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 curiositech/some_claude_skills --skill research-craftgit clone --depth 1 https://github.com/curiositech/some_claude_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.
[](https://agentmods.dev/skills/curiositech/some_claude_skills/research-craft)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/research-craft"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/research-craft/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/curiositech/some_claude_skills/research-craft"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/research-craft.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 | $0.00049 | $0.03134 |
| Opus 5 | $0.00024 | $0.01567 |
| Sonnet 5 | $0.00010 | $0.00627 |
| Haiku 4.5 | $0.00005 | $0.00313 |
Grade A, and why
research-craft 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 8d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Craft
Master the systematic process of formulating meaningful research problems, constructing evidence-based arguments, and communicating findings that contribute to scholarly conversations.
When to Use
✅ Use for: Academic research papers, thesis/dissertation work, scholarly article writing, literature reviews, evidence-based argumentation, knowledge synthesis, participating in disciplinary conversations ❌ NOT for: Creative writing, journalistic reporting, business case studies, technical documentation, marketing content, personal essays, opinion pieces
Core Process
Problem Formulation Decision Tree
START: Do you have a clear research problem?
├─ NO: Do you have a specific topic (not just broad subject)?
│ ├─ NO → Find specific topic within general interest area
│ └─ YES → Question topic systematically
│ └─ Ask "So what?" to test consequences
│ ├─ Readers won't care → Reframe problem from reader perspective
│ └─ Readers will care → Verify problem structure:
│ ├─ Condition (knowledge gap) stated?
│ ├─ Cost/consequence stated?
│ └─ Evidence type available?
│ ├─ ALL YES → PROCEED to argument building
│ └─ ANY NO → Revise problem formulation
└─ YES → Is problem practical or conceptual?
├─ PRACTICAL (tangible costs requiring action)
│ └─ Solution must be actionable
└─ CONCEPTUAL (understanding gap)
├─ Pure research → Solution improves understanding
└─ Applied research → Solution has practical consequences
Argument Construction Decision Tree
START: Building argument for research claim
├─ State CLAIM (answers research question)
├─ Develop REASONS (assertions from thinking)
│ └─ For each reason, do you have EVIDENCE (data from world)?
│ ├─ NO → Insufficient support; gather evidence or drop reason
│ └─ YES → Is evidence representative, accurate, sufficient?
│ ├─ NO → Cherry-picking risk; expand sample or qualify claim
│ └─ YES → Continue
├─ Anticipate reader objections
│ ├─ Plausible objections exist?
│ │ ├─ YES → ACKNOWLEDGE and RESPOND with subordinate argument
│ │ │ ├─ Can you refute? → Provide counter-evidence
│ │ │ ├─ Must concede? → Acknowledge limitation candidly
│ │ │ └─ Alternative view? → Show why yours is stronger
│ │ └─ NO → Proceed to warrants
│ └─ Will readers question reason-claim connection?
│ ├─ YES → STATE WARRANT (general principle)
│ └─ NO (expert audience) → Omit warrant
└─ Test complete argument
└─ Evidence comprises ~1/3 of section?
├─ NO: Too little → Data dump; too much → Add interpretation
└─ YES → ARGUMENT COMPLETE
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.
- 8d ago First seen · 258 lines · 49 tokens per session scan A 5dc32d7e9983
research-craft is a skill published in the GitHub repository curiositech/some_claude_skills (219 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 3,134 once invoked, about $0.0002 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 2026-09-03.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…