agentleFS
krzysukrzysu/market-skills/skills/market-fibonacci/SKILL.md

market-fibonacci

Skill3 starsChanged 4 months agoMITView on GitHub

Computes Fibonacci retracement levels (0.236/0.382/0.5/0.618/0.786) and extensions (1.272/1.618) from the most recent swing high/low. Use for identifying potential support/resistance zones and price targets. Supports any yfinance ticker.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not enter purely off a fib level — confirm confluence with market-s-r (touches >= 3) and a trend context.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

market-fibonacci

Fibonacci retracement and extension analysis based on the most recent significant swing high and swing low.

When NOT to use

  • This is a context/level skill, not a directional signal — it returns zones, never a buy/sell call. Pair with a directional read (market-trend, market-s-r) before acting.
  • It needs a clear recent swing high/low; on choppy or range-less series the levels are arbitrary. Requires 25+ candles minimum.
  • Do not enter purely off a fib level — confirm confluence with market-s-r (touches >= 3) and a trend context.

Quick Start

uv run skills/market-fibonacci/scripts/run.py AAPL --json

Flags

FlagDefaultNotes
TICKER (positional)—Required. Supports provider:ticker (e.g. hl:LIT, yf:AAPL).
--jsonhumanEmit JSON to stdout.
--source=PROVIDERauto-detectForce a data provider (see README).
--interval=INTERVAL1d1m/2m/5m/15m/30m/1h/2h/4h/8h/12h/1d/3d/1wk/1M.
--period=PERIOD1y1d/5d/1mo/3mo/6mo/1y/2y/5y/10y/ytd/max.

Both timeframe flags are validated — bad values exit 2 with a friendly error. Defaults give daily candles over 1y (~250 bars), enough for a recent swing high/low pair. For intraday (--interval=1h), bump --period to 6mo or 1y; yfinance caps hourly at ~2y and anything sub-hour at ~60d.

What it returns

  • fib_levels — dict of all retracement and extension levels
  • swing_high, swing_low — the identified swing points
  • current_position — above_swing_high / below_swing_low / inside_swing
  • nearest_fib_support — closest fib level below current price
  • nearest_fib_resistance — closest fib level above current price
  • nearest_fib_distance_pct — distance to nearest fib level

Interpretation

Key LevelSignificance
0.382Shallow retracement — trend may continue
0.5Psychological midpoint — watch for reversal
0.618Golden ratio — strongest retracement level
0.786Deep retracement — trend may be ending
1.272 / 1.618Extension targets if price breaks beyond swing

Edge Cases

  • Context skill: no directional score or signal.
  • Swing point detection uses a 5-bar window — less sensitive than parameterized versions.
  • Requires 25+ candles minimum for reliable swing identification.
  • Combine with market-s-r for multi-level confluence confirmation.

Output envelope (AXI)

--json output follows the canonical AXI envelope — {data, count, errors, help[]}. Default schema is the per-skill minimal fields (3-6 essentials); pass --fields=<csv> to project or --full for the full payload. count is the item count, help[] is contextual next-step command templates. Lib.py return shapes (L1Result / L2Result / L3Result / L3Idea / RegimeSignal) are unchanged — the envelope wraps them at the scripts/run.py boundary.

Home view (no-arg mode)

No-arg mode prints the home view from $XDG_DATA_HOME/market-skills/<skill>_last.json (last successful run). Errors are not cached.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.