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 | $0.00182 | $0.03024 |
| Opus 5 | $0.00091 | $0.01512 |
| Sonnet 5 | $0.00036 | $0.00605 |
| Haiku 4.5 | $0.00018 | $0.00302 |
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 10d 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 — 220 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 decides which topic; research-design-helper designs how). - 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 ("No one has tried this" / "Current methods fall short") |
| 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 | formal research-memo prose — the do-not-pursue topic and the conditional topic, with named actions |
| 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.
- 10d 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 (54 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 3,024 once invoked, about $0.0009 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
migrate-v0-to-v1
Migrate a Scraps wiki from v0 to v1. Use this whenever the user asks to upgrade Scraps, migrate v0 wiki syntax/config, convert implicit tags to explicit #[[tag]], move from scraps-writer to scraps, or audit a wiki for v1 readiness. This skill is designed for one-pass LLM-led migrations that discover the latest v0 and…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
ingest
Create a new scrap from a source (prompt, URL, or arbitrary markdown), update cross-links in related scraps, and run a sanity check. Use this when the user wants to add a scrap, summarize an article, save synthesized content to the wiki, or file back a Q&A result.
query
Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.
planning-with-scratchpad
Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.
scratch
Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.