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 akiotanaka847/qaio-desktop --skill research-a-topicgit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/research-a-topic)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/research-a-topic"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/research-a-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/akiotanaka847/qaio-desktop/research-a-topic"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/research-a-topic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01336 |
| Opus 5 | $0.00024 | $0.00668 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
research-a-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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research A Topic
Source template: Gumloop "AI Research Agent with Automated Report Generation". Adapted for hand-off to other four marketing agents, not 20-page investor memos.
When to use
- "research {topic}" / "I need a brief on {topic}" / "what's state of {topic}".
- "summarize what's happening in {category}".
- Called implicitly by other skills (
plan-a-campaign,watch-my-competitors,profile-my-customer) when they hit an evidence gap that needs a dedicated research run.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing -> I name the category, ask you to connect it from the Integrations tab, stop.
- Web search (Exa or Perplexity) - the engine that finds and ranks sources. Required - no useful fallback, I need a search index to start from.
- Web scrape (Firecrawl) - optional, fetches full text cleanly. If not connected I fall back to basic HTTP fetch on each source URL, rougher but enough to pull quotes from static pages.
If web search isn't connected I stop. The scrape fallback keeps me going on its own.
Information I need
I read your marketing context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- Your positioning - Required. Why I need it: a brief that doesn't filter for your ideal customer and category is just generic internet research. If missing I ask: "Want me to draft your positioning first? It's one skill, takes about five minutes."
- The research question - Required. Why I need it: scope creep makes briefs useless. If missing I ask: "What's the one question this brief should answer, and what decision does it unblock?"
- Depth - Optional, default standard. If missing I ask: "How deep should I go, a fifteen-minute scan, an hour-long dive, or a deep run? If you don't have a preference I keep going with standard depth."
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 · 91 lines · 49 tokens per session scan A c333ff53c970
research-a-topic is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 1,336 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 2026-08-31.
Other skills, from other repositories
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
offers
When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment structure. Also use when the user mentions 'offer,' 'offer design,' 'build an offer,' 'grand slam offer,' 'irresistible offer,'…