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 swan-gtm/gtm-skills --skill conference-recommendationgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/conference-recommendation)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/conference-recommendation"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/conference-recommendation/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/swan-gtm/gtm-skills/conference-recommendation"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/conference-recommendation.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 | $0.00095 | $0.02639 |
| Opus 5 | $0.00048 | $0.01319 |
| Sonnet 5 | $0.00019 | $0.00528 |
| Haiku 4.5 | $0.00010 | $0.00264 |
Grade A, and why
conference-recommendation 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 9d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup state. Not yet configured for this org. Load the Readme sub-page and walk the user through locking their ICP (buyer roles, target verticals, ACV range, sales-cycle length), geographic scope, B2B/B2C classification, and any events to force-include or force-exclude before scoring anything. (After setup completes, rewrite this paragraph to capture the locked profile — buyer roles, verticals, ACV band, geo scope, classification, exclusions, and last-refreshed date — so future runs proceed without re-asking.)
This skill scores the front-end decision — which events to invest in. It is the mirror image of an attendee-radar skill, which acts on attendees after an event. Run this one first; feed its picks into your calendar, then let the attendee-radar work the lists post-event.
The scoring frame
Every event is scored on a 100-point base across three dimensions, plus a +10 bonus for organizer-run matchmaking (Total Score out of 110).
| Dimension | Weight | What it measures |
|---|---|---|
| Relevance | 40 | How closely the attendee/exhibitor composition matches the client's ICP. |
| Decision-maker accessibility | 40 | Density of actual buyers AND structural reach to them (floor layout, meeting infrastructure, side events). |
| Engagement mode | 20 | Are attendees in a vendor-buying mindset, or is it a learning/keynote-driven crowd? |
Tiers:
| Tier | Score | Meaning |
|---|---|---|
| P1 | ≥ 80 | Must-attend. Book it. |
| P2 | 70–79 | Strong. Attend if budget/calendar allows. |
| P3 | < 70 | Excluded from the ranked list. No padding, no filler. |
Do not pad the list to hit a target count. A short list of P1/P2 events beats a long list diluted with P3s.
Step 0 — Lock the classification (do this first, never infer it)
Where buyers physically stand at an event depends entirely on what the client sells. Get this wrong and every downstream score is measuring the wrong crowd.
| Classification | Where the buyers are | Scoring orientation |
|---|---|---|
| B2C (general) | In the audience | Audience-driven |
| B2C with booth-density exception (e.g. consumer brand selling to other exhibitors) | At exhibitor booths | Booth-driven |
| B2B selling to marketing / growth / sales | Behind the booths (every booth is staffed by the buyer) | Booth-driven |
| B2B selling to non-marketing functions (CISO, CIO, CFO, engineering) | In the audience / session tracks | Audience-driven |
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.
- 9d ago First seen · 148 lines · 95 tokens per session scan A 61ee35b30d62
conference-recommendation is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 2,639 once invoked, about $0.0005 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
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.
k8s-workload-inventory
List Kubernetes workloads and namespaces — pods with their node, phase and readiness, plus events. Use when asked what is running, where it is running, what is failing, or for a general inventory of a cluster.
luma-event-insights
Starter skill for analyzing Lu.ma events, attendees, invites, and engagement signals from organizer-provided API access, exports, or manual event inputs. Use this when a template or workflow needs a repeatable path to turn Lu.ma event data into an organizer-ready analysis brief.
huawei-cloud-cce-kubernetes-event-analyzer
Query and analyze Kubernetes Events in Huawei Cloud CCE clusters. Trigger when users ask about CCE events, Kubernetes warning events, FailedScheduling, FailedMount, ImagePullBackOff, event patterns, historical events in LTS, or event-based diagnosis for a CCE cluster or namespace.
cairo-contract-authoring
Cairo smart-contract authoring on Starknet. Trigger on "write a contract", "create a contract", "implement this in Cairo", "add storage/events/interface", "compose components". Guides structure, security patterns, and component wiring.
backend-event-sourcing
Use this skill when the user says 'event sourcing', 'event store', 'event stream', 'event sourced', 'rehydrate from events', 'event replay', 'projection rebuild', 'event log', 'append-only log', 'event history'. This skill enforces: events as the single source of truth, current state derived from event replay…