← ClaudeAtlas

fire-trackerlisted

Track FIRE progress by orchestrating the public planfi MCP. Use whenever someone wants to know whether they're already financially independent or can coast, how their savings/net worth benchmark against peers, which net-worth milestones they've hit, or whether they can retire by a target age and which levers get them there — e.g. "am I already financially independent?", "can I coast to retirement?", "how do I compare to other people my age?", "what milestones have I hit?", "can I retire by 50?".
KameronKales/planfi-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill KameronKales/planfi-skills
# FIRE Tracker A thin orchestration layer over the **planfi MCP** (https://ai.planfi.app/mcp, public, no auth). All the math — the already-won surplus/cushion test, peer benchmarking, milestone thresholds, and the goal solver's lever ranking — lives server-side. This skill only gathers inputs and calls the tools — it does **not** compute anything locally and bakes in no defaults of its own. Read-only. ## Step 0 — Make sure the planfi tools are connected This skill uses these tools (may be namespaced, e.g. `mcp__planfi__analyze_already_won`): `analyze_already_won`, `analyze_fire_benchmark`, `analyze_fire_variants`, `analyze_milestones`, `solve_goal`, plus optional `generate_financial_plan` (for `plan_id` chaining + a `share_url`). Use whichever name your environment exposes (bare or `mcp__planfi__`-prefixed); below they are written bare. If they're NOT available, tell the user to connect the MCP, then continue: ``` claude mcp add --transport http planfi https://ai.planfi.app/mcp ``` (On claude.ai: add a custom connector pointing at https://ai.planfi.app/mcp — no auth.) ## Step 1 — (Optional but preferred) build a plan first to chain context + get a share link If the user has (or wants) a full household model, call **`generate_financial_plan`** once and **capture the returned `plan_id`**. **Four of the five** tools — `analyze_already_won`, `analyze_milestones`, `analyze_fire_variants`, and `solve_goal` — accept `{ plan_id }` (plus an `overrides` object), so they can res