cross-critique

Name: cross-critique
Author: warpdotdev

8.3kinstalls1forks

How to install cross-critique?

warpdotdev/common-skills/cross-critique

$npx -y skills add warpdotdev/common-skills --skill cross-critique

Installs into the current project.

Summary

Run a second round on a contested question by circulating each subagent's independent proposal to the other authors and asking for structured pros and cons, then synthesize. Use this skill whenever you have multiple independent proposals or opinions on a contested decision — arch

Files · 1

View on GitHub

SKILL.md

1	# Cross-Critique
2
3	Use this skill to run a second round after several subagents have independently produced proposals or opinions on the same contested question. Instead of synthesizing their reports yourself, you circulate each proposal to the other authors and ask them to critique it — pros and cons — and then you synthesize the richer set of analyses that results.
4
5	## Why this matters
6
7	When you generate independent proposals (different models, different angles), each author ends up with deep context on the question — often deeper than yours, since they did the investigation. If you jump straight to synthesizing their reports alone, you're the bottleneck: you can only see the tradeoffs you happen to notice.
8
9	Asking the authors to critique each other is what a good leader does when seeking advice: get a few people with differing perspectives in a room, let them poke holes in each other's reasoning, and you walk away with a far more complete picture than any one of them — or you — would produce alone. The authors will surface failure modes, hidden assumptions, and tradeoffs that neither you nor the original proposer flagged.
10
11	## When to use it
12
13	Use cross-critique when a decision is contested — i.e. independent agents produced genuinely divergent proposals, or the question is subjective enough that reasonable approaches disagree. Good fits:
14
15	- Architecture and design tradeoffs.
16	- Code review where reviewers reached different conclusions.
17	- Competing root-cause theories for a bug.
18	- Code-structure or API-shape decisions with no single right answer.
19
20	Don't bother when the proposals already strongly agree, or when the question has an objective answer you can verify directly — critique adds latency and tokens, and its value comes specifically from resolving genuine disagreement. Within that scope, use it freely; you don't need a high-stakes justification, just real divergence worth resolving.
21
22	## Prerequisite: you need independent proposals first
23
24	This skill is the second round. It assumes you already have N independent proposals in hand. If you don't yet:
25
26	- For a judgment-heavy decision, generate them with the council skill (model-diverse subagents on the same question).
27	- For an investigation-heavy question, generate them by spawning parallel subagents (see the research skill).
28	- Or use any ad-hoc set of independent subagent proposals you've already collected.
29
30	Critically, the first round must be independent — do not let the authors see each other's work during round one, or you lose the diversity that makes round two valuable.
31
32	## How to do it
33
34	### 1. Assemble the proposals
35
36	Collect each author's proposal. Keep them concise — the core recommendation and its reasoning, not the full transcript. Consider labeling them neutrally (Proposal A, B, C) and, where practical, anonymizing authorship to reduce bandwagon bias toward whichever model sounds most confident.
37
38	### 2. Circulate and ask for structured critique
39
40	Reuse the same subagents from round one rather than spawning fresh ones — they retain their context and can critique from a position of understanding. Send each author the other proposals (not their own) and ask each for:
41
42	- For each alternative: its pros (what it gets right, where it's stronger than my approach) and its cons (risks, edge cases, hidden costs, wrong assumptions).
43	- Whether, having seen the alternatives, they would revise their own recommendation — and why or why not.
44	- A final ranking or recommendation with confidence.
45
46	Insist on both pros and cons for each alternative. An honest critique that credits a rival's strengths is far more useful than a reflexive defense of one's own proposal.
47
48	### 3. Synthesize
49
50	Now bring it together yourself. Compare critiques by evidence quality, not vote count. In your final answer:
51
52	- Lead with the recommendation.
53	- Note where the authors converged after seeing each other's work — convergence in round two is a strong signal.
54	- Surface the most incisive cons raised against each option.
55	- Explain why the recommended option survives critique best against the decision criteria.
56	- Call out remaining disagreement, confidence, and material unknowns.
57
58	## Final answer template
59
60	Use this shape unless the task calls for something different:
61
62	```markdown
63	## Recommendation
64	[One or two sentences with the decision.]
65
66	## How the critiques shifted

