Wick tldr
Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.
npx -y skills add agoradynamics/wick --skill wick-tldrAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Summarize long content — document, paper, thread, or conversation — into a faithful TL;DR with key claims, action items, and flagged omissions. Use on long articles, meeting notes, papers, or prior-conversation compression.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.2 KB, as published. Nobody here has run it
Wick — TL;DR
Summarization with epistemic discipline. Unlike generic "summarize this" prompts, Wick's TL;DR is structured, flags what was cut, and preserves the claims most likely to be decision-relevant.
When to invoke
- A long article, paper, or document needs compression
- Meeting notes, email thread, or chat log
- Prior conversation you want to compress before continuing
- Before
/reflectwhen sessions have accumulated
What Wick does
- Read the target content
- Identify:
- Core claims — what the author or speaker is asserting
- Supporting evidence — what backs the claims
- Action items — decisions, commitments, next steps (if any)
- Flag omissions — what was in the source but intentionally cut from the summary
- Note open questions — what the content raises but doesn't resolve
Output format
## TL;DR
[2-3 sentences — the headline]
## Key claims
- [claim 1] — [evidence / source]
- [claim 2] — [evidence / source]
## Action items
- [if any, with owner and due-date if stated]
## Omitted (but noted)
- [anything cut that might still matter]
## Open questions
- [anything the source raised but didn't resolve]
Length discipline
- Default: ~150 words
- Short mode (ask for it): 2 sentences
- Long mode (ask for it): ~400 words with preserved nuance
Framework grounding
Gate 3 (Specificity) applied to reading — the summary should be as long as the claim deserves, not a fixed length. Epistemic humility: if the source is ambiguous, say so rather than picking a confident reading. Stoic discipline of assent: don't pattern-match what the source "probably" said — quote where it matters.
Anti-patterns
- Summarizing an opinion piece as if it were fact
- Losing the author's hedges ("might," "in some cases") and turning them into definitive claims
- Bullet-list-ifying prose that was making a cumulative argument — the bullets lose the argument