Stats
Actions
Tags
From Superposition
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").
How this skill is triggered — by the user, by Claude, or both
Slash command
/superposition:manage-rolesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Reads are answerable directly from job data; edits and new roles flow through the Master Agent via
Reads are answerable directly from job data; edits and new roles flow through the Master Agent via
invoke_agent (which owns update_job / create_draft_job).
list_jobs (active roles) and get_job for detail —
answer directly. get_job carries compensationRange, equityRange, locationType/location/
inOfficeDaysPerWeek, isVisaSponsorshipProvided/workAuthorizationRequirement, jobDescription,
and infoToFlagToCandidates.get_job first (so you can show a diff and not clobber
other fields), then invoke_agent, threading sessionId:
"Update job
<id>: set to (e.g. compensationRange to '$120–160K+'; add 'remote first' to the JD; set infoToFlagToCandidates to ''). Leave other fields unchanged."
get_supported_roles if the user wants a template — then invoke_agent to create a draft.list_interview_stages, then invoke_agent to create/copy the stages (or draft the duplicate
role). Confirm interviewers/scheduling URLs carried over.https://app.superposition.ai/j/{jobId}.infoToFlagToCandidates),
not an insight. But work-authorization and standard location/work-model belong in the dedicated job
fields, not as free-text checks — the agent handles that routing.Updated [Head of Marketing](https://app.superposition.ai/j/job-789): compensationRange "$110–140K" → "$120–160K+, depending on level".
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.