edge-hint-extractor

Name: edge-hint-extractor
Author: mphinance

15stars3forks

How to install edge-hint-extractor?

mphinance/alpha-skills/edge-hint-extractor

$npx -y skills add mphinance/alpha-skills --skill edge-hint-extractor

Installs into the current project.

Summary

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.

Files · 1

View on GitHub

SKILL.md

1	# Edge Hint Extractor
2
3	## Overview
4
5	Convert raw observation signals (`market_summary`, `anomalies`, `news reactions`) into structured edge hints.
6	This skill is the first stage in the split workflow: `observe -> abstract -> design -> pipeline`.
7
8	## When to Use
9
10	- You want to turn daily market observations into reusable hint objects.
11	- You want LLM-generated ideas constrained by current anomalies/news context.
12	- You need a clean `hints.yaml` input for concept synthesis or auto detection.
13
14	## Prerequisites
15
16	- Python 3.9+
17	- `PyYAML`
18	- Optional inputs from detector run:
19	- `market_summary.json`
20	- `anomalies.json`
21	- `news_reactions.csv` or `news_reactions.json`
22
23	## Output
24
25	- `hints.yaml` containing:
26	- `hints` list
27	- generation metadata
28	- rule/LLM hint counts
29
30	## Workflow
31
32	1. Gather observation files (`market_summary`, `anomalies`, optional news reactions).
33	2. Run `scripts/build_hints.py` to generate deterministic hints.
34	3. Optionally augment hints with LLM ideas via one of two methods:
35	- a. `--llm-ideas-cmd` — pipe data to an external LLM CLI (subprocess).
36	- b. `--llm-ideas-file PATH` — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).
37	4. Pass `hints.yaml` into concept synthesis or auto detection.
38
39	Note: `--llm-ideas-cmd` and `--llm-ideas-file` are mutually exclusive.
40
41	## Quick Commands
42
43	Rule-based only (default output to `reports/edge_hint_extractor/hints.yaml`):
44
45	```bash
46	python3 skills/edge-hint-extractor/scripts/build_hints.py \
47	--market-summary /tmp/edge-auto/market_summary.json \
48	--anomalies /tmp/edge-auto/anomalies.json \
49	--news-reactions /tmp/news_reactions.csv \
50	--as-of 2026-02-20 \
51	--output-dir reports/
52	```
53
54	Rule + LLM augmentation (external CLI):
55
56	```bash
57	python3 skills/edge-hint-extractor/scripts/build_hints.py \
58	--market-summary /tmp/edge-auto/market_summary.json \
59	--anomalies /tmp/edge-auto/anomalies.json \
60	--llm-ideas-cmd "python3 /path/to/llm_ideas_cli.py" \
61	--output-dir reports/
62	```
63
64	Rule + LLM augmentation (pre-written file, for Claude Code):
65
66	```bash
67	python3 skills/edge-hint-extractor/scripts/build_hints.py \
68	--market-summary /tmp/edge-auto/market_summary.json \
69	--anomalies /tmp/edge-auto/anomalies.json \
70	--llm-ideas-file /tmp/llm_hints.yaml \
71	--output-dir reports/
72	```
73
74	## Resources
75
76	- `skills/edge-hint-extractor/scripts/build_hints.py`
77	- `references/hints_schema.md`

People who liked this also viewed

6 picks

Type

edge-hint-extractor

15stars3forks

View on GitHub

How to install edge-hint-extractor?

mphinance/alpha-skills/edge-hint-extractor

$npx -y skills add mphinance/alpha-skills --skill edge-hint-extractor

Installs into the current project.

Summary

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.

Files · 1

View on GitHub

SKILL.md

1	# Edge Hint Extractor
2
3	## Overview
4
5	Convert raw observation signals (`market_summary`, `anomalies`, `news reactions`) into structured edge hints.
6	This skill is the first stage in the split workflow: `observe -> abstract -> design -> pipeline`.
7
8	## When to Use
9
10	- You want to turn daily market observations into reusable hint objects.
11	- You want LLM-generated ideas constrained by current anomalies/news context.
12	- You need a clean `hints.yaml` input for concept synthesis or auto detection.
13
14	## Prerequisites
15
16	- Python 3.9+
17	- `PyYAML`
18	- Optional inputs from detector run:
19	- `market_summary.json`
20	- `anomalies.json`
21	- `news_reactions.csv` or `news_reactions.json`
22
23	## Output
24
25	- `hints.yaml` containing:
26	- `hints` list
27	- generation metadata
28	- rule/LLM hint counts
29
30	## Workflow
31
32	1. Gather observation files (`market_summary`, `anomalies`, optional news reactions).
33	2. Run `scripts/build_hints.py` to generate deterministic hints.
34	3. Optionally augment hints with LLM ideas via one of two methods:
35	- a. `--llm-ideas-cmd` — pipe data to an external LLM CLI (subprocess).
36	- b. `--llm-ideas-file PATH` — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).
37	4. Pass `hints.yaml` into concept synthesis or auto detection.
38
39	Note: `--llm-ideas-cmd` and `--llm-ideas-file` are mutually exclusive.
40
41	## Quick Commands
42
43	Rule-based only (default output to `reports/edge_hint_extractor/hints.yaml`):
44
45	```bash
46	python3 skills/edge-hint-extractor/scripts/build_hints.py \
47	--market-summary /tmp/edge-auto/market_summary.json \
48	--anomalies /tmp/edge-auto/anomalies.json \
49	--news-reactions /tmp/news_reactions.csv \
50	--as-of 2026-02-20 \
51	--output-dir reports/
52	```
53
54	Rule + LLM augmentation (external CLI):
55
56	```bash
57	python3 skills/edge-hint-extractor/scripts/build_hints.py \
58	--market-summary /tmp/edge-auto/market_summary.json \
59	--anomalies /tmp/edge-auto/anomalies.json \
60	--llm-ideas-cmd "python3 /path/to/llm_ideas_cli.py" \
61	--output-dir reports/
62	```
63
64	Rule + LLM augmentation (pre-written file, for Claude Code):
65
66	```bash
67	python3 skills/edge-hint-extractor/scripts/build_hints.py \
68	--market-summary /tmp/edge-auto/market_summary.json \
69	--anomalies /tmp/edge-auto/anomalies.json \
70	--llm-ideas-file /tmp/llm_hints.yaml \
71	--output-dir reports/
72	```
73
74	## Resources
75
76	- `skills/edge-hint-extractor/scripts/build_hints.py`
77	- `references/hints_schema.md`

People who liked this also viewed

6 picks

Type