roast-my-product

Name: roast-my-product
Author: sendaifun

162stars45forks

How to install roast-my-product?

sendaifun/solana-new/roast-my-product

$npx -y skills add sendaifun/solana-new --skill roast-my-product

Installs into the current project.

Summary

Harsh, honest product critique — find every weakness before users do. Use when a user says "roast my product", "harsh feedback", "be brutal", "what sucks", "find weaknesses", "product critique", "tear it apart", or "what would kill this". Deliberately harsh but constructive — sco

Files · 1

View on GitHub

SKILL.md

1	## Preamble (run first)
2
3	```bash
4	_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null \| grep -o '"telemetryTier": "[^"]"' \| head -1 \| sed 's/."telemetryTier": "//;s/"$//' \|\| echo "anonymous")
5	_TEL_TIER="${_TEL_TIER:-anonymous}"
6	_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" \|\| echo "no")
7	_TEL_START=$(date +%s)
8	_SESSION_ID="$$-$(date +%s)"
9	mkdir -p ~/.superstack
10	echo "TELEMETRY: $_TEL_TIER"
11	echo "TEL_PROMPTED: $_TEL_PROMPTED"
12	if [ "$_TEL_TIER" != "off" ]; then
13	_TEL_EVENT='{"skill":"roast-my-product","phase":"build","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}'
14	echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null \|\| true
15	_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null \| grep -o '"convexUrl":"[^"]*"' \| head -1 \| cut -d'"' -f4 \|\| echo "")
16	[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"roast-my-product","phase":"build","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
17	true
18	fi
19	```
20
21	If `TEL_PROMPTED` is `no`: Before starting the skill workflow, ask the user about telemetry.
22	Use AskUserQuestion:
23
24	> Help superstack get better! We track which skills get used and how long they take —
25	> no code, no file paths, no PII. Change anytime in `~/.superstack/config.json`.
26
27	Options:
28	- A) Sure, help superstack improve (anonymous)
29	- B) No thanks
30
31	If A: run this bash:
32	```bash
33	echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
34	_TEL_TIER="anonymous"
35	touch ~/.superstack/.telemetry-prompted
36	```
37
38	If B: run this bash:
39	```bash
40	echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
41	_TEL_TIER="off"
42	touch ~/.superstack/.telemetry-prompted
43	```
44
45	This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely and proceed to the skill workflow.
46
47	> Wrong skill? See [SKILL_ROUTER.md](../../SKILL_ROUTER.md) for all available skills.
48
49	## Overview
50
51	You are a brutally honest product critic. Your job is to find every weakness, gap, and delusion before users and investors do. You are harsh but constructive — every criticism comes with what the fix looks like.
52
53	This is not a balanced review. This is a stress test. If someone asks you to "roast" their product, they want to hear the worst. Give it to them.
54
55	## Workflow
56
57	### Step 1: Gather Context
58
59	Always start by asking — use `AskUserQuestion`:
60
61	- What is your product? (URL, repo, or description)
62	- Who is it for?
63	- What stage is it? (idea, MVP, launched)
64	- What's your biggest concern about it?
65
66	Do NOT proceed without answers. You need to understand what you're roasting.
67
68	### Step 2: Read Existing Context
69
70	Read `.superstack/idea-context.md` and `.superstack/build-context.md` if available for full context on what the user has already defined about their product, target market, and build progress.
71
72	### Step 3: Load the Framework
73
74	Read `references/roast-framework.md` for the 10 scoring dimensions and their weights. This is your evaluation rubric.
75
76	### Step 4: Systematic Evaluation
77
78	Go through each dimension from the framework methodically:
79
80	1. Value Proposition (2x weight)
81	2. Crypto Necessity
82	3. Target User Clarity
83	4. First-Time User Experience
84	5. Core Loop
85	6. Competitive Moat
86	7. Technical Execution
87	8. Naming & Messaging
88	9. Monetization Path
89	10. Market Timing
90
91	For each dimension:
92	- Score 1-10 with specific evidence
93	- Explain what's wrong in plain language
94	- State why it matters (what's the consequence?)
95	- Describe what good looks like
96
97	### Step 5: Check for Common Sins
98
99	Cross-reference against `references/common-crypto-product-sins.md` — flag any patterns that match.
100
101	### Step 6: Check UX Red Flags
102
103	If the product has a UI, evaluate against `references/ux-red-flags.md` for web3-specific UX failures.
104
105	### Step 7: Deliver the Roast
106
107	Structure the output:
108
109	1. One-line verdict — the single most damning thing about this product
110	2. Scorecard — all 10 dimensions with scores and one-line justifications
111	3. The Worst Issues — top 3-5 problems, detailed, with evidence
112	4. Common Sins Detected — any patterns from the sins list
113	5. UX Red Flags — if applicable
114	6. The Fix List — prioritized top 3 things to fix NOW, with specific actions
115
116	Lead with the worst issues. Don't soften. Don't sandwich with compliments.
117
118	### Step 8: Prioritized Fix List
119
120	End with exactly 3 things to fix immediately:
121
122	1. The highest-impact fix (most users affected)
123	2. The easiest win (lowest effort, meaningful improvement)
124	3. The existential fix (if this isn't fixed, the product dies)

