Install
$ agentstack add skill-skyf0xx-better-thinking-argument-construction ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Argument Construction
Build a claim-evidence-warrant chain with counterargument slots designed in from the start, rather than bolted on defensively.
Why
Arguments built without anticipating objections either ignore them, which is weak, or address them as a defensive afterthought, which is weak differently. Building counterargument slots into the structure from the start produces an argument that survives contact with a skeptical reader.
Use when / Don't use when
- Use when: writing persuasive content meant to survive scrutiny — proposals, briefs, pitches.
- Don't use when: the audience isn't skeptical and persuasion isn't the goal — informational writing wants pyramid-structuring instead.
Inputs → Outputs
- Inputs: a claim to argue for.
- Outputs: a structured argument — claim, evidence, the warrant connecting them, and pre-addressed counterarguments.
Principles
- The warrant — why this evidence supports this claim — usually needs to be stated explicitly, not assumed shared.
- Address the strongest counterargument, not the weakest — steelman it before answering it.
- A claim with no acknowledged counterargument reads as either naive or evasive to a sophisticated audience.
Procedure
- State the claim precisely.
- Select evidence that actually supports this specific claim, not a nearby one.
- State the warrant: the reasoning connecting the evidence to the claim explicitly.
- Run steelmanning on the likely counterargument(s); select the strongest.
- Address it directly in the argument's structure, not as a buried footnote.
- Order: claim, evidence and warrant, counterargument and response, restated claim with earned confidence.
Common mistakes
- Omitting the warrant, assuming the evidence "obviously" supports the claim.
- Addressing only a weak counterargument, which looks evasive to anyone who knows the strong one.
- Tacking the counterargument on as an afterthought rather than integrating it.
Examples
- A proposal defending a controversial technical choice.
- A legal brief; an op-ed.
- A research paper's discussion section.
Related
- [[argument-mapping]] — the structural tool this construction produces.
- [[steelmanning]] — the necessary step for selecting the right counterargument.
- [[persuasive-case]] — the composite this skill feeds.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: skyf0xx
- Source: skyf0xx/better-thinking
- License: MIT
- Homepage: https://zenbin.org/p/better-thinking
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.