What is spec_analyst?

A senior software-analysis process that reads a project's documentation and creates one master plan. It identifies whether the project is a website, an app, or both, then records the technology and architecture decisions it can justify from the documents.

Use it to inspect documentation, classify the platform, record supporting keywords and locations, identify missing information, and produce a root-level MASTER_PLAN.md file.

Projects with incomplete or scattered documentation are easy to classify incorrectly. The required scoring and questions make missing information and the reasoning behind the plan visible.

spec_analyst — Skill for Claude Code and Codex by coreline-ai

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.

Any agent

npx skills add coreline-ai/antigravity_gemini_skills --skill spec_analyst

Clone the repo

git clone --depth 1 https://github.com/coreline-ai/antigravity_gemini_skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/coreline-ai/antigravity_gemini_skills/spec_analyst/github.svg)](https://agentmods.dev/skills/coreline-ai/antigravity_gemini_skills/spec_analyst)

Your own site

<a href="https://agentmods.dev/skills/coreline-ai/antigravity_gemini_skills/spec_analyst"><img src="https://agentmods.dev/badge/skills/coreline-ai/antigravity_gemini_skills/spec_analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/coreline-ai/antigravity_gemini_skills/spec_analyst"><img src="https://agentmods.dev/badge/skills/coreline-ai/antigravity_gemini_skills/spec_analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01122
Opus 5	$0.00000	$0.00561
Sonnet 5	$0.00000	$0.00224
Haiku 4.5	$0.00000	$0.00112

Measured 12d ago against content hash b19a4e2aa286, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

spec_analyst 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 12d 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.

.agent/skills/spec_analyst/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📡 Senior Architect & Analyst Skill (v2)

Role

docs/ 폴더를 유일한 입력 소스로 읽고,
프로젝트 플랫폼(Web/App/Hybrid)과 기술스택/아키텍처를
규칙 기반으로 확정하여,
루트에 MASTER_PLAN.md(단일 계약서)를 생성합니다.

출력은 반드시 MASTER_PLAN.md 하나로 수렴합니다.

Platform Detection Rule (MANDATORY)

1. Keyword Scoring (점수화)

WEB 키워드 발견 시 +2
- SEO, SSR, CMS, Admin, Dashboard, URL, Webhook, Browser, Landing, Marketing Site
APP 키워드 발견 시 +2
- App Store, Play Store, Push, Permission, Offline, Camera, Sensor, BLE, GPS, Background Service

2. Decision Rule (판정)

WEB ≥ 4 and APP < 4 → PLATFORM_MODE = WEB
APP ≥ 4 and WEB < 4 → PLATFORM_MODE = APP
WEB ≥ 4 and APP ≥ 4 → PLATFORM_MODE = HYBRID
애매한 경우(둘 다 0~2점대):
- MCP(ChatGPT) 질의 후
- 여전히 불명확하면 보수적으로 HYBRID

3. Hard Constraints

"감으로 판단" 금지
반드시 점수 합산 결과와 **근거 키워드(문서 내 위치/문장)**를 MASTER_PLAN.md에 기록

✅ INSERT: Gap-driven Q&A (Field Completion Protocol)

목적

docs/ 문서가 불완전할 때(필수 정보 누락), 추측으로 진행하지 않고 **최소한의 문답(Q&A)**을 통해 MASTER_PLAN.md를 흔들림 없이 생성하기 위함입니다.

A. 필수 필드 (Required Fields)

Project Identity: PLATFORM_MODE, PRIMARY_TYPE, LANGUAGE
Platform & Repo Flags: BACKEND_REQUIRED, REPO_LAYOUT
Tech Stack: Frontend, Backend, Database
Platform Detection Evidence: WEB_SCORE, APP_SCORE, EVIDENCE

B. Gap Detection (누락 감지 규칙)

docs/PRD.md를 읽고 Scoring 수행.
점수 불충분(WEB<4, APP<4)하거나 BACKEND_REQUIRED가 모호하면 GAP 판정.

C. Question Generation Rule

1회 최대 5문항 (3문항 권장)
YES/NO 또는 선택형(A/B/C)만 허용
"모르겠다(C)" 옵션과 기본값 필수

D. Defaulting Policy (응답 없을 시)

PLATFORM_MODE: HYBRID (보수적)
BACKEND_REQUIRED: NO (명시 없으면 최소화)
REPO_LAYOUT: APPS_SPLIT

E. Output Rule

QNA_REQUEST.md 생성/출력
답변 수집 후 MASTER_PLAN.md Evidence에 병합

MCP(ChatGPT) Usage (Optional Brain)

When to Call

PRD에 기술스택이 명시되지 않은 경우
DB/ERD 초안이 필요한 경우
복잡한 비즈니스 로직의 엣지케이스가 필요한 경우

Prompt Contract

버전 포함(Pinned)
폴더 트리 포함
대안 1개 포함
리스크/폴백 포함
JSON + Markdown 병행

Read the full file on GitHub · 122 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.

12d ago First seen · 122 lines · 0 tokens per session scan A b19a4e2aa286

Subscribe to this mod's changes

spec_analyst is a skill published in the GitHub repository coreline-ai/antigravity_gemini_skills (2 stars, last pushed 4mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 1,122 tokens. 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.

Planning agent-skills ai ai-agent antigravity coreline-ai

spec_analyst