boomkin 0.9.1 → 0.11.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +15 -0
- package/README.md +24 -16
- package/catalog/skills.json +8 -7
- package/catalog/templates.json +41 -0
- package/catalog/workflows.json +40 -0
- package/dist/cli.js +1619 -295
- package/dist/desk/app.js +421 -0
- package/dist/desk/assets/OFL-Manrope.txt +93 -0
- package/dist/desk/assets/favicon.svg +1 -0
- package/dist/desk/assets/manrope.ttf +0 -0
- package/dist/desk/data/bitcoin-180d.json +739 -0
- package/dist/desk/data/bitcoin-capture.json +14 -0
- package/dist/desk/data/synthetic-daily.json +258 -0
- package/dist/desk/desk.css +20 -0
- package/dist/desk/index.html +67 -0
- package/dist/desk/ui.d.ts +22 -0
- package/dist/desk/ui.js +114 -0
- package/dist/desk/vendor/LICENSE +21 -0
- package/dist/desk/vendor/provenance.json +12 -0
- package/dist/desk/vendor/strategy-engine.mjs +234 -0
- package/docs/AGENT-INDEX.md +6 -2
- package/docs/DESK.md +70 -0
- package/docs/GETTING-STARTED.md +20 -3
- package/docs/PROJECTS.md +17 -0
- package/docs/UPDATES.md +2 -2
- package/docs/WORKFLOWS.md +17 -1
- package/docs/assets/boomkin-desk.jpg +0 -0
- package/llms.txt +4 -2
- package/package.json +2 -2
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,20 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.11.0 · 2026-10-09
|
|
4
|
+
|
|
5
|
+
- Add a local browser desk with guided public-tool preparation, asset snapshots, Hyperliquid wallet cost reviews and documented strategy comparisons.
|
|
6
|
+
- Preserve frozen inputs and separate saved runs with progress, cancellation, sources, hashes, exports and explicit partial/failure/interruption states.
|
|
7
|
+
- Add optional native Hermes browser model setup and explicit research follow-ups; keep credentials and the agent loop with Hermes.
|
|
8
|
+
- Bind the desk to authenticated loopback access, reject foreign origins and unsafe paths, and verify installed helper resources before execution.
|
|
9
|
+
- Simplify the human start path and document the local API, evidence contracts and recovery for agents.
|
|
10
|
+
|
|
11
|
+
## 0.10.0 · 2026-10-09
|
|
12
|
+
|
|
13
|
+
- Add four reviewed project templates with explicit defaults and required inputs, frozen per-project context and previews without model or data calls.
|
|
14
|
+
- Add public Hyperliquid wallet audits, market research, completed-trade review and frozen strategy validation workflows, expanding discovery to 31 tasks.
|
|
15
|
+
- Add research rule presets and separate held-out/higher-cost validation to the browser strategy lab, with downloadable reports and disclosed restart accounting.
|
|
16
|
+
- Review independently released Hyperliquid 0.4.0 and strategy 0.2.0 resources; preserve immutable source pins and existing profile selections.
|
|
17
|
+
|
|
3
18
|
## 0.9.1 · 2026-10-08
|
|
4
19
|
|
|
5
20
|
- Refresh the GitHub and npm introduction with a browser demo, clear installation steps and a public-data first task.
|
package/README.md
CHANGED
|
@@ -2,15 +2,15 @@
|
|
|
2
2
|
|
|
3
3
|
**Your open-source DeFi desk.**
|
|
4
4
|
|
|
5
|
-
Research
|
|
5
|
+
Research an asset, review public wallet costs and test a strategy in a simple local browser desk. Keep the result, sources and run history on your computer. Add native [Hermes research](https://github.com/NousResearch/hermes-agent) when you want to investigate further.
|
|
6
6
|
|
|
7
|
-
[](https://galleonlabs.github.io/boomkin/docs/desk/)
|
|
8
8
|
|
|
9
9
|
**[Try the strategy lab →](https://galleonlabs.github.io/boomkin/lab/)** · [Explore workflows](https://galleonlabs.github.io/boomkin/#workflows) · [Read the docs](https://galleonlabs.github.io/boomkin/docs/)
|
|
10
10
|
|
|
11
|
-
The browser demo needs no installation.
|
|
11
|
+
The browser demo needs no installation. Choose a research rule, compare held-out periods and higher trading costs, and inspect simulated trades using a dated Bitcoin capture, synthetic prices or your own dataset. Uploaded data stays in your browser.
