/profile-memory
How Rebound stores and reuses the user's career profile, including the private "situation" (work authorization, timeline). Use when reading, writing, or reasoning about the saved profile at ~/.rebound/.
Claude Code
$ npx -y skills add snehag01/rebound --skill profile-memory --agent claude-code
Codex
$ npx skills add snehag01/rebound --skill profile-memory -a codex -y
Cursor
$ npx skills add snehag01/rebound --skill profile-memory -a cursor -y
Gemini CLI
$ npx skills add snehag01/rebound --skill profile-memory -a gemini-cli -y
GitHub Copilot
$ npx skills add snehag01/rebound --skill profile-memory -a github-copilot -y
OpenCode
$ npx skills add snehag01/rebound --skill profile-memory -a opencode -y
Windsurf
$ npx skills add snehag01/rebound --skill profile-memory -a windsurf -y
SKILL.md
profile-memory.SKILL.mdname: profile-memory
description: How Rebound stores and reuses the user's career profile, including the private "situation" (work authorization, timeline). Use when reading, writing, or reasoning about the saved profile at ~/.rebound/.
Profile & Memory
Rebound persists one profile per machine so the user never re-enters their details. It is the reusable base for every `/rebound:tailor`, `/rebound:match`, and `/rebound:rise`.
Location & format
- `~/.rebound/profile.json` — machine-readable (authoritative).
- `~/.rebound/profile.md` — human-readable mirror (keep in sync on every write).
- `~/.rebound/pylibs/` — bundled python deps (python-docx).
Create `~/.rebound/` if missing. On updates, rewrite both files and confirm.
Schema
{
"name": "", "contact": "", "current_title": "", "years_experience": "",
"base_resume_path": "",
"primary_stack": [], "secondary_stack": [], "differentiators": [],
"roles": [{"title": "", "org": "", "location": "", "dates": "", "bullets": []}],
"education": [], "certifications": [],
"situation": {
"work_authorization": null, // high-level only: "no sponsorship needed" | "will need sponsorship" | null
"timeline": null, // absolute dates + runway, e.g. "authorization/sponsorship deadline ~2026-08-15; ~60 days"
"target_roles": [], "locations": [], "work_mode": null, "notes": null
},
"preferences": {
"framing_notes": [
"fast learner across stacks; strong OOP/systems fundamentals",
"surface secondary skills but never above primary stack",
"honesty-first: never claim expertise in unused tech"
]
}
}The private "situation" — handle with care
This block is sensitive and personal. Rules:
- **Local only.** Never transmit it to any external service or include it in a resume/PDF.
- **Don't echo** the values unless the user explicitly asks to see them.
- **Use it to serve the user**: set urgency from `timeline`; respect `work_authorization` when judging whether a role must sponsor; prioritize accordingly.
- **Be supportive** — this is often stressful, time-boxed information. Never pressure or judge.
Reasoning with the profile
- `primary_stack` ranks first in every tailored resume; `secondary_stack` is surfaced only when a JD needs it.
- `differentiators` lead in summaries and referral notes.
- `framing_notes` are defaults applied during tailoring; the user can edit them via `/rebound:profile`.
- Keep the raw `roles[].bullets` verbatim as the truth source; tailoring re-words copies of them, never the stored originals.
Read more
name: profile-memory description: How Rebound stores and reuses the user's career profile, including the private "situation" (work authorization, timeline). Use when reading, writing, or reasoning about the saved profile at ~/.rebound/.
Profile & Memory
Rebound persists one profile per machine so the user never re-enters their details. It is the reusable base for every `/rebound:tailor`, `/rebound:match`, and `/rebound:rise`.
Location & format
- `~/.rebound/profile.json` — machine-readable (authoritative).
- `~/.rebound/profile.md` — human-readable mirror (keep in sync on every write).
- `~/.rebound/pylibs/` — bundled python deps (python-docx).
Create `~/.rebound/` if missing. On updates, rewrite both files and confirm.
Schema
{
"name": "", "contact": "", "current_title": "", "years_experience": "",
"base_resume_path": "",
"primary_stack": [], "secondary_stack": [], "differentiators": [],
"roles": [{"title": "", "org": "", "location": "", "dates": "", "bullets": []}],
"education": [], "certifications": [],
"situation": {
"work_authorization": null, // high-level only: "no sponsorship needed" | "will need sponsorship" | null
"timeline": null, // absolute dates + runway, e.g. "authorization/sponsorship deadline ~2026-08-15; ~60 days"
"target_roles": [], "locations": [], "work_mode": null, "notes": null
},
"preferences": {
"framing_notes": [
"fast learner across stacks; strong OOP/systems fundamentals",
"surface secondary skills but never above primary stack",
"honesty-first: never claim expertise in unused tech"
]
}
}The private "situation" — handle with care
This block is sensitive and personal. Rules:
- **Local only.** Never transmit it to any external service or include it in a resume/PDF.
- **Don't echo** the values unless the user explicitly asks to see them.
- **Use it to serve the user**: set urgency from `timeline`; respect `work_authorization` when judging whether a role must sponsor; prioritize accordingly.
- **Be supportive** — this is often stressful, time-boxed information. Never pressure or judge.
Reasoning with the profile
- `primary_stack` ranks first in every tailored resume; `secondary_stack` is surfaced only when a JD needs it.
- `differentiators` lead in summaries and referral notes.
- `framing_notes` are defaults applied during tailoring; the user can edit them via `/rebound:profile`.
- Keep the raw `roles[].bullets` verbatim as the truth source; tailoring re-words copies of them, never the stored originals.
Knocked down. Not out. A Claude Code plugin that turns a job description into a tailored, honest, ATS-safe résumé (Word + PDF) in one command — then remembers who you are so the next one takes seconds.
Other skills on rebound.
More skills from other plugins.
prompt-lookup
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to…
Questions about profile-memory.
- Which coding agents can use profile-memory?
- profile-memory installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

