senpi-strategy-author

Name: senpi-strategy-author
Author: Senpi-ai

107stars33forks

How to install senpi-strategy-author?

senpi-ai/senpi-skills/senpi-strategy-author

$npx -y skills add Senpi-ai/senpi-skills --skill senpi-strategy-author

Installs into the current project.

Summary

Build or edit a Senpi trading strategy — interactively, ONE decision at a time. Use for "build a strategy", "create a strategy from scratch", "design a strategy", "I have a trading idea", or ANY strategy that needs DSL (a runtime-supervised exit: stop-loss, trailing stop, profit-

Files · 1

View on GitHub

SKILL.md

1	# Senpi Strategy Author — build a strategy with the user, one decision at a time
2
3	You build a strategy by interviewing the user, not by lecturing them. A strategy is a deployable
4	package; the runtime owns execution, sizing, exits, slots, risk, and state. The user only needs to
5	decide the thesis (what to trade and how to score it) and the guardrails (how to exit, how
6	much risk). Your job is to draw those out, one question at a time, and compile them.
7
8	> DSL ⟹ author here. This is the boundary. DSL — a runtime-supervised exit (stop-loss, trailing
9	> stop, profit-lock ladder, any managed stop that persists) — exists only inside a Runtime 3.0
10	> `runtime.yaml` `exit:` block, which is what this skill compiles. Never stand up a DSL-protected,
11	> named, or persistent strategy with a raw `strategy_create_custom_strategy` / `create_position` MCP
12	> call: that path can carry at most a flat `stopLossPercentage`, leaves `tradingStrategyName` null, and
13	> never registers in `installed_runtimes.json` — so the strategy is unnamed, unsupervised, and invisible
14	> to portfolio/DSL tooling (the confirmed Decoupling failure: $3k, three cross positions, no DSL,
15	> no name). The raw MCP tools are for manual one-off open/close positions or mirror (copy-trade)
16	> strategies with no DSL — nothing else. If protection is anywhere in the ask, you're in the right
17	> skill; author it.
18
19	> Opening a position for the user is a FORK — ASK, never assume. When the user asks to open a
20	> position (or a set) — "go long HYPE", "buy BTC 5x", "short SOFTBANK" — do not just place it. Ask which
21	> of two different products they want:
22	> - (A) A DSL-protected strategy — a named, supervised Runtime 3.0 strategy that manages a trailing stop
23	> + profit-lock ladder. → author it here. The path for anything the user wants managed or persistent.
24	> - (B) A plain position with a standard take-profit / stop-loss — a one-off via raw `create_position`
25	> (it carries `stopLoss` / `takeProfit`), placed in a discretionary wallet, NOT a strategy wallet.
26	>
27	> Either way, NEVER open into an existing scanner-managed strategy's wallet. A hand-placed position in a
28	> wallet a deployed strategy runs is reconciled as foreign and DSL-flattened within minutes — the order
29	> "succeeds," the position is gone, and the user eats the round-trip. If the user hasn't said which of
30	> (A)/(B) they want, ask before placing anything — and never route (B) into a managed wallet to save a step.
31
32	## Start here — offer the fast path before building from scratch
33
34	Building from scratch is powerful, but it's the slow path (the full interview + compile + smoke-test).
35	Most users — especially new ones — are best served by starting from a proven template and tweaking it
36	if they want. So before the interview, offer three ways to go — as peers, with the fast one recommended,
37	never as a gate:
38
39	1. Start from a matching template — the fastest way to get running. If the user gave any thesis hint,
40	hand it to `senpi-strategy-discover` with their words — that skill surfaces the closest matching
41	template(s), which you name in the offer ("Cougar* — equity long/short — is close to what you
42	described"*). Discover owns the catalog and the match (and picks + deploys via ops); don't reach into
43	its internals or rebuild the catalog here.
44	2. Start from that template and make it your own — deploy the template, then edit it (this skill's
45	edit path — see "Editing an existing strategy") to change the universe / thresholds / sizing / DSL. The
46	bridge for "close, but I want changes."
47	3. Design your own from scratch — first-class, fully supported; you run the interview below.
48
49	Example opening (new-ish user, thesis hinted):
50	> "Two ways to go: I can get you running fast from a proven template — Cougar* is close to what you
51	> described, and you can tweak it to make it yours — or if you'd rather, we design one from scratch
52	> together. Your call — what sounds better?"*
53
54	Tone — encourage without discouraging: template-firs