|
|
12
12
|
|
|
13
|
-
**
|
|
13
|
+
**31 workflows · 60 providers in discovery · 17 independent packs · 49 reviewed skills**
|
|
14
14
|
|
|
15
15
|
[](https://github.com/galleonlabs/boomkin/actions/workflows/ci.yml)
|
|
16
16
|
[](https://www.npmjs.com/package/boomkin)
|
|
@@ -21,25 +21,33 @@ The browser demo needs no installation. Compare daily spot rules, change fees an
|
|
|
21
21
|
Use macOS or Linux with [Bun](https://bun.sh) 1.3.12+ and Git. Windows users can use WSL2.
|
|
22
22
|
|
|
23
23
|
```bash
|
|
24
|
-
bun install -g boomkin@0.
|
|
25
|
-
boomkin
|
|
26
|
-
boomkin doctor --live
|
|
27
|
-
boomkin start
|
|
24
|
+
bun install -g boomkin@0.11.0
|
|
25
|
+
boomkin desk
|
|
28
26
|
```
|
|
29
27
|
|
|
30
|
-
|
|
28
|
+
Choose **Prepare public tools**, then a task. Boomkin installs the three reviewed packs needed for the desk into `~/.boomkin/hermes`, retaining your existing instructions and selections. Public jobs need no model account or funded wallet. The launching terminal owns the local server; Ctrl-C stops it.
|
|
31
29
|
|
|
32
|
-
|
|
30
|
+
Optional model setup opens Hermes's own isolated browser dashboard. Hermes owns sign-in and model selection; explicit research follow-ups use your account and may incur provider usage. The desk installs no background service or scheduler. [Local desk guide and API](docs/DESK.md).
|
|
33
31
|
|
|
34
|
-
[
|
|
32
|
+
[Native agent chat, profiles and source setup](docs/GETTING-STARTED.md) · [Model connections](docs/CONNECTIONS.md)
|
|
35
33
|
|
|
36
34
|
## First useful task
|
|
37
35
|
|
|
38
|
-
|
|
36
|
+
Choose **Review a wallet**, supply a public Hyperliquid address and date range, or try the clearly labeled public vault example. Read fees, signed funding and current exposure; expand the source evidence, export the report, then reopen it from Recent research.
|
|
37
|
+
|
|
38
|
+
**Research an asset** captures public USD marks and their age. **Test a strategy** compares a documented daily rule across independently restarted reference and held-out periods at baseline and higher costs. Wallet coverage and simulation assumptions remain visible. Refresh saves a new run without overwriting earlier work.
|
|
39
|
+
|
|
40
|
+
## Start from a research template
|
|
39
41
|
|
|
40
|
-
|
|
42
|
+
```bash
|
|
43
|
+
boomkin templates
|
|
44
|
+
boomkin templates --template wallet-audit --json
|
|
45
|
+
boomkin project create --name wallet-review \
|
|
46
|
+
--template wallet-audit --input-file ./inputs.json
|
|
47
|
+
boomkin project run --name wallet-review --dry-run
|
|
48
|
+
```
|
|
41
49
|
|
|
42
|
-
|
|
50
|
+
Four reviewed templates cover public wallet cost audits, frozen strategy validation, stablecoin income and thesis review. Supply your public account/window or local dataset/rule paths; required fields and defaults are visible before saving. Templates preserve the question and evidence in your own profile. [Inputs and run guide](docs/PROJECTS.md)
|
|
43
51
|
|
|
44
52
|
## Pick a job
|
|
45
53
|
|
|
@@ -61,7 +69,7 @@ Workflow discovery runs locally. Each job names its inputs, expected result and
|
|
|
61
69
|
| Review an exact unsigned payload | `unsigned-plan`, `transaction-simulation` |
|
|
62
70
|
| Research prediction markets | `prediction-research`, `prediction-resolution` |
|
|
63
71
|
|
|
64
|
-
[All
|
|
72
|
+
[All 31 workflows, inputs and outputs](docs/WORKFLOWS.md)
|
|
65
73
|
|
|
66
74
|
## Keep the question and the evidence
|
|
67
75
|
|
|
@@ -121,7 +129,7 @@ Fresh onboarding includes all 17 packs. Repeated `--pack` options choose fewer;
|
|
|
121
129
|
## Updates and recovery
|
|
122
130
|
|
|
123
131
|
```bash
|
|
124
|
-
bun install -g boomkin@0.
|
|
132
|
+
bun install -g boomkin@0.11.0
|
|
125
133
|
boomkin check --directory "$HOME/.boomkin/hermes"
|
|
126
134
|
boomkin update --directory "$HOME/.boomkin/hermes"
|
|
127
135
|
boomkin doctor --directory "$HOME/.boomkin/hermes" --live
|
package/catalog/skills.json
CHANGED
|
@@ -23,9 +23,9 @@
|
|
|
23
23
|
{
|
|
24
24
|
"id": "hyperliquid-skills",
|
|
25
25
|
"source": "galleonlabs/crypto-defi-skills",
|
|
26
|
-
"description": "
|
|
27
|
-
"version": "0.
