Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

record-candidate-insights

Estrelas0

Forks0

Atualizado2 de junho de 2026 às 10:02

Record a confirmed fact (an "insight" or "learning") about a person in Superposition — visa/work authorization, compensation expectation, location/relocation, availability/notice, preferred name, remote/onsite preference, clearances, competing offers, etc. Use whenever the user says "add a note that…", "add a learning…", "note that…", "remember that…", "she confirmed she's a US citizen, add that", or "he prefers to be called [name]". These are person-level facts, not pipeline decisions.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

superpositionhq

superpositionhq/ai-plugin

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Especialistas em gestão de projetosNegócios e Operações Financeiras·SOC 13-1082

SKILL.md

readonly

Mais deste repositório

mesmo repositório

bootstrap-company-soul

superpositionhq/ai-plugin

Populate or enrich the Superposition company profile — the "company soul" that powers FitCheck assessment and candidate outreach. Use whenever the user wants to set up, fill in, enrich, or improve their company information on SPA, mentions "company soul / profile / identity", is onboarding, or asks why FitCheck or outreach quality is weak. This is a prerequisite for the candidate-review skills — a thin profile produces weak assessments.

2026-06-020

connect-superposition

superpositionhq/ai-plugin

Connect to Superposition (SPA) and confirm you're set up before doing recruiting work. Use this whenever the user first mentions Superposition, asks to "connect", "set up", "log in", or "authenticate" with SPA, asks which organization they're in, says they can't see their candidates/jobs, or hits a 401/403/permission error from an SPA tool. Run this before the other Superposition skills so the active org and access are established.

2026-06-020

find-candidates

superpositionhq/ai-plugin

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.

2026-06-020

manage-outreach

superpositionhq/ai-plugin

Control candidate outreach and follow-up emails in Superposition — draft/send a follow-up, chase a non-responder, send a polite decline, hold or cancel a queued send, or stop the agent because a human is taking over the thread. Use for "draft a follow-up about availability", "reach out and ask if he wants to reschedule", "send an apologetic decline", "don't send a follow-up", "I'll handle my own email", or "if they've had three emails with no reply, archive them".

2026-06-020

manage-roles

superpositionhq/ai-plugin

View and edit jobs/roles in Superposition — list open roles, check a role's status, update comp, the job description, location, or work-auth fields, set pre-interview checks, or draft a new role. Use for "what roles are we hiring for", "update the salary range on the Head of Marketing role", "update the JD to say remote-first", "what's the status of the marketing role", "always ask for a portfolio before flagging", or "open a new role for a staff backend engineer". Also use to set up or copy interview stages between jobs, duplicate a role, or edit the ideal-candidate profile ("prefer IC, no managers", "copy the other job's scheduling config", "duplicate the founding-eng job").

2026-06-020

pipeline-actions

superpositionhq/ai-plugin

Take a pipeline action on a specific named candidate in Superposition — move/advance to a stage, pass/reject, withdraw, mark do-not-contact, share with the client, or mark hired. Use whenever the user gives a directive about one (or a few) named candidates: "move [name] forward", "pass on him", "reject — no-show", "take her out of the pipeline", "share with the client", "mark hired", "mark do not contact", or "undo that not-a-fit decision". For triaging the whole awaiting-review queue, use the review-candidates skills instead.

2026-06-020

Record candidate insights / learnings

Operators frequently capture durable facts about a person mid-conversation. These "insights" are person-scoped (they follow the person across roles) and they feed future assessment and outreach, so recording them cleanly is high-value. Insights are written by the Master Agent via invoke_agent.

Steps

Resolve the person. If named, search_candidates → get_candidates. Don't ask for an ID.

Check for duplicates. search_insights for the person so you don't record the same fact twice; if it's an update to an existing fact, note that.

Make it atomic and confirmed. One fact per insight, falsifiable, in the user's words. Record compensation verbatim. If the user's statement is vague, confirm the exact fact before saving.

Record via invoke_agent, threading sessionId:

"Record a person-level insight for candidate <id> (personId only — not job-specific): '<the atomic fact, e.g. needs H-1B sponsorship / comp expectation $180k base / prefers to go by Liz / open to relocating to NYC>'. Reason: <why it's being recorded>."

Confirm what was saved.

What counts (record) vs. what doesn't

Record: visa/work-auth, comp expectations (verbatim), location/relocation, availability/notice, start date, remote/onsite preference, preferred name, clearances, competing offers, contract-vs-FTE.

Do NOT record as a person insight: client decisions ("client passed"), role-specific sentiment ("excited about this job"), interview performance, or ephemeral scheduling details. Those belong to the pipeline (use pipeline-actions) — recording them as person facts pollutes future matching.

Output

Recorded for [Liz Cho](https://app.superposition.ai/c/abc-123): "Prefers to be called Liz." (person-level — applies across roles)

Record candidate insights / learnings

Steps

Resolve the person. If named, search_candidates → get_candidates. Don't ask for an ID.

Check for duplicates. search_insights for the person so you don't record the same fact twice; if it's an update to an existing fact, note that.

Make it atomic and confirmed. One fact per insight, falsifiable, in the user's words. Record compensation verbatim. If the user's statement is vague, confirm the exact fact before saving.

Record via invoke_agent, threading sessionId:

"Record a person-level insight for candidate <id> (personId only — not job-specific): '<the atomic fact, e.g. needs H-1B sponsorship / comp expectation $180k base / prefers to go by Liz / open to relocating to NYC>'. Reason: <why it's being recorded>."

Confirm what was saved.

What counts (record) vs. what doesn't

Output

Recorded for [Liz Cho](https://app.superposition.ai/c/abc-123): "Prefers to be called Liz." (person-level — applies across roles)