competitive-research

Name: competitive-research
Author: aleksander-dytko

31stars4forks

How to install competitive-research?

aleksander-dytko/ai-pm-workspace/competitive-research

$npx -y skills add aleksander-dytko/ai-pm-workspace --skill competitive-research

Installs into the current project.

Summary

Produce a sourced competitive matrix for a focused research question

Files · 1

View on GitHub

SKILL.md

1	# Competitive Research
2
3	You help produce a sourced competitive matrix for a focused research question. The output is a markdown table plus sourced observations, landed in `research/`.
4
5	## Input
6
7	The user provides via `$ARGUMENTS`:
8	- A short research topic (e.g., "how competitors handle first-time user onboarding"), OR
9	- A path to a research-prompt file (e.g., `samples/sample-competitor-prompt.md`)
10
11	## Workflow
12
13	### 1. Read the prompt
14
15	If `$ARGUMENTS` is a file path, read it. Otherwise use the prompt directly.
16
17	Extract (or ask in one round):
18	- Research topic - the question.
19	- Scope - which competitors (direct / adjacent / aspirational), any exclusions.
20	- Questions - 3-7 specific things you want answered.
21	- Deliverable format - matrix (rows = products, columns = questions) by default.
22	- Timeline and non-goals.
23
24	If any of these are missing, ask the user in ONE `AskUserQuestion` round. Skip any that are clear.
25
26	### 2. Pick the competitor set
27
28	If the user provided competitors, use them. Otherwise suggest a set and confirm:
29
30	- Direct: 2-3 products in the same pricing tier and feature surface as your own (list your company's known competitors from `CLAUDE.md` or ask).
31	- Adjacent / aspirational: 1-2 products in related spaces known for excellent practice in the research topic.
32	- Exclude: tools clearly out of scope.
33
34	Confirm the list with the user before proceeding.
35
36	### 3. Gather observations (sourced)
37
38	For each product, for each research question, gather observations. Use available tools:
39
40	- WebFetch / WebSearch for public product docs, blog posts, marketing pages, changelog posts, and product-hunt-style coverage.
41	- Any documentation MCP your environment has configured (check the `MCP Servers Available` section of `CLAUDE.md`).
42	- Internal research notes in `Loose Notes/Work/` that mention the competitor by name.
43
44	Rules for observations:
45	- Sourced: every observation has a URL or an internal note reference. No "I think they probably...".
46	- Observed vs. inferred: mark each cell as `observed:` (you can point to a specific page/screenshot) or `inferred:` (your reasoning based on other evidence).
47	- Date-stamped: competitive landscapes move fast. Note the date of the source when it's older than 6 months.
48
49	### 4. Build the matrix
50
51	Produce a markdown table:
52
53	\| Product \| Q1 \| Q2 \| Q3 \| ... \|
54	\|---------\|----\|----\|----\|-----\|
55	\| Competitor A \| observed: [fact] - [link] \| inferred: [reasoning] \| ... \| ... \|
56	\| Competitor B \| ... \| ... \| ... \| ... \|
57
58	Cells can be long. Keep them scannable but informative.
59
60	### 5. Summarize the landscape
61
62	Below the matrix, write a 3-5 paragraph synthesis:
63
64	- Common patterns: what do all / most of the competitors do similarly?
65	- Divergences: where do they differ meaningfully, and why?
66	- Outliers: any surprising approaches worth investigating further.
67	- Implications for us: how this should inform our decision (without prescribing a specific solution yet).
68
69	### 6. Note methodology and limits
70
71	A short section at the end:
72
73	- Sources consulted: docs, blog posts, pricing pages, external analyses.
74	- Gaps: what you couldn't find out (and would need a customer conversation or a demo account to verify).
75	- Confidence: where you're confident in observations vs. where you're inferring.
76
77	### 7. File location and naming
78
79	- Folder: `research/`. Create if it doesn't exist.
80	- Filename: `YYYY-MM-DD - Competitive - [Topic slug].md`. Example: `2026-04-20 - Competitive - Onboarding UX.md`.
81	- Frontmatter: `tags: Research, Competitive`, `created: YYYY-MM-DD`.
82
83	### 8. Link the research
84
85	- Daily journal: under `## Notes`.
86	- Related epic (if any): add a link in that epic's `## Breakdown > Explore` section.
87
88	### 9. Output summary
89
90	```
91	✅ Research: [[YYYY-MM-DD - Competitive - Topic]]
92	✅ Linked in today's journal
93
94	Products compared: [N]
95	Questions answered: [N]
96	Sources cited: [N]
97	Gaps flagged: [N]
98
99	💡 Key pattern: [One-line top insight]
100
101	Next step: run `/opportunity-solution-tree` to convert insights into opportunities.
102	```
103
104	## Notes
105
106	- Sourced over speculative. If you can't find evidence, say so.
107	- A matrix is a structure, not a verdict. Don't prescribe "we should do X because Competitor Y does it."
108	- Competitive research ages fast. Add the source date for anything older than 6 months. A year-old blog post about a product's onboarding is probably wrong now.
109	- The Extended Opportunity Solution Tree framework pairs well with this - use `/opportunity-solution-tree` next to turn patterns into opportunity hypotheses.

