New skill for analyzing token holder chip structure.
Includes dump risk, dev wallet status, related funds,
quality signals, entry cost batches, buying power,
and AI recommendation. Supports zh/en bilingual output
via LANG env var. Uses pure Python subprocess + ThreadPoolExecutor,
no /tmp files.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
AI models may use incorrect currency addresses from training data (e.g.
So11111111111111111111111111111111111111111 vs the correct ...112), causing
silent failures or misleading "jupiter has no route" errors. Added a warning
above the table and wrapped all addresses in backticks for clarity.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- parseDuration: bare numbers now default to minutes (e.g. "5" → "5m") instead of hard error
- Print a warning to stderr so users know the implicit conversion is happening
- Update SKILL.md: document unit suffix recommendation and bare-number fallback behavior
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Bare numbers like 0.5 were silently accepted but caused inconsistent
server-side filtering. This change:
- Adds a parseDuration() validator that rejects values without a unit
- Accepts seconds (e.g. 30s) and minutes (e.g. 0.5m / 1m / 5m)
- Prints a clear error message when a bare number is passed
- Updates desc strings to document the required unit format
- Adds a new TrenchesFieldType 'duration' to distinguish these fields
