What is rescue-operator?

A recovery and reorganising skill for messy novel-project folders. It detects damaged text encoding, duplicate files, and misplaced material, then prepares a standard folder structure.

It is for scanning folders, fixing unreadable text, finding duplicates, and arranging manuscripts, reference material, outlines, and raw drafts.

It helps restore a disorganised project without permanently deleting the original files. It also previews changes and creates snapshots so work can be rolled back.

How PTCuong-1102/story-architect-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to PTCuong-1102/story-architect-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PTCuong-1102/story-architect-mcp/main/.agents/skills/rescue-operator/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/PTCuong-1102/story-architect-mcp

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/ptcuong-1102/story-architect-mcp/rescue-operator/github.svg)](https://agentmods.dev/skills/ptcuong-1102/story-architect-mcp/rescue-operator)

Your own site

<a href="https://agentmods.dev/skills/ptcuong-1102/story-architect-mcp/rescue-operator"><img src="https://agentmods.dev/badge/skills/ptcuong-1102/story-architect-mcp/rescue-operator/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/ptcuong-1102/story-architect-mcp/rescue-operator"><img src="https://agentmods.dev/badge/skills/ptcuong-1102/story-architect-mcp/rescue-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,829 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	$0.00148	$0.01829
Opus 5.5	$0.00059	$0.00732
Sonnet 5.5	$0.00030	$0.00366
Haiku 4.5	$0.00015	$0.00183

Measured 3d ago against content hash 812cace885c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rescue-operator 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 3d 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.

.agents/skills/rescue-operator/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rescue Operator — Chuyên gia cứu hộ & tái cấu trúc dự án

Kỹ năng này biến AI thành Chuyên gia cứu hộ và tái cấu trúc dự án tiểu thuyết: tiếp nhận những thư mục bản thảo "thảm họa" (file rải rác, encoding hỏng, trùng lặp) và đưa chúng về chuẩn cấu trúc story-architect-mcp v0.7.0 một cách an toàn tuyệt đối — luôn tự động tạo snapshot trước khi sửa đổi để có thể quay lại bất cứ lúc nào.

🎯 NGUYÊN TẮC HOẠT ĐỘNG CỐT LÕI

AN TOÀN LÀ TRÊN HẾT (Safety first):
- Mọi thao tác di chuyển/đổi tên file hay ghi đè chỉ thực hiện sau khi có snapshot hoàn chỉnh.
- Không bao giờ chạy confirm: true mà chưa cho tác giả xem preview (confirm: false).
QUÉT TRƯỚC — HÀNH ĐỘNG SAU (Scan first, act later):
- Luôn bắt đầu bằng story_scan_messy_project để có bức tranh toàn cảnh: loại file, encoding, độ tương đồng và các file trùng lặp.
ENCODING LÀ RÀO CẢN ĐẦU TIÊN (Encoding gate):
- File tiếng Việt sai encoding (mojibake) phải được phát hiện và giải mã đúng trước khi xử lý nội dung.
KHÔNG BAO GIỜ GHI ĐÈ DỮ LIỆU GỐC (Never overwrite originals):
- File gốc chỉ được di chuyển (move) vào drafts_raw/, không xóa vĩnh viễn.

📋 WORKFLOW CỨU HỘ DỰ ÁN (5 BƯỚC)

Bước 1: Thiết lập dự án đích (Project Setup)

Gọi story_set_project với projectPath trỏ tới thư mục cần cứu hộ (bật force: true nếu thư mục chưa theo chuẩn); có nhiều dự án đang mở thì kiểm tra bằng story_list_projects (v0.3.0) trước.
Nếu thư mục mới hoàn toàn, dùng story_init để tạo cấu trúc chuẩn.

Bước 2: Quét & phát hiện sự cố toàn diện (Comprehensive Scan)

Gọi story_scan_messy_project với path và detectDuplicates: true.
Đánh giá danh sách encoding lỗi (Windows-1252/ISO-8859-1) và các cặp file trùng lặp.

Bước 3: Lập kế hoạch tái cấu trúc (Dry-run Preview)

Gọi story_auto_refactor_structure với strategy (mặc định từ v0.6.0 là auto_profile — tự chọn hành vi theo bố cục nhận diện; còn by_chapter/by_arc/chronological nếu muốn ép kiểu) và confirm: false.
từ v0.7.0 — luồng phán đoán AI (khuyến nghị khi bố cục quirks): gọi story_export_layout_brief → đọc brief (cây file + trích nội dung + heuristic profile) → phán đoán bằng NGỮ CẢNH (chương không từ khóa "Chương", tên file tự đặt, truyện thư từ/ngày tháng...) → nộp story_apply_layout_verdict (chapters có startLine 1-based; hình dạng JSON đúng → server tự xác thực) → chạy lại refactor: preview sẽ nhắc "🧠 Phán đoán AI". Để quay về heuristic: xóa .story/layout-verdict.json.
Bố cục từng dạng tác giả bố trí trước khi cài tool được nhận diện tự động: thư mục arc tự đặt tên ("Quyển 3", "phan 2"...) → map arc_XX; chương phẳng → đánh số lại; một file lớn chứa cả quyển ("Chương N"/"Chapter N"/"第N章" — cả số chữ "mười hai", La Mã, Hán tự) → ✂️ TÁCH thành ch_XXX (bản gốc bảo toàn drafts_raw/). Trình bày bảng preview chi tiết cho tác giả duyệt.

Read the full file on GitHub · 91 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.

3d ago Changed · +3 lines 812cace885c2
6d ago Changed · +1 lines · +148 tokens per session 2cb53d94868e
1mo ago First seen · 87 lines · 0 tokens per session scan A d7be784d001c

Subscribe to this mod's changes

rescue-operator is a skill published in the GitHub repository PTCuong-1102/story-architect-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 148 tokens to every session and 1,829 once invoked, about $0.0006 per session on Opus 5.5. 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.

Documents Writing and docs

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

apify-youtube-transcript-scraper

Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.

sickn33/agentic-awesome-skills · 48 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

story-architect-mcp: Skill for Claude Code