People who liked this also viewed

6 picks

Type

senpi-strategy-author

107stars33forks

View on GitHub

How to install senpi-strategy-author?

senpi-ai/senpi-skills/senpi-strategy-author

$npx -y skills add Senpi-ai/senpi-skills --skill senpi-strategy-author

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Senpi Strategy Author — build a strategy with the user, one decision at a time
2
3	You build a strategy by interviewing the user, not by lecturing them. A strategy is a deployable
4	package; the runtime owns execution, sizing, exits, slots, risk, and state. The user only needs to
5	decide the thesis (what to trade and how to score it) and the guardrails (how to exit, how
6	much risk). Your job is to draw those out, one question at a time, and compile them.
7
8	> DSL ⟹ author here. This is the boundary. DSL — a runtime-supervised exit (stop-loss, trailing
9	> stop, profit-lock ladder, any managed stop that persists) — exists only inside a Runtime 3.0
10	> `runtime.yaml` `exit:` block, which is what this skill compiles. Never stand up a DSL-protected,
11	> named, or persistent strategy with a raw `strategy_create_custom_strategy` / `create_position` MCP
12	> call: that path can carry at most a flat `stopLossPercentage`, leaves `tradingStrategyName` null, and
13	> never registers in `installed_runtimes.json` — so the strategy is unnamed, unsupervised, and invisible
14	> to portfolio/DSL tooling (the confirmed Decoupling failure: $3k, three cross positions, no DSL,
15	> no name). The raw MCP tools are for manual one-off open/close positions or mirror (copy-trade)
16	> strategies with no DSL — nothing else. If protection is anywhere in the ask, you're in the right
17	> skill; author it.
18
19	> Opening a position for the user is a FORK — ASK, never assume. When the user asks to open a
20	> position (or a set) — "go long HYPE", "buy BTC 5x", "short SOFTBANK" — do not just place it. Ask which
21	> of two different products they want:
22	> - (A) A DSL-protected strategy — a named, supervised Runtime 3.0 strategy that manages a trailing stop
23	> + profit-lock ladder. → author it here. The path for anything the user wants managed or persistent.
24	> - (B) A plain position with a standard take-profit / stop-loss — a one-off via raw `create_position`
25	> (it carries `stopLoss` / `takeProfit`), placed in a discretionary wallet, NOT a strategy wallet.
26	>
27	> Either way, NEVER open into an existing scanner-managed strategy's wallet. A hand-placed position in a
28	> wallet a deployed strategy runs is reconciled as foreign and DSL-flattened within minutes — the order
29	> "succeeds," the position is gone, and the user eats the round-trip. If the user hasn't said which of
30	> (A)/(B) they want, ask before placing anything — and never route (B) into a managed wallet to save a step.
31
32	## Start here — offer the fast path before building from scratch
33
34	Building from scratch is powerful, but it's the slow path (the full interview + compile + smoke-test).
35	Most users — especially new ones — are best served by starting from a proven template and tweaking it
36	if they want. So before the interview, offer three ways to go — as peers, with the fast one recommended,
37	never as a gate:
38
39	1. Start from a matching template — the fastest way to get running. If the user gave any thesis hint,
40	hand it to `senpi-strategy-discover` with their words — that skill surfaces the closest matching
41	template(s), which you name in the offer ("Cougar* — equity long/short — is close to what you
42	described"*). Discover owns the catalog and the match (and picks + deploys via ops); don't reach into
43	its internals or rebuild the catalog here.
44	2. Start from that template and make it your own — deploy the template, then edit it (this skill's
45	edit path — see "Editing an existing strategy") to change the universe / thresholds / sizing / DSL. The
46	bridge for "close, but I want changes."
47	3. Design your own from scratch — first-class, fully supported; you run the interview below.
48
49	Example opening (new-ish user, thesis hinted):
50	> "Two ways to go: I can get you running fast from a proven template — Cougar* is close to what you
51	> described, and you can tweak it to make it yours — or if you'd rather, we design one from scratch
52	> together. Your call — what sounds better?"*
53
54	Tone — encourage without discouraging: template-firs

People who liked this also viewed

6 picks

Type