From aidd-refine
Toggles terse output mode with intensity levels (lite, full, ultra) that strips articles, filler, and pleasantries from prose while preserving code, errors, and security warnings. Also reports token usage and savings.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aidd-refine:03-condenseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Toggles a terse output mode with three intensity levels (lite, full, ultra). Strips articles, filler, and pleasantries from prose while preserving technical substance, code blocks, quoted errors, and security warnings.
Toggles a terse output mode with three intensity levels (lite, full, ultra). Strips articles, filler, and pleasantries from prose while preserving technical substance, code blocks, quoted errors, and security warnings.
| # | Action | Role | Input |
|---|---|---|---|
| 01 | condense | Toggle terse mode and apply intensity rules | current_state + requested_intensity |
| 02 | stats | Report real token usage and estimated savings for the current session | session log + intensity timeline |
Router dispatches by intent:
condense, /condense full, stop condense, normal mode, ...) → 01-condense/condense-stats, how much have we saved, token savings, ...) → 02-statsstop condense, normal mode, /condense off, or invoking the skill again to toggle.full) unless an explicit intensity is given.[thing] [action] [reason]. [next step].
< not <=. Fix:"@references/intensity-levels.md: detailed per-level rules and side-by-side examples.../hooks/condense-stats.js - UserPromptSubmit hook that intercepts stats triggers, reads the session transcript, and returns the formatted savings report without invoking the model.npx claudepluginhub ai-driven-dev/framework --plugin aidd-refineCompresses verbose responses by eliminating filler, hype, hedging, framing, and transitions to save 200-400 tokens per response while preserving clarity. Use for token-efficient, direct AI outputs.
Compresses verbose Claude responses into concise grammatical English by removing filler, hedging, and ceremony while preserving technical accuracy and decision-oriented register.