People who liked this also viewed

6 picks

Type

cross-critique

8.3kinstalls1forks

View on GitHub

How to install cross-critique?

warpdotdev/common-skills/cross-critique

$npx -y skills add warpdotdev/common-skills --skill cross-critique

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Cross-Critique
2
3	Use this skill to run a second round after several subagents have independently produced proposals or opinions on the same contested question. Instead of synthesizing their reports yourself, you circulate each proposal to the other authors and ask them to critique it — pros and cons — and then you synthesize the richer set of analyses that results.
4
5	## Why this matters
6
7	When you generate independent proposals (different models, different angles), each author ends up with deep context on the question — often deeper than yours, since they did the investigation. If you jump straight to synthesizing their reports alone, you're the bottleneck: you can only see the tradeoffs you happen to notice.
8
9	Asking the authors to critique each other is what a good leader does when seeking advice: get a few people with differing perspectives in a room, let them poke holes in each other's reasoning, and you walk away with a far more complete picture than any one of them — or you — would produce alone. The authors will surface failure modes, hidden assumptions, and tradeoffs that neither you nor the original proposer flagged.
10
11	## When to use it
12
13	Use cross-critique when a decision is contested — i.e. independent agents produced genuinely divergent proposals, or the question is subjective enough that reasonable approaches disagree. Good fits:
14
15	- Architecture and design tradeoffs.
16	- Code review where reviewers reached different conclusions.
17	- Competing root-cause theories for a bug.
18	- Code-structure or API-shape decisions with no single right answer.
19
20	Don't bother when the proposals already strongly agree, or when the question has an objective answer you can verify directly — critique adds latency and tokens, and its value comes specifically from resolving genuine disagreement. Within that scope, use it freely; you don't need a high-stakes justification, just real divergence worth resolving.
21
22	## Prerequisite: you need independent proposals first
23
24	This skill is the second round. It assumes you already have N independent proposals in hand. If you don't yet:
25
26	- For a judgment-heavy decision, generate them with the council skill (model-diverse subagents on the same question).
27	- For an investigation-heavy question, generate them by spawning parallel subagents (see the research skill).
28	- Or use any ad-hoc set of independent subagent proposals you've already collected.
29
30	Critically, the first round must be independent — do not let the authors see each other's work during round one, or you lose the diversity that makes round two valuable.
31
32	## How to do it
33
34	### 1. Assemble the proposals
35
36	Collect each author's proposal. Keep them concise — the core recommendation and its reasoning, not the full transcript. Consider labeling them neutrally (Proposal A, B, C) and, where practical, anonymizing authorship to reduce bandwagon bias toward whichever model sounds most confident.
37
38	### 2. Circulate and ask for structured critique
39
40	Reuse the same subagents from round one rather than spawning fresh ones — they retain their context and can critique from a position of understanding. Send each author the other proposals (not their own) and ask each for:
41
42	- For each alternative: its pros (what it gets right, where it's stronger than my approach) and its cons (risks, edge cases, hidden costs, wrong assumptions).
43	- Whether, having seen the alternatives, they would revise their own recommendation — and why or why not.
44	- A final ranking or recommendation with confidence.
45
46	Insist on both pros and cons for each alternative. An honest critique that credits a rival's strengths is far more useful than a reflexive defense of one's own proposal.
47
48	### 3. Synthesize
49
50	Now bring it together yourself. Compare critiques by evidence quality, not vote count. In your final answer:
51
52	- Lead with the recommendation.
53	- Note where the authors converged after seeing each other's work — convergence in round two is a strong signal.
54	- Surface the most incisive cons raised against each option.
55	- Explain why the recommended option survives critique best against the decision criteria.
56	- Call out remaining disagreement, confidence, and material unknowns.
57
58	## Final answer template
59
60	Use this shape unless the task calls for something different:
61
62	```markdown
63	## Recommendation
64	[One or two sentences with the decision.]
65
66	## How the critiques shifted

People who liked this also viewed

6 picks

Type