Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

aeon-narrative-tracker — measured AI agent skill | DecimalAI

bankrbot/aeon-narrative-tracker

SkillScore86Maintained

Daily narrative map for crypto and AI. Each narrative gets a mindshare score (1-5), a velocity arrow (↑↑ ↑ → ↓ ↓↓), a phase label (Emerging / Rising / Peak / Fading), named drivers (@handles, not "people are saying"), and an explicit position call (FRONT-RUN / RIDE / FADE / WATCH / IGNORE). Drops narratives that grade IGNORE. Surfaces transitions vs prior runs as the headline. Triggers: "track narratives", "what's running on CT", "is X peaking", "narrative positions today".

financeby bankrbot

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Finance & Accounting pack

decimalai skills pull bankrbot-aeon-narrative-tracker

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/bankrbot-aeon-narrative-tracker/SKILL.md

Raw file: /s/bankrbot-aeon-narrative-tracker/SKILL.md ↗ · machine-readable summary at /s/bankrbot-aeon-narrative-tracker.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-24% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-31%	0%
case-07	✗→✓	▲ Improved	-17%	0%
case-03	✗→✓	▲ Improved	-32%	0%
case-05	✗→✓	▲ Improved	-19%	0%
case-06	✗→✓	▲ Improved	-39%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

bankrbot / skills

aeon-narrative-tracker/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

aeon-narrative-tracker

Decision-grade narrative map. The point isn't to print today's zeitgeist — it's to catch phase transitions and flag when the story is moving outcomes (reflexivity).

Signal sources

xAI x_search (optional XAI_API_KEY) — pre-fetched cache of 12-15 narrative threads from the last 3 days.
WebSearch — DefiLlama, Kaito mindshare, broader web.
Memory diff — narrative labels from prior runs, to compute transitions.

Output

Lead with transitions and reflexivity. Positions next. Static map last.

TRANSITIONS
  NEW: agentic-payments — first merchant adoption announcement
  PROMOTED: restaking — Rising → Peak (ETF leak)
  DEMOTED: memecoin-szn — Peak → Fading (60% vol drop WoW)
  DEAD: parallel-EVM — gone

REFLEXIVITY
  prediction-markets — protocols rebranding around the Polymarket S-1 leak

POSITIONS
  FRONT-RUN: agentic-payments (mindshare 2 ↑↑) — drivers, bear case, link
  FADE: restaking (5 → Cope) — driver list, reflexivity flagged

MAP
  Emerging: agentic-payments
  Rising: AI-x-crypto
  Peak: restaking
  Fading: memecoin-szn

Quiet day: one line — no phase transitions, map unchanged from {date}. Silence is correct.

Rules

Drop narratives that grade IGNORE.
Named drivers only. "Crypto Twitter is excited" is not a driver.
Cope sentiment is a first-class tag (bag-holder energy, bear-narratives-dressed-as-bull).
Reflexivity only flagged with concrete evidence (rebrands, on-chain flows, named endorsements).

Want to see if bankrbot/aeon-narrative-tracker would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.