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 WenyuChiou/research-hub --skill gap-to-topicgit clone --depth 1 https://github.com/WenyuChiou/research-hubWrote 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/wenyuchiou/research-hub/gap-to-topic)<a href="https://agentmods.dev/skills/wenyuchiou/research-hub/gap-to-topic"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/gap-to-topic/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/wenyuchiou/research-hub/gap-to-topic"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/gap-to-topic.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 | $0.00188 | $0.04469 |
| Opus 5.5 | $0.00075 | $0.01788 |
| Sonnet 5.5 | $0.00038 | $0.00894 |
| Haiku 4.5 | $0.00019 | $0.00447 |
Grade A, and why
gap-to-topic 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 2d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gap-to-topic
Choosing a thesis or proposal topic is not "do a literature review." It is a decision under uncertainty: given everything already known, what should I do next, and why is it defensible? This skill produces the document that decision actually needs — a 3-gate decision dossier for one (or a few) candidate breakthrough points.
It deliberately stops short of the verdict. It assembles the evidence for three gates and hands the final "is this worth doing" call back to the researcher and their advisor — where it belongs.
When to use
Trigger phrases:
- "Is this research gap worth pursuing?"
- "Help me pick a thesis / proposal topic."
- "Is this idea already taken? / has someone done this?"
- "Find me a defensible research gap in ."
- "Vet this research idea before I commit."
- "Should I do this? / should I commit to this?"
Not for:
- A comparison matrix over a known paper set — that's
literature-triage-matrix. - Designing the study once a topic is chosen — that's
research-design-helper(gap-to-topic assembles options for the researcher to choose; research-design-helper designs how after that choice). - A narrative literature review — that's a writing task.
- Building manuscript claim memory — that's
paper-memory-builder.
What it produces
.research/topic_dossier.md and .research/topic_dossier.docx — a
research-grade decision memo in Markdown and as a colour-coded Word
document: first page enables a decision; the body supports verification; the
appendices support a re-run. Reads top-to-bottom in Word with no decoding —
no codes (G1/G2 stay only in .gaps.yml), no decorative glyphs,
plain-language verdicts, decision-relevant tables in the body and reference /
log tables in the appendices. Verdict cells are colour-coded in the .docx
(light red / yellow / green / grey by verdict phrase, bilingual en + zh-TW).
| Section | What it covers |
|---|---|
| 1. Executive Decision Summary | metadata box; one framing sentence; per-candidate verdict cards (small 2-column tables, generator colour-codes the verdict cell); a one-line key uncertainty |
| 2. Candidate Definitions | per candidate, name + one-sentence statement + a plain "why it could be a gap" tag ("Application coverage unresolved" / "Specific method limitation") |
| 3. Decision Scorecards | per candidate, a small 3-column table (Gate / Score / Rationale) with the three gates rated 1–5 (Likert) plus a Verdict row; cells colour-coded by the generator |
| 4. Evidence Base | the search funnel, the prior-art classification, and the closest prior work per candidate with inline evidence-type tags |
| 5. Gate-by-Gate Assessment | each gate uses a fixed five-field skeleton: Score / Evidence / Interpretation / Risk / Action needed |
| 6. Risks and Upgrade / Kill Tests | named risks (construct validity, dataset, novelty, reproducibility); operational upgrade / kill test per conditional candidate; salvage path per failed candidate |
| 7. Recommended Next Steps | actual options and tradeoffs, reason-specific bounded next checks, and pending or explicit user choice |
| Appendix A. Search and Screening Protocol | a reproducibility log — search date, databases, query families, retrieved, dedup, inclusion / exclusion, screening, known limitations, recall confidence |
| Appendix B. Deliverable File List | the file index and the file tree |
What ships with it
6 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.
- 2d ago Changed · +5 lines 7b8bf66ae16c
- 24d ago Changed · +44 lines 8c72bfd79877
- 25d ago Changed · +58 lines · +6 tokens per session 912b0abba7c5
- 1mo ago First seen · 220 lines · 182 tokens per session scan A 1c7d4579b386
gap-to-topic is a skill published in the GitHub repository WenyuChiou/research-hub (66 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 4,469 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
novel-writer-cli
A command-line long-form novel writing assistant that uses wpsnote-cli to manage WPS notes, a digital notebook, while creating a story chapter by chapter.
novel-writer
A long-form novel writing assistant that uses WPS notes, a digital notebook, to keep track of the story, characters, and world while writing chapter by chapter.
wps-note
A note-management helper for WPS Notes, a cloud note-taking service. It reads, creates, edits, searches, and organizes notes through document blocks exchanged as XML.
live-transcript-summary
A real-time note-taking skill that watches audio transcription in the current WPS note and periodically organizes it. WPS is an office and note-taking application.
xiaohongshu-note-creator
A rewriting helper that turns existing WPS Notes or articles into image-and-text plans for Xiaohongshu, a Chinese social platform for visual posts. It shortens and adapts the original material to that format.
tag-organize-cli
A command-line workflow for organizing file-level tags in WPS Notes, a cloud note-taking service. It uses the wpsnote-cli program and does not require an MCP server connection.