발동하는가만 기술한다. HOW(동작 방식)은 본문으로.

금지:

  • , 파이프라인, 4단, Explorer×3 같은 단계 열거
  • "X로 Y를 Z한다" 형식의 동작 기술 전체
  • "엔진", "시스템"만 선언하는 정체성 홍보 (예: "Nova XXX 엔진 —")

요구:

  • "...할 때.", "...가 필요한 경우" 같은 트리거 표현
  • MUST TRIGGER: ... 섹션에 트리거 조건 3개 이상
  • 사용자 요청 패턴 포함 (예: "사용자가 /nova:xxx 호출 시")

예시 (evaluator):

  • ❌ "Nova Adversarial Evaluator — Nova Quality Gate의 핵심 검증 엔진. 독립 서브에이전트로 코드를 적대적 관점에서 검증."
  • ✅ "코드 구현을 적대적 관점으로 검증해야 할 때. — MUST TRIGGER: /run, /check, /review 내부에서 독립 서브에이전트로 호출, 스프린트 완료 직후, 커밋 전 Evaluator PASS 필요 시."

2. 본문 구조

  1. 한 문단 — 스킬 목적 + Nova 5기둥 내 위치
  2. ## 핵심 원칙 — 설계 결정 3~5개
  3. ## 적용 규칙 (on-demand 로드) — 참조하는 nova-rules §N 번호
  4. ## 오케스트레이션 추적mcp__plugin_nova_nova__orchestration_update 호출 의무 (해당 시)
  5. 예시 / 안티패턴

3. 트리거 회귀 테스트 (MUST)

새 스킬 추가 시 tests/skill-triggering/prompts/{name}-positive.txt 제출 의무.

  • positive: 이 스킬이 반드시 발동해야 할 사용자 프롬프트 1개
  • negative (선택): 이 스킬이 발동하면 안 되는 유사 맥락 프롬프트

tests/test-skill-triggering.sh가 각 skills/*/SKILL.md에 대응하는 positive fixture 존재를 강제한다. 누락 시 CI FAIL.

실제 LLM 트리거 검증은 Nova 개발자 전용 dev/skills/field-test/로 수동 수행 (사용자 플러그인에는 미포함).

4. 동기화 체크리스트 (CLAUDE.md와 일치)

새 스킬 추가 시:

  1. hooks/session-start.sh 커맨드 목록 영향 여부 확인 (커맨드 아니면 대개 불필요)
  2. tests/test-scripts.sh의 description lint 통과 확인
  3. docs/nova-meta.jsonbump-version.sh가 자동 재생성 (수동 편집 금지)
  4. tests/skill-triggering/prompts/{name}-positive.txt 제출

안티패턴

  • description을 짧게 만들려고 트리거를 생략한다 → Claude가 언제 쓸지 판단 못 함
  • "5인 적대 평가자", "3단 파이프라인" 같은 숫자 홍보 → 본문 스킵 유발
  • 여러 목적을 한 스킬에 몰아넣는다 → 트리거 모호, 본문 비대

근거 (왜 이 규약이 존재하는가)

  • obra/superpowers/skills/writing-skills/SKILL.md"Testing revealed that when a description summarizes the skill's workflow, Claude may follow the description instead of reading the full skill content"
  • memory/project_nova_competitive_analysis_2026_04_23.md — 경쟁 분석 결과 9개 Nova SKILL 중 5개가 이 안티패턴에 해당, Tier 1.1에서 일괄 리팩터
  • Nova 5기둥 중 협업 기둥 — 스킬이 제 때 발동하지 않으면 에이전트 협업이 붕괴한다

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 70 lines · 59 tokens per session scan A 0ecce29b710c

Subscribe to this mod's changes

writing-nova-skill is a skill published in the GitHub repository TeamSPWK/nova (2 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 1,126 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories