Stats
Actions
Tags
From Superposition
Find, look up, research, and summarize candidates in Superposition. Use for "find Python engineers from Google", "who are the top people we haven't contacted yet", "give me a quick summary of this person before I decide", "research this candidate and check their GitHub", "what's his comp expectation / notice period / timezone", "what's her LinkedIn", or "who failed the technical screen". Also use to assess a candidate against the bar — "why does he clear the bar?", "is she really top-tier? what are the proof points?", "show me the best matches and filter out weak schools/companies". This is the read/research/assess entry point — for taking an action on a candidate use pipeline-actions; for recording a new fact use record-candidate-insights; for telling the client use pitch-to-client.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superposition:find-candidatesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The #1 thing operators do is look people up — to search, to get a quick read before deciding, or to
The #1 thing operators do is look people up — to search, to get a quick read before deciding, or to
answer a factual question. This skill is read-first; only reach for invoke_agent when the user
wants active research/enrichment beyond what's already on file.
search_candidates with filters
(skills, company, jobTitle, school, summary, stages). Defaults to the active pipeline;
pass includeEligible/includeArchived when the ask implies it.search_candidates (pass the URL as searchTerm) then
get_candidates for full detail. Batch multiple IDs in one get_candidates call.get_candidates (FitCheck, traits,
location, links), search_insights (person facts: visa, comp, availability), and
get_candidate_email_thread (what they last said) usually have the answer — don't guess, don't
escalate.invoke_agent to actively research and summarize:
"Research candidate
<id>(check their public profiles / GitHub as relevant) and give a concise fit summary for job<id>."
https://app.superposition.ai/c/{candidateId}:
highlights, fit signal, watch-outs. For lists, a compact ranked table.Top uncontacted for Senior Backend (5):
| Candidate | Why | Signal |
|---|---|---|
| [A. Rivera](https://app.superposition.ai/c/abc) | ex-Stripe, distributed systems | strong |
| [J. Okoro](https://app.superposition.ai/c/def) | 6y Go, fintech | strong |
npx claudepluginhub superpositionhq/ai-plugin --plugin superpositionProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.