|
|
28
|
-
"revision": "
|
|
26
|
+
"description": "Hyperliquid market research, trade planning, monitoring, performance review and reproducible public wallet cost audits.",
|
|
27
|
+
"version": "0.4.0",
|
|
28
|
+
"revision": "3f91a955d59a55b9927403ddc3c2e26660d48bf8",
|
|
29
29
|
"skills": [
|
|
30
30
|
"hyperliquid-analyze",
|
|
31
31
|
"hyperliquid-engineer",
|
|
@@ -33,7 +33,8 @@
|
|
|
33
33
|
"hyperliquid-monitor",
|
|
34
34
|
"hyperliquid-plan",
|
|
35
35
|
"hyperliquid-review",
|
|
36
|
-
"hyperliquid-setup"
|
|
36
|
+
"hyperliquid-setup",
|
|
37
|
+
"hyperliquid-wallet-audit"
|
|
37
38
|
],
|
|
38
39
|
"path": "packages/hyperliquid",
|
|
39
40
|
"package": "galleon-hyperliquid-skills"
|
|
@@ -201,9 +202,9 @@
|
|
|
201
202
|
{
|
|
202
203
|
"id": "defi-strategy-skills",
|
|
203
204
|
"source": "galleonlabs/crypto-defi-skills",
|
|
204
|
-
"description": "Test daily spot rules with
|
|
205
|
-
"version": "0.
|
|
206
|
-
"revision": "
|
|
205
|
+
"description": "Test frozen daily spot rules with chronological held-out periods, higher trading costs and reproducible same-cost benchmarks.",
|
|
206
|
+
"version": "0.2.0",
|
|
207
|
+
"revision": "3f91a955d59a55b9927403ddc3c2e26660d48bf8",
|
|
207
208
|
"skills": [
|
|
208
209
|
"galleon-defi-strategy-backtest"
|
|
209
210
|
],
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
{
|
|
2
|
+
"schemaVersion": 1,
|
|
3
|
+
"templates": [
|
|
4
|
+
{
|
|
5
|
+
"id": "wallet-audit",
|
|
6
|
+
"title": "Find the costs in a Hyperliquid wallet",
|
|
7
|
+
"workflow": "hyperliquid-wallet-audit",
|
|
8
|
+
"description": "Reconcile a public account's realized activity, fees, funding and current exposure. Preserve raw sources and explain incomplete history.",
|
|
9
|
+
"defaults": { "network": "mainnet", "maxPages": 10 },
|
|
10
|
+
"requiredInputs": ["account", "startTime", "endTime"],
|
|
11
|
+
"exampleInputs": { "account": "YOUR_PUBLIC_ACCOUNT_ADDRESS", "startTime": "2026-10-01T00:00:00.000Z", "endTime": "2026-10-08T00:00:00.000Z" }
|
|
12
|
+
},
|
|
13
|
+
{
|
|
14
|
+
"id": "strategy-validation",
|
|
15
|
+
"title": "Test a rule on an untouched period",
|
|
16
|
+
"workflow": "strategy-validation",
|
|
17
|
+
"description": "Freeze a daily spot rule, compare higher trading costs and inspect a separate held-out period against the same-cost benchmark.",
|
|
18
|
+
"defaults": {},
|
|
19
|
+
"requiredInputs": ["dataFile", "specFile"],
|
|
20
|
+
"exampleInputs": { "dataFile": "/absolute/path/to/daily-prices.json", "specFile": "/absolute/path/to/frozen-rule.json" }
|
|
21
|
+
},
|
|
22
|
+
{
|
|
23
|
+
"id": "stablecoin-yields",
|
|
24
|
+
"title": "Screen stablecoin income",
|
|
25
|
+
"workflow": "yield-screen",
|
|
26
|
+
"description": "Separate base income from incentives and collect the missing exit and liquidity evidence before a deposit decision.",
|
|
27
|
+
"defaults": { "minimumTvlUsd": "10000000", "limit": 5, "yieldPreference": "Separate base yield from incentive emissions" },
|
|
28
|
+
"requiredInputs": ["chain", "asset"],
|
|
29
|
+
"exampleInputs": { "chain": "Ethereum", "asset": "USDC" }
|
|
30
|
+
},
|
|
31
|
+
{
|
|
32
|
+
"id": "thesis-review",
|
|
33
|
+
"title": "Keep an investment thesis accountable",
|
|
34
|
+
"workflow": "thesis-review",
|
|
35
|
+
"description": "Save explicit invalidation conditions and review preferences, then compare each research run with its captured baseline.",
|
|
36
|
+
"defaults": { "reviewFrequency": "Weekly", "notifyWhen": "An invalidation condition changes verdict" },
|
|
37
|
+
"requiredInputs": ["asset", "thesis", "invalidationConditions", "evidenceStandard"],
|
|
38
|
+
