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 LMDHQ-0420/ResearchPilot-Skills --skill research-g.1-methodgit clone --depth 1 https://github.com/LMDHQ-0420/ResearchPilot-SkillsWrote 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 research[G.1]-method](/badge/skills/lmdhq-0420/researchpilot-skills/research-g.1-method/github.svg?v=0-21-A){kind=icon}
[](https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-g.1-method)<a href="https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-g.1-method"><img src="https://agentmods.dev/badge/skills/lmdhq-0420/researchpilot-skills/research-g.1-method/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.
![agentmods 80×15 button for research[G.1]-method](/badge/skills/lmdhq-0420/researchpilot-skills/research-g.1-method.svg?v=A-x){kind=icon}
<a href="https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-g.1-method"><img src="https://agentmods.dev/badge/skills/lmdhq-0420/researchpilot-skills/research-g.1-method.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 | $0.00021 | $0.00909 |
| Opus 5 | $0.00010 | $0.00454 |
| Sonnet 5 | $0.00004 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
research[G.1]-method 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase G.1: Method
user_requirements.md priority: All user constraints in
docs/user_requirements.mdtake precedence over any default instruction in this skill. Always read it before generating output.
Overview
Paper Writing Stage Chain
| Skill | Responsibility |
|---|---|
/research[G.0]-plan |
Update idea_report → plan structure/figures → select format |
/research[G.1]-method |
Write / revise Method |
/research[G.2]-experiments |
Write / revise Experiments |
/research[G.3]-abstract |
Write / revise Abstract |
/research[G.4]-introduction |
Write / revise Introduction |
/research[G.5]-related |
Write / revise Related Works |
/research[G.6]-conclusion |
Write / revise Conclusion + References |
/research[G.7]-review |
Full-paper review (five dimensions + claim-evidence) |
Command
/research[G.1]-method
An optional natural-language instruction may follow the command. The AI will treat it as an additional constraint or supplement for this invocation.
Prerequisite: Manuscript file contains a complete === 论文架构 === annotation block at the top, with all sections annotated with content points and figure positions
Before Writing: Required Steps
- Read the full manuscript (avoid disconnection from already-written sections)
- Read all existing references (References section or .bib file)
- Read the
=== Paper Architecture ===comment block at the top of the manuscript - Read
docs/idea_report.mdanddocs/dev_log.md(find answers to writing questions here first) - Read example analysis if
docs/manuscripts/examples/style-notes.mdexists - Scan all annotations in the manuscript, list pending ones
- Confirm writing plan with user before writing anything
See references/common-writing-constraints.md for full details.
Method Section-Specific Requirements
Three Questions Before Writing (for each module):
- How does this module work? (read from code)
- Why is this module needed? (corresponds to RQ2 bottleneck, from idea_report)
- Why does this module work? (theoretical intuition or prior evidence)
What ships with it
12 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.
- references/common-writing-constraints.md 7.7 KB
- references/examples/common-issues.md 355 B
- references/examples/example-of-the-three-elements.md 7.3 KB
- references/examples/module-design-instant-ngp.md 4.5 KB
- references/examples/module-motivation-patterns.md 410 B
- references/examples/module-triad-neural-body.md 763 B
- references/examples/overview-template.md 2.0 KB
- references/examples/pre-writing-questions.md 479 B
- references/examples/section-skeleton.md 110 B
- references/section-guide-source.md 6.1 KB
- references/section-guide.md 573 B
- references/template-flexibility.md 5.1 KB
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 · 123 lines · 21 tokens per session scan A e14735efafd4
research[G.1]-method is a skill published in the GitHub repository LMDHQ-0420/ResearchPilot-Skills (284 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 909 once invoked, about $0.0001 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…