Borrowing it
Nothing to install: this file belongs to web-casa/DeepSeek-Harness-Desktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/web-casa/DeepSeek-Harness-Desktop/main/.agents/skills/asc-whats-new-writer/SKILL.mdgit clone --depth 1 https://github.com/web-casa/DeepSeek-Harness-DesktopWrote 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.
[](https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-whats-new-writer)<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-whats-new-writer"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-whats-new-writer/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.
<a href="https://agentmods.dev/skills/web-casa/deepseek-harness-desktop/asc-whats-new-writer"><img src="https://agentmods.dev/badge/skills/web-casa/deepseek-harness-desktop/asc-whats-new-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00045 | $0.01643 |
| Opus 5 | $0.00023 | $0.00822 |
| Sonnet 5 | $0.00009 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
asc-whats-new-writer 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 13d 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.
This is a copy
100% identical to asc-whats-new-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asc What's New Writer
Generate engaging, localized release notes from flexible input. Optionally pair with promotional text updates.
Preconditions
- Metadata pulled locally into canonical files via
asc metadata pull --app "APP_ID" --version "1.2.3" --dir "./metadata". OR: user provides keywords manually. - Auth configured for upload (
asc auth loginorASC_*env vars). - The primary locale is
en-USunless the user specifies otherwise.
Before You Start
- Read
references/release_notes_guidelines.mdfor tone, structure, and examples. - Identify the latest version directory under
metadata/version/(highest semver). Use this for all metadata reads. - Enumerate existing locales by listing the JSON files in that version directory.
Phase 1: Gather Input
Accept one of three input modes (auto-detect):
Git Log
Parse commits since the last tag:
# Find latest tag
git describe --tags --abbrev=0
# List commits since that tag
git log $(git describe --tags --abbrev=0)..HEAD --oneline --no-merges
Filter out noise: merge commits, dependency bumps, CI changes, formatting-only commits. Extract user-facing changes.
Bullet Points
User provides rough bullets like:
- "improved search"
- "fixed crash on launch"
- "added sleep timer"
Free Text
User describes changes conversationally:
"We made search faster, fixed that annoying crash when you open the app, and added a sleep timer feature"
The skill extracts and structures the changes from the text.
No Input Provided
Prompt the user: "What changed in this release? You can paste git log output, bullet points, or just describe the changes."
Phase 2: Draft Notes (Primary Locale)
Step 1: Classify Changes
Group changes into sections per the guidelines:
- New — new features or capabilities
- Improved — enhancements to existing features
- Fixed — bug fixes users would notice
Omit empty sections. If all changes are fixes, only show "Fixed."
Step 2: Write Benefit-Focused Copy
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 186 lines · 45 tokens per session scan A 592c33a56caf
asc-whats-new-writer is a skill published in the GitHub repository web-casa/DeepSeek-Harness-Desktop (121 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 1,643 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to asc-whats-new-writer, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
content-translator
Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support for teams working across language barriers.
tauri-expert
Expert in Tauri framework, Rust backend, web frontend integration, and lightweight desktop applications. Use when the user mentions desktop, Rust, web, cross platform, or performance, or when the task involves Tauri Architecture, Tauri vs Electron, Core Components, or Security Features.
skill_creator
An interactive workflow for creating, importing, and adapting Tiangong skills, which are instruction packages for an AI agent.
volcengine_video
Instructions for generating videos with Volcengine’s Seedance model from a text description.
internet_search
Instructions for using a local search script to retrieve current web results as JSON, including titles, links, summaries, and sources.
dsh-translate-docs
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.