Systems Lab

Agent skill

research-events

Find and inspect Lensmor trade shows by name, topic, location, date, or attendee Insights (level, industry, function, company size, analyzed sample).

activeReaches the webInstructions only890 words

Filed under ABM and paid.

From LensmorOfficial/event-to-pipeline · 7 skill entries · 2 · pushed 2026-11-02

What it does when it runs

Find and inspect Lensmor trade shows by name, topic, location, date, or attendee Insights (level, industry, function, company size, analyzed sample). Use for event discovery and event details, not exhibitor, contact, unlock, or outreach work.

Automated analysis of the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
  • platform.lensmor.com
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about research-events

Opens your assistant with this page's recorded context. Check the linked sources before relying on it.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/LensmorOfficial/event-to-pipeline.git /tmp/event-to-pipeline
git -C /tmp/event-to-pipeline sparse-checkout set "skills/research-events"
mkdir -p ~/.claude/skills/research-events
cp -R "/tmp/event-to-pipeline/skills/research-events/." ~/.claude/skills/research-events/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from LensmorOfficial/event-to-pipeline/blob/ced49373c570cd76908d7784033f60cf2f9338a4/skills/research-events/SKILL.md, which is licensed MIT (repository). 890 words, 8 headings.

Lensmor Event Research

Evidence and delivery boundaries

Treat tool data as observations within the returned scope. An exact domain resolves a stored domain group, not a legal entity or parent/subsidiary relationship. Differences in headquarters, names or LinkedIn pages require verification; they do not establish that companies are unrelated. A regional job title is a responsibility-review flag, not enough to exclude a person from another market without the user's role criteria. Never generalize industry-wide data coverage from one sample.

For contact fields, use field_availability when returned. NOT_CHECKED, null and redaction mean availability has not been established. contact_unlock_status describes email access only; it says nothing about phone availability. Say "Email/Phone availability has not been checked" unless an authenticated field result supports a stronger statement. Do not promise a value will exist after purchase.

Task fit

Find events or inspect one event. Use the logical tool names below; the host assigns their runtime namespace.

Scope and clarification

Preserve the user's event, topic, location and time constraints. Resolve a name against actual returned candidates; a familiar name or a year in the request is not proof of uniqueness. Continue a unique match within scope without another confirmation. Ask only when candidates remain ambiguous or the scope must change.

Cross-tool steps

For attendee metrics, use the Audience Insights path below first. Otherwise use resolve_event for a named or misspelled event and search_events_v2 for discovery. Follow each tool's input descriptions for topic interpretation and filters. Do not fan out translations or broaden an empty search without permission. For requested pagination, reuse the same filters and returned cursor. Use get_event when detail is requested or needed for the next task, not as a compulsory extra step.

Read coverage and the zero-result reason before describing availability: an existing event with an unavailable exhibitor index is not evidence of no matching exhibitors.

Result and handoff

Show event names, dates, locations and relevant coverage in the user's requested format. Briefly state a returned correction or translation that changes the search interpretation. Keep handles, cursors and internal metadata out of the answer. For downstream exhibitor or people research, hand off the resolved scope. For an explicit request to unlock that event's directories, hand off the existing event handle to manage-contact-actions; ordinary discovery does not require a purchase.

Audience Insights queries

For cross-event attendee proportions, sample counts, audience ranking or quantitative fit, use search_events_by_insights after the user has supplied a bounded date range. If dates are missing, ask for the date range before calling. Never silently default to the next three months. This path requires an actual attendee-metric request; it is never a fallback for unavailable topic discovery. Both paths share the same topic index. Do not drop the topic, switch to keyword, remove filters or query Insights to work around an index outage. Combine every requested event condition and metric in one call; do not enumerate ordinary event results and compute or rank a partial page locally. For one event, resolve its handle and use get_event_insights; single-event Insights do not require a date range. If a search already returned the required metrics, answer from that response.

Cross-event limits default to 93 inclusive days and 100 candidate events before attendee-metric filtering. The tool error details maxRangeDays and maxCandidateEvents are authoritative for the current environment. EVENT_INSIGHTS_SCOPE_REQUIRED is a clarification request, not a service outage or a zero-match result: for date_range_required, ask for dates; for date_range_too_wide, ask for a shorter date range; for too_many_candidate_events, ask the user to narrow the dates or further limit the country, city, or event topic. Preserve every original metric condition and wait for the user's scope choice before calling again. Never add scope constraints yourself or truncate to the first 100 events and present them as the complete search. candidateCountLowerBound is only a lower bound on candidate events, not a count of events meeting the metric thresholds.

  • Director+ = Owner, Partner, C-suite, VP, Director; never Head. C-suite is independent and never substituted by Director+ or an executive function.
  • Financial Services uses attendee industry; Sales uses attendee function. Event topic is an independent condition. Company size uses attendees' linked-company size, not the exhibitor distribution.
  • “Mainly 51–200” means attendee_company_size / category:51-200 / gt:50; state the >50% rule.
  • Preserve >= versus > exactly. Use relative months/days with the user's time zone when provided; otherwise state the returned UTC interval. Do not invent dates or locations; missing cross-event dates require clarification, while single-event reads need no date filter.
  • Ratios must show the returned sample/denominator; explain unknown coverage, definition and update time. Treat unavailable/no_sample as unavailable, not zero. Use returned dataVersion when comparing page data.
  • Insights tools use page/pageSize. Preserve original filters/metrics and resolved date bounds when paging, and omit timeRange; do not resend derived metrics or mix the ordinary search cursor protocol.
  • Empty means empty. Explain zeroResultReason and coverage; do not broaden, replace metrics, or recommend qualitatively “executive-focused” events without new user scope.
  • Aggregate reads are free, including for zero-credit users. Do not call contacts, previews, balance, unlock, quote or paid confirmation to answer these questions. Never return contact lists automatically. Explain audience fit only against user-provided criteria.

Research mode

Research uses the account's existing access. For invitation drafts, use booth-invitation-writer with the available facts. Purchases and external writes require a separate workflow and explicit user authorization.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what research-events does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.

Build my GTM engine

Tell us what you want to improve. Fedor reviews the workflow and replies by email when there is a useful fit.

Fedor reviews every request personally. If there is a useful fit, he will reply by email.