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 find-my-docs-gapsgit 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/find-my-docs-gaps)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/find-my-docs-gaps"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/find-my-docs-gaps/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/find-my-docs-gaps"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/find-my-docs-gaps.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 | $0.00065 | $0.00875 |
| Opus 5 | $0.00032 | $0.00438 |
| Sonnet 5 | $0.00013 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
find-my-docs-gaps 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 7d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find My Docs Gaps
When to use
- Ask: "what should I write docs for?", "what gaps do we have?", "what's missing from help center?".
- Weekly cadence - usually paired with or before
review-my-support scope=help-center-digest. - After
flag-a-signal signal=repeat-questionfind new clusters worth review.
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.
- Knowledge base (Notion / Google Docs) - cross-check your published articles so I don't flag a gap you've already filled. Optional if your articles live locally.
- CRM (HubSpot / Attio / Salesforce) - weight gaps by customer plan tier and monthly revenue. Optional, falls back to equal weight.
I keep going if neither is connected, but I'll tell you the ranking is rougher without them.
Information I need
I read your support 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.
- Help-center platform - Required. Why I need it: I check existing coverage before ranking a cluster as a real gap. If missing I ask: "Where do your help articles live today - Notion, Intercom, a docs site, or nowhere yet?"
- Plan tiers - Optional. Why I need it: gaps hitting paying customers rank higher than free-tier hits. If you don't have it I keep going with equal weight per ticket.
Steps
- Read
patterns.json(clusters of repeat questions) andarticles/(existing KB). Filter patterns without matching article. - List empty → run
flag-a-signal signal=repeat-questionfirst (or tell me just ran, nothing yet). - Rank each open gap by impact score:
occurrenceCount- primary signal (how often asked)- Customer value - each
sourceTicketId, lookup customer incustomers.json, weight by plan tier / monthly revenue if present (fallback: equal weight) - Freshness - recent occurrences beat stale; heavy penalize gaps with no hits in last 14 days
- Present top 3 gaps in chat:
1. "How do I reset my API key?" - 7 occurrences, 3 paying customers, latest 2 days ago Source tickets: t_abc, t_def, t_ghi 2. ... 3. ... - Ask: "Want me to draft articles for any of these? Reply with the numbers (e.g. '1 and 3')."
- Each number picked, pick representative source ticket (most recent, or clearest resolution) and chain to
write-an-article type=from-ticket. - Write ranking snapshot to
gaps/{YYYY-MM-DD}.md, append entry tooutputs.jsonwithtype: "docs-gap",domain: "help-center". - Gap promoted to article → refresh
patterns.jsonentry withrelatedArticleSlugso won't re-surface.
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.
- 7d ago First seen · 61 lines · 65 tokens per session scan A 9647a3f908de
find-my-docs-gaps is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 875 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
support-digest
A local tool that reads exported customer-support tickets in JSON or CSV and produces a daily summary after hiding personal information. It does not fetch data from support systems or call outside APIs.
sillytavern-shadow
A fast-response workflow for debugging and implementation. It moves from noticing a request or problem to providing support, solving it, and checking the work with investigation steps.
moonpay-feedback
Submit feedback, bug reports, or feature requests for the MoonPay CLI. Use when the user encounters issues, wants to suggest improvements, or has general feedback.
customer-support-expert
Build comprehensive customer support systems including ticketing, knowledge management, SLA tracking, and customer satisfaction analytics. Use when the user mentions helpdesk or service desk, ticketing, SLA targets, knowledge bases, escalation workflows, CSAT/NPS, or customer success operations.
Troubleshooting Guide Builder
Builds a structured troubleshooting guide with symptom → cause → fix format for any tool or system.
supportive-conversation
Generate supportive responses with safety boundaries. Use when user asks to 'be supportive', 'help with emotional support', 'provide encouragement', 'respond with empathy', 'offer emotional support'.