"exampleInputs": { "asset": "YOUR_EXACT_ASSET_IDENTITY", "thesis": "YOUR_THESIS", "invalidationConditions": ["YOUR_MEASURABLE_INVALIDATION_CONDITION"], "evidenceStandard": "YOUR_PRIMARY_SOURCE_REQUIREMENTS" }
|
|
39
|
+
}
|
|
40
|
+
]
|
|
41
|
+
}
|
package/catalog/workflows.json
CHANGED
|
@@ -1,6 +1,46 @@
|
|
|
1
1
|
{
|
|
2
2
|
"schemaVersion": 1,
|
|
3
3
|
"workflows": [
|
|
4
|
+
{
|
|
5
|
+
"id": "hyperliquid-wallet-audit",
|
|
6
|
+
"protocol": "Hyperliquid",
|
|
7
|
+
"title": "Find fees, funding costs and exposure in a public wallet",
|
|
8
|
+
"skill": "hyperliquid-wallet-audit",
|
|
9
|
+
"pack": "hyperliquid-skills",
|
|
10
|
+
"inputs": ["Public account address and mainnet or testnet", "UTC startTime and endTime for the activity window", "Maximum history pages and explicit coverage limits"],
|
|
11
|
+
"output": "Reproducible wallet diagnostics with captured source hashes, observed realized PnL, signed fees and funding, maker/taker costs, current exposure and explicit history gaps.",
|
|
12
|
+
"access": "Bounded official Hyperliquid public info reads; no trading key or wallet connection. Default perpetual activity is distinct from a complete portfolio or verified investment return."
|
|
13
|
+
},
|
|
14
|
+
{
|
|
15
|
+
"id": "strategy-validation",
|
|
16
|
+
"protocol": "Strategy research",
|
|
17
|
+
"title": "Validate a frozen rule with higher costs and a held-out period",
|
|
18
|
+
"skill": "galleon-defi-strategy-backtest",
|
|
19
|
+
"pack": "defi-strategy-skills",
|
|
20
|
+
"inputs": ["Absolute dataFile and specFile paths for a sourced daily USD series and frozen rule", "Optional splitIndex for the first held-out observation", "Baseline fees/slippage and higher-cost assumptions"],
|
|
21
|
+
"output": "Separate baseline and higher-cost results for development and held-out periods, same-cost benchmarks, trade logs, input hashes and explicit independent restart accounting.",
|
|
22
|
+
"access": "Local Node.js helper with no wallet or network request; no parameter optimization, live execution or forward-return claim."
|
|
23
|
+
},
|
|
24
|
+
{
|
|
25
|
+
"id": "hyperliquid-market",
|
|
26
|
+
"protocol": "Hyperliquid",
|
|
27
|
+
"title": "Research a Hyperliquid market before planning a trade",
|
|
28
|
+
"skill": "hyperliquid-analyze",
|
|
29
|
+
"pack": "hyperliquid-skills",
|
|
30
|
+
"inputs": ["Exact network, market and DEX identity", "Research question, observation window and freshness limit", "Liquidity, funding and catalyst evidence requirements"],
|
|
31
|
+
"output": "Cited market/funding/liquidity evidence, supported thesis and invalidation conditions with data gaps; historical, paper and live evidence stay separate.",
|
|
32
|
+
"access": "Existing official public info reads or explicitly configured tools; market analysis grants no financial authority."
|
|
33
|
+
},
|
|
34
|
+
{
|
|
35
|
+
"id": "hyperliquid-review",
|
|
36
|
+
"protocol": "Hyperliquid",
|
|
37
|
+
"title": "Review a completed trade against its original intent",
|
|
38
|
+
"skill": "hyperliquid-review",
|
|
39
|
+
"pack": "hyperliquid-skills",
|
|
40
|
+
"inputs": ["Account, market/DEX and completed trade window", "Original ticket, risk unit, order/fill identities and exchange history", "Signed fees/funding, position changes and incident record"],
|
|
41
|
+
"output": "Reconciled trade outcome and cost accounting with a separate process grade, incident findings and one supported follow-up test.",
|
|
42
|
+
"access": "Read-only exchange history and local arithmetic; a profitable result does not establish that controls or authorization were respected."
|
|
43
|
+
},
|
|
4
44
|
{
|
|
5
45
|
"id": "market-snapshot",
|
|
6
46
|
"protocol": "Market data",
|