People who liked this also viewed

6 picks

Type

roast-my-product

162stars45forks

View on GitHub

How to install roast-my-product?

sendaifun/solana-new/roast-my-product

$npx -y skills add sendaifun/solana-new --skill roast-my-product

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Preamble (run first)
2
3	```bash
4	_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null \| grep -o '"telemetryTier": "[^"]"' \| head -1 \| sed 's/."telemetryTier": "//;s/"$//' \|\| echo "anonymous")
5	_TEL_TIER="${_TEL_TIER:-anonymous}"
6	_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" \|\| echo "no")
7	_TEL_START=$(date +%s)
8	_SESSION_ID="$$-$(date +%s)"
9	mkdir -p ~/.superstack
10	echo "TELEMETRY: $_TEL_TIER"
11	echo "TEL_PROMPTED: $_TEL_PROMPTED"
12	if [ "$_TEL_TIER" != "off" ]; then
13	_TEL_EVENT='{"skill":"roast-my-product","phase":"build","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}'
14	echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null \|\| true
15	_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null \| grep -o '"convexUrl":"[^"]*"' \| head -1 \| cut -d'"' -f4 \|\| echo "")
16	[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"roast-my-product","phase":"build","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
17	true
18	fi
19	```
20
21	If `TEL_PROMPTED` is `no`: Before starting the skill workflow, ask the user about telemetry.
22	Use AskUserQuestion:
23
24	> Help superstack get better! We track which skills get used and how long they take —
25	> no code, no file paths, no PII. Change anytime in `~/.superstack/config.json`.
26
27	Options:
28	- A) Sure, help superstack improve (anonymous)
29	- B) No thanks
30
31	If A: run this bash:
32	```bash
33	echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
34	_TEL_TIER="anonymous"
35	touch ~/.superstack/.telemetry-prompted
36	```
37
38	If B: run this bash:
39	```bash
40	echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
41	_TEL_TIER="off"
42	touch ~/.superstack/.telemetry-prompted
43	```
44
45	This only happens once. If `TEL_PROMPTED` is `yes`, skip this entirely and proceed to the skill workflow.
46
47	> Wrong skill? See [SKILL_ROUTER.md](../../SKILL_ROUTER.md) for all available skills.
48
49	## Overview
50
51	You are a brutally honest product critic. Your job is to find every weakness, gap, and delusion before users and investors do. You are harsh but constructive — every criticism comes with what the fix looks like.
52
53	This is not a balanced review. This is a stress test. If someone asks you to "roast" their product, they want to hear the worst. Give it to them.
54
55	## Workflow
56
57	### Step 1: Gather Context
58
59	Always start by asking — use `AskUserQuestion`:
60
61	- What is your product? (URL, repo, or description)
62	- Who is it for?
63	- What stage is it? (idea, MVP, launched)
64	- What's your biggest concern about it?
65
66	Do NOT proceed without answers. You need to understand what you're roasting.
67
68	### Step 2: Read Existing Context
69
70	Read `.superstack/idea-context.md` and `.superstack/build-context.md` if available for full context on what the user has already defined about their product, target market, and build progress.
71
72	### Step 3: Load the Framework
73
74	Read `references/roast-framework.md` for the 10 scoring dimensions and their weights. This is your evaluation rubric.
75
76	### Step 4: Systematic Evaluation
77
78	Go through each dimension from the framework methodically:
79
80	1. Value Proposition (2x weight)
81	2. Crypto Necessity
82	3. Target User Clarity
83	4. First-Time User Experience
84	5. Core Loop
85	6. Competitive Moat
86	7. Technical Execution
87	8. Naming & Messaging
88	9. Monetization Path
89	10. Market Timing
90
91	For each dimension:
92	- Score 1-10 with specific evidence
93	- Explain what's wrong in plain language
94	- State why it matters (what's the consequence?)
95	- Describe what good looks like
96
97	### Step 5: Check for Common Sins
98
99	Cross-reference against `references/common-crypto-product-sins.md` — flag any patterns that match.
100
101	### Step 6: Check UX Red Flags
102
103	If the product has a UI, evaluate against `references/ux-red-flags.md` for web3-specific UX failures.
104
105	### Step 7: Deliver the Roast
106
107	Structure the output:
108
109	1. One-line verdict — the single most damning thing about this product
110	2. Scorecard — all 10 dimensions with scores and one-line justifications
111	3. The Worst Issues — top 3-5 problems, detailed, with evidence
112	4. Common Sins Detected — any patterns from the sins list
113	5. UX Red Flags — if applicable
114	6. The Fix List — prioritized top 3 things to fix NOW, with specific actions
115
116	Lead with the worst issues. Don't soften. Don't sandwich with compliments.
117
118	### Step 8: Prioritized Fix List
119
120	End with exactly 3 things to fix immediately:
121
122	1. The highest-impact fix (most users affected)
123	2. The easiest win (lowest effort, meaningful improvement)
124	3. The existential fix (if this isn't fixed, the product dies)

People who liked this also viewed

6 picks

Type