trump-truth-monitor

Name: trump-truth-monitor
Author: kansoku-trade

226stars19forks

How to install trump-truth-monitor?

kansoku-trade/kansoku/trump-truth-monitor

$npx -y skills add kansoku-trade/kansoku --skill trump-truth-monitor

Installs into the current project.

Summary

Use when monitoring or interpreting Donald Trump's Truth Social posts for market-moving events — tariff announcements, sanctions, deals with countries (China / Mexico / Canada / EU / Japan / Korea / Taiwan), specific company / CEO mentions, Fed pressure, energy / oil commentary,

Files · 1

View on GitHub

SKILL.md

1	# Trump Truth Monitor
2
3	Pulls Donald Trump's Truth Social feed via the trumpstruth.org RSS mirror, classifies posts into market-relevant topic buckets, and hands the candidate list off for LLM-level market-impact grading.
4
5	## When to use
6
7	- User asks what Trump has posted recently
8	- Pre-market gap on policy-sensitive sectors (semis, China ADRs, autos, energy, banks, defense) — check whether a Trump post is the trigger
9	- Building the "Catalyst (now)" lens of `stock-deep-dive` for a name with policy exposure (TSM, NVDA, AAPL, F, GM, XOM, BAC, RTX, LMT)
10	- `market-session-tracker` pre-market protocol — add a Trump-feed pass
11
12	If the user wants tweet history beyond ~5 days, this skill is insufficient — the RSS mirror only exposes the latest ~100 posts. Route to Factba.se / Roll Call (paid) or note the limitation explicitly.
13
14	## Data source
15
16	trumpstruth.org/feed — a public third-party mirror of @realDonaldTrump on Truth Social. RSS 2.0 XML with these fields per item:
17
18	\| Field \| Meaning \|
19	\| --------------------- \| -------------------------------------------------------------------- \|
20	\| `<pubDate>` \| RFC 2822, original Truth Social post timestamp \|
21	\| `<link>` \| trumpstruth.org/statuses/{mirror_id} \|
22	\| `<truth:originalUrl>` \| truthsocial.com/@realDonaldTrump/{truth_id} — the primary source \|
23	\| `<description>` \| Full post body with HTML (links + ellipsis spans) \|
24
25	The mirror typically lags the original by ≤2 minutes. Single feed pull returns ~100 most recent posts, covering ~5 days at Trump's typical cadence.
26
27	## CLI
28
29	### Read mode — `fetch.py`
30
31	```bash
32	# Default: last 24h, keyword-filtered, markdown
33	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py
34
35	# Wider window
36	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 72
37
38	# All posts in feed regardless of keyword
39	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 72 --all
40
41	# Single topic
42	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --topic tariff_trade
43
44	# JSON output (for chaining)
45	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --json
46	```
47
48	Topic buckets defined in script: `tariff_trade`, `semi_tech`, `energy`, `fed_macro`, `crypto`, `geopolitical`.
49
50	### Archive mode — `archive.py`
51
52	```bash
53	# Append new posts to journal/trump-feed/YYYY-MM-DD.md (idempotent)
54	python3 .claude/skills/trump-truth-monitor/scripts/archive.py
55
56	# Custom output dir
57	python3 .claude/skills/trump-truth-monitor/scripts/archive.py --out /path/to/dir
58
59	# Silent unless something new was added
60	python3 .claude/skills/trump-truth-monitor/scripts/archive.py --quiet
61	```
62
63	The archive de-dupes by mirror status_id — re-running on the same feed is a no-op. Designed to be scheduled (see `launchd/README.md`). Once archived, posts persist locally even if trumpstruth.org goes down.
64
65	## Workflow
66
67	1. Decide window. Default 24h. Use 48–72h when investigating a multi-day move. Use `--all` when context-grazing.
68	2. Decide scope. If user asks generally → no `--topic`. If user names a domain (关税 / 半导体 / 油 / 加密) → pass `--topic`.
69	3. Pull feed. Run `fetch.py` with chosen flags. Always include `--hours` — never default to "all of feed" silently.
70	4. Second-pass grading. Script output is _candidates_, not signals. For each post:
71	- Read the full text before assigning impact. Headlines and keyword tags lie.
72	- Assign a market-impact tier: `high` / `med` / `low` / `noise`
73	- high = concrete action with $ figure, %, date, named country/company (e.g. "25% tariff on Mexican imports effective June 1", "Section 232 on chips")
74	- med = directional signal without specifics (e.g. "We'll be tough on China", "must invest in America")
75	- low = brand alignment with sector (e.g. "American Energy DOMINANCE", "Crypto Capital of the World" — already-priced policy stance)
76	- noise = keyword matched but body is endorsement / personal / off-topic (e.g. "support the Military" in a Senate endorsement)
77	5. Anchor on original URL. When quoting, always cite `truth:originalUrl` (the truthsocial.com link), not the mirror.
78	6. Render output. For multi-post stretches, group by tier — high first, then med, then

