technical-analyzer

technical-analyzer is a skill for Claude Code, Codex from Haochenhust/ch-skills. It costs 73 tokens per session (926 once invoked), scanned A, original, MIT.

A stock-chart analysis workflow that examines moving-average trends, support and resistance levels, trading volume and related market measures.

In plain words
What is it for?
Use it to assess entry timing, possible buy or sell price levels, and whether a stock appears overbought or oversold.
Why use it?
It adds evidence for deciding when to enter or exit a position, while keeping company fundamentals as the main basis for the investment decision.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to assess entry timing, possible buy or sell price levels, and whether a stock appears overbought or oversold.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/haochenhust/ch-skills/technical-analyzer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Haochenhust/ch-skills --skill technical-analyzer
Clone the repo
git clone --depth 1 https://github.com/Haochenhust/ch-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for technical-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/haochenhust/ch-skills/technical-analyzer/github.svg)](https://agentmods.dev/skills/haochenhust/ch-skills/technical-analyzer)
Your own site
<a href="https://agentmods.dev/skills/haochenhust/ch-skills/technical-analyzer"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/technical-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for technical-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/haochenhust/ch-skills/technical-analyzer"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/technical-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.00926
Opus 5.5 $0.00029 $0.00370
Sonnet 5.5 $0.00015 $0.00185
Haiku 4.5 $0.00007 $0.00093

Measured 2mo ago against content hash fb8aa2074a63, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

technical-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/technical-analyzer/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Analyzer

Auxiliary timing tool for entry/exit decisions. NEVER use as primary decision basis — fundamentals first.

When to Use

  • After stock-analyzer confirms a fundamental thesis, use this to time the entry
  • When deciding specific buy/sell price levels
  • When checking if a stock is overbought/oversold

Prerequisites

Uses the sibling tushare-data / stock-market-data skills. Set once per shell:

export TUSHARE_TOKEN=<your Tushare Pro token>    # never hard-code; see the tushare-data skill
PY=python3                                       # a python3 with tushare/pandas/akshare (e.g. stock-market-data/.venv/bin/python3)
SKILLS=~/.claude/skills                          # where you installed these skills
TS=$SKILLS/tushare-data/scripts/fetch_tushare.py
AK=$SKILLS/stock-market-data/scripts

Data Retrieval

# Primary: Tushare Pro — 近3个月日K(OHLCV + 复权因子)
$PY $TS --mode daily --symbols {CODE}.SZ --start {3_MONTHS_AGO_YYYYMMDD}
$PY $TS --mode adj_factor --symbols {CODE}.SZ --start {3_MONTHS_AGO_YYYYMMDD}

# PE/PB/换手率/市值(用于量价+估值辅助)
$PY $TS --mode daily_basic --symbols {CODE}.SZ --start {3_MONTHS_AGO_YYYYMMDD}

# 周K(看中期趋势)
$PY $TS --mode weekly --symbols {CODE}.SZ --start {6_MONTHS_AGO_YYYYMMDD}

# Fallback: AKShare
$PY $AK/fetch_market_data.py --mode evening --stocks {CODE}

Data Processing

Use adj_factor to calculate 前复权价格: adj_price = close * adj_factor / latest_adj_factor This ensures MA calculations reflect true price movements (not distorted by splits/dividends).

Analysis Framework

1. Trend Assessment

  • Compare current price to 5/10/20/60 day moving averages
  • Price above all MAs = strong uptrend
  • Price below all MAs = strong downtrend
  • MAs converging = potential breakout

2. Support & Resistance

  • Recent highs/lows as reference points
  • Round numbers (e.g., 80, 100) as psychological levels
  • Volume clusters as support/resistance zones

3. Volume Analysis

  • Volume increasing with price up = healthy trend
  • Volume decreasing with price up = potential exhaustion
  • Volume spike on down day = possible capitulation/bottom

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 92 lines · 73 tokens per session scan A fb8aa2074a63

Subscribe to this mod's changes

technical-analyzer is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 926 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

technical-analyzer compared with skills from other repositories

technical-analyzer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
technical-analyzerHaochenhust/ch-skillsSkill93mo agoMITA73Claude Code, Codex
rugpull-detectorDjordjeMojsilovic/Djordjes-Claude-SetupSkill43mo agononeA205Claude Code, Codex
ma-playbookalirezarezvani/claude-skillsSkill29kyesterdayMITA29Claude Code
fiscalisteromainsimon/paperasseSkill2.6kyesterdayMITA320Claude Code, Codex
comptableromainsimon/paperasseSkill2.6kyesterdayMITA153Claude Code, Codex
syndicromainsimon/paperasseSkill2.6kyesterdayMITA204Claude Code, Codex
prompt-masternidhinjs/prompt-masterSkill16k15d agoMITB78Claude Code, Codex