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.
npx skills add Chip-G0202/PaperEcho --skill paperecho-zotero-desktopgit clone --depth 1 https://github.com/Chip-G0202/PaperEchoWrote 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/chip-g0202/paperecho/paperecho-zotero-desktop)<a href="https://agentmods.dev/skills/chip-g0202/paperecho/paperecho-zotero-desktop"><img src="https://agentmods.dev/badge/skills/chip-g0202/paperecho/paperecho-zotero-desktop/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/chip-g0202/paperecho/paperecho-zotero-desktop"><img src="https://agentmods.dev/badge/skills/chip-g0202/paperecho/paperecho-zotero-desktop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01330 |
| Opus 5 | $0.00030 | $0.00665 |
| Sonnet 5 | $0.00012 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
paperecho-zotero-desktop 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PaperEcho - Zotero Desktop
Use this skill for the repository's desktop-only Zotero literature review path. Keep work narrow: prefer Stage2-only benchmark and targeted tests, and run a full workflow only for final end-to-end acceptance.
Execution Intent Routing
- Production intent such as “运行”, “跑一次”, “完整流程”, “文献追踪”, “检查配置并启动”, or “配置完成，继续” must use only
node skills/paperecho-zotero-desktop/scripts/run.mjs. Pass--config config/paperecho.config.jsonwhen using unified configuration. With sufficient parameters, invoke--run; when only safe configuration inspection is possible, invoke--check. - Development intent such as modifying, fixing, refactoring, auditing code, or updating tests must not invoke the production launcher. Use mocks and targeted validation.
- Explanation intent must only explain or invoke
--check; never invoke--run. - A reply of “继续” reruns the same launcher with the same
--config, reloads the file, and performs a fresh preflight. Inspect onlycommonplusdesktop; do not reuse readiness, wait in the background, switch to Web/Local, or ask the user to paste secrets into chat. - Loading this Skill alone causes no production side effect. A production run modifies runtime data but must not modify code or create a Git commit.
Read the shared execution contract before invoking the launcher. It defines profiles, preflight, blocked recovery, current-run validation, exit codes, and secret handling; this Skill fixes the mode to Desktop and must not choose another launcher.
The launcher-fixed Desktop mode must agree with an explicit config mode or unique enabled section; a Web/Local selection is a blocking conflict. Missing output is grouped into common and desktop only. Use the shared configuration guide rather than maintaining a second field table here.
Architecture Boundary
- The workflow remains shared Stage0-Stage5 orchestration; Desktop differs only at the Zotero backend/strategy boundary.
- For Desktop changes, inspect first:
workflow/tools/lib/zotero_cli_backend.mjs,workflow/tools/lib/zotero_cli_executor.mjs,workflow/tools/lib/zotero_desktop_launcher.mjs, Desktop benchmark/tests, and this skill. - Only inspect shared Stage2/Stage3 or shared validation when changing business semantics such as source/grade routing, root
文献池, shortTitle, run marker, cleanup, or local/live index. - Do not add Desktop-specific
stage0-4copies. Do not add Web API rate-limit or HTTP behavior to Desktop code. - For Web API work use
paperecho-zotero-web; for standalone filesystem work usepaperecho-local. - For shared or cross-path behavior, first use paperecho-workflow and load its relevant reference.
What ships with it
5 files 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.
- 12d ago First seen · 63 lines · 59 tokens per session scan A b28df3584e81
paperecho-zotero-desktop is a skill published in the GitHub repository Chip-G0202/PaperEcho (56 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,330 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…