People who liked this also viewed

6 picks

Type

trump-truth-monitor

226stars19forks

View on GitHub

How to install trump-truth-monitor?

kansoku-trade/kansoku/trump-truth-monitor

$npx -y skills add kansoku-trade/kansoku --skill trump-truth-monitor

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Trump Truth Monitor
2
3	Pulls Donald Trump's Truth Social feed via the trumpstruth.org RSS mirror, classifies posts into market-relevant topic buckets, and hands the candidate list off for LLM-level market-impact grading.
4
5	## When to use
6
7	- User asks what Trump has posted recently
8	- Pre-market gap on policy-sensitive sectors (semis, China ADRs, autos, energy, banks, defense) — check whether a Trump post is the trigger
9	- Building the "Catalyst (now)" lens of `stock-deep-dive` for a name with policy exposure (TSM, NVDA, AAPL, F, GM, XOM, BAC, RTX, LMT)
10	- `market-session-tracker` pre-market protocol — add a Trump-feed pass
11
12	If the user wants tweet history beyond ~5 days, this skill is insufficient — the RSS mirror only exposes the latest ~100 posts. Route to Factba.se / Roll Call (paid) or note the limitation explicitly.
13
14	## Data source
15
16	trumpstruth.org/feed — a public third-party mirror of @realDonaldTrump on Truth Social. RSS 2.0 XML with these fields per item:
17
18	\| Field \| Meaning \|
19	\| --------------------- \| -------------------------------------------------------------------- \|
20	\| `<pubDate>` \| RFC 2822, original Truth Social post timestamp \|
21	\| `<link>` \| trumpstruth.org/statuses/{mirror_id} \|
22	\| `<truth:originalUrl>` \| truthsocial.com/@realDonaldTrump/{truth_id} — the primary source \|
23	\| `<description>` \| Full post body with HTML (links + ellipsis spans) \|
24
25	The mirror typically lags the original by ≤2 minutes. Single feed pull returns ~100 most recent posts, covering ~5 days at Trump's typical cadence.
26
27	## CLI
28
29	### Read mode — `fetch.py`
30
31	```bash
32	# Default: last 24h, keyword-filtered, markdown
33	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py
34
35	# Wider window
36	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 72
37
38	# All posts in feed regardless of keyword
39	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 72 --all
40
41	# Single topic
42	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --topic tariff_trade
43
44	# JSON output (for chaining)
45	python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --json
46	```
47
48	Topic buckets defined in script: `tariff_trade`, `semi_tech`, `energy`, `fed_macro`, `crypto`, `geopolitical`.
49
50	### Archive mode — `archive.py`
51
52	```bash
53	# Append new posts to journal/trump-feed/YYYY-MM-DD.md (idempotent)
54	python3 .claude/skills/trump-truth-monitor/scripts/archive.py
55
56	# Custom output dir
57	python3 .claude/skills/trump-truth-monitor/scripts/archive.py --out /path/to/dir
58
59	# Silent unless something new was added
60	python3 .claude/skills/trump-truth-monitor/scripts/archive.py --quiet
61	```
62
63	The archive de-dupes by mirror status_id — re-running on the same feed is a no-op. Designed to be scheduled (see `launchd/README.md`). Once archived, posts persist locally even if trumpstruth.org goes down.
64
65	## Workflow
66
67	1. Decide window. Default 24h. Use 48–72h when investigating a multi-day move. Use `--all` when context-grazing.
68	2. Decide scope. If user asks generally → no `--topic`. If user names a domain (关税 / 半导体 / 油 / 加密) → pass `--topic`.
69	3. Pull feed. Run `fetch.py` with chosen flags. Always include `--hours` — never default to "all of feed" silently.
70	4. Second-pass grading. Script output is _candidates_, not signals. For each post:
71	- Read the full text before assigning impact. Headlines and keyword tags lie.
72	- Assign a market-impact tier: `high` / `med` / `low` / `noise`
73	- high = concrete action with $ figure, %, date, named country/company (e.g. "25% tariff on Mexican imports effective June 1", "Section 232 on chips")
74	- med = directional signal without specifics (e.g. "We'll be tough on China", "must invest in America")
75	- low = brand alignment with sector (e.g. "American Energy DOMINANCE", "Crypto Capital of the World" — already-priced policy stance)
76	- noise = keyword matched but body is endorsement / personal / off-topic (e.g. "support the Military" in a Senate endorsement)
77	5. Anchor on original URL. When quoting, always cite `truth:originalUrl` (the truthsocial.com link), not the mirror.
78	6. Render output. For multi-post stretches, group by tier — high first, then med, then

People who liked this also viewed

6 picks

Type