Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/nicepkg/ai-workflow/canslim-screener)<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/canslim-screener"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/canslim-screener.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.05892 |
| Opus 5 | $0.00030 | $0.02946 |
| Sonnet 5 | $0.00012 | $0.01178 |
| Haiku 4.5 | $0.00006 | $0.00589 |
Grade A, and why
canslim-screener 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANSLIM Stock Screener - Phase 2
Overview
This skill screens US stocks using William O'Neil's proven CANSLIM methodology, a systematic approach for identifying growth stocks with strong fundamentals and price momentum. CANSLIM analyzes 7 key components: Current Earnings, Annual Growth, Newness/New Highs, Supply/Demand, Leadership/RS Rank, Institutional Sponsorship, and Market Direction.
Phase 2 implements 6 of 7 components (C, A, N, S, I, M), representing 80% of the full methodology. This phase adds critical volume analysis (S) and institutional ownership tracking (I) to the Phase 1 foundation.
Two-Stage Approach:
- Stage 1 (FMP API + Finviz): Analyze stock universe with 6 CANSLIM components
- Stage 2 (Reporting): Rank by composite score and generate actionable reports
Key Features:
- Composite scoring (0-100 scale) with weighted components
- Finviz fallback for institutional ownership data (automatic when FMP data incomplete)
- Progressive filtering to optimize API usage
- JSON + Markdown output formats
- Interpretation bands: Exceptional+ (90+), Exceptional (80-89), Strong (70-79), Above Average (60-69)
- Bear market protection (M component gating)
Phase 2 Component Weights (Renormalized for 6 components):
- C (Current Earnings): 19%
- A (Annual Growth): 25%
- N (Newness): 19%
- S (Supply/Demand): 19% ← NEW
- I (Institutional): 13% ← NEW
- M (Market Direction): 6%
Future Phases:
- Phase 3: Add L (Leadership/RS Rank) → 100% coverage (full CANSLIM)
- Phase 4: FINVIZ Elite integration → 10x faster execution
When to Use This Skill
Explicit Triggers:
- "Find CANSLIM stocks"
- "Screen for growth stocks using O'Neil's method"
- "Which stocks have strong earnings and momentum?"
- "Identify stocks near 52-week highs with accelerating earnings"
- "Run a CANSLIM screener on [sector/universe]"
Implicit Triggers:
- User wants to identify multi-bagger candidates
- User is looking for growth stocks with proven fundamentals
- User wants systematic stock selection based on historical winners
- User needs a ranked list of stocks meeting O'Neil's criteria
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/canslim_methodology.md 25 KB
- references/fmp_api_endpoints.md 18 KB
- references/interpretation_guide.md 17 KB
- references/scoring_system.md 20 KB
- scripts/calculators/earnings_calculator.py 13 KB runs code
- scripts/calculators/growth_calculator.py 11 KB runs code
- scripts/calculators/institutional_calculator.py 13 KB runs code
- scripts/calculators/leadership_calculator.py 13 KB runs code
- scripts/calculators/market_calculator.py 8.0 KB runs code
- scripts/calculators/new_highs_calculator.py 6.3 KB runs code
- scripts/calculators/supply_demand_calculator.py 7.8 KB runs code
- scripts/canslim_screener_2026-01-12_000442.json 25 KB
- scripts/finviz_stock_client.py 7.0 KB runs code
- scripts/fmp_client.py 12 KB runs code
- scripts/report_generator.py 14 KB runs code
- scripts/scorer.py 22 KB runs code
- scripts/screen_canslim.py 13 KB runs code
- scripts/test_institutional_endpoint.py 3.8 KB runs code
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.
- 2d ago First seen · 600 lines · 60 tokens per session scan A 0810188f2fa7
canslim-screener is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 60 tokens to every session and 5,892 once invoked, about $0.0003 per session on Opus 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 2026-09-03.
Other skills, from other repositories
budget-allocation
按住宿/交通/餐饮/门票/杂项这些类目，给旅行预算做完整的逐项拆解，而不是 只给一个笼统的总数。Use when 用户说"这趟旅行大概要花多少钱""帮我做个 预算""这个预算够不够""钱应该怎么分配"。产出的是按类目细分、有档位区间 的预算表，而不是一个模糊的总数。.
financial-analysis
Financial analysis workflow: gather current market data, analyze metrics, contextualize against benchmarks, assess risk, report with disclaimer. Use when the user asks about stocks, markets, investments, company financials, or economic indicators.
invinoveritas
Pay-per-call agent tools over Bitcoin Lightning / USDC (x402), exposed as a remote MCP server. Use BEFORE any irreversible or consequential action (a trade, a destructive command, shipping code, spending funds) to get a capital-scale-aware governance review; for facts-only crypto market intelligence (macro risk…
qcc-risk-screen
企查查"全维度风险扫描"工作流。一次性跑 34 个 risk 维度:司法 / 失信 / 限消 / 限出 / 限高 / 经营异常 / 严重违法 / 行政处罚 / 税务异常 / 破产清算 / 股权冻结 / 质押 / 抵押 / 担保 / 公告 / 开庭 等。 适用于授信风控 / 投后监控 / M&A 红线扫描 / 重大合同前最后一道闸 / 供应商准入。配额消耗大(34 次/家),只在真的需要全维度时跑。 IF user asks for 风险扫描 / 司法风险 / 失信 / 限高 / 经营异常 / 严重违法 / DD 红线 of a Chinese company, THEN this skill. Triggers: "查司法风险"…
qcc-ownership-trace
企查查"股权穿透"工作流。聚合:实际控制人 / 受益所有人 (UBO, 25% AML 口径) / 一层股东 / 对外投资 / 工商变更记录(股权与资本变更线索)。 适用于关联交易识别 / 反洗钱合规 (KYB AML) / M&A 标的实控人确认 / 集团股权结构梳理 / 关键股东退出预警。 IF user asks about 实控人 / 股东 / UBO / 受益所有人 / 股权穿透 / 谁控制 / 对外投资 / 集团结构, THEN this skill. Triggers: "实控人是谁", "穿透股权", "查受益所有人", "对外投资了哪些", "股东结构", "股权变更", "谁拿了多少股". NOT for…
polymarket
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.