People who liked this also viewed

6 picks

Type

seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026168k41k
copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026159k41k
marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026116k41k
content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026111k41k
programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026107k41k
marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026104k41k

competitive-research

31stars4forks

View on GitHub

How to install competitive-research?

aleksander-dytko/ai-pm-workspace/competitive-research

$npx -y skills add aleksander-dytko/ai-pm-workspace --skill competitive-research

Installs into the current project.

Summary

Produce a sourced competitive matrix for a focused research question

Files · 1

View on GitHub

SKILL.md

1	# Competitive Research
2
3	You help produce a sourced competitive matrix for a focused research question. The output is a markdown table plus sourced observations, landed in `research/`.
4
5	## Input
6
7	The user provides via `$ARGUMENTS`:
8	- A short research topic (e.g., "how competitors handle first-time user onboarding"), OR
9	- A path to a research-prompt file (e.g., `samples/sample-competitor-prompt.md`)
10
11	## Workflow
12
13	### 1. Read the prompt
14
15	If `$ARGUMENTS` is a file path, read it. Otherwise use the prompt directly.
16
17	Extract (or ask in one round):
18	- Research topic - the question.
19	- Scope - which competitors (direct / adjacent / aspirational), any exclusions.
20	- Questions - 3-7 specific things you want answered.
21	- Deliverable format - matrix (rows = products, columns = questions) by default.
22	- Timeline and non-goals.
23
24	If any of these are missing, ask the user in ONE `AskUserQuestion` round. Skip any that are clear.
25
26	### 2. Pick the competitor set
27
28	If the user provided competitors, use them. Otherwise suggest a set and confirm:
29
30	- Direct: 2-3 products in the same pricing tier and feature surface as your own (list your company's known competitors from `CLAUDE.md` or ask).
31	- Adjacent / aspirational: 1-2 products in related spaces known for excellent practice in the research topic.
32	- Exclude: tools clearly out of scope.
33
34	Confirm the list with the user before proceeding.
35
36	### 3. Gather observations (sourced)
37
38	For each product, for each research question, gather observations. Use available tools:
39
40	- WebFetch / WebSearch for public product docs, blog posts, marketing pages, changelog posts, and product-hunt-style coverage.
41	- Any documentation MCP your environment has configured (check the `MCP Servers Available` section of `CLAUDE.md`).
42	- Internal research notes in `Loose Notes/Work/` that mention the competitor by name.
43
44	Rules for observations:
45	- Sourced: every observation has a URL or an internal note reference. No "I think they probably...".
46	- Observed vs. inferred: mark each cell as `observed:` (you can point to a specific page/screenshot) or `inferred:` (your reasoning based on other evidence).
47	- Date-stamped: competitive landscapes move fast. Note the date of the source when it's older than 6 months.
48
49	### 4. Build the matrix
50
51	Produce a markdown table:
52
53	\| Product \| Q1 \| Q2 \| Q3 \| ... \|
54	\|---------\|----\|----\|----\|-----\|
55	\| Competitor A \| observed: [fact] - [link] \| inferred: [reasoning] \| ... \| ... \|
56	\| Competitor B \| ... \| ... \| ... \| ... \|
57
58	Cells can be long. Keep them scannable but informative.
59
60	### 5. Summarize the landscape
61
62	Below the matrix, write a 3-5 paragraph synthesis:
63
64	- Common patterns: what do all / most of the competitors do similarly?
65	- Divergences: where do they differ meaningfully, and why?
66	- Outliers: any surprising approaches worth investigating further.
67	- Implications for us: how this should inform our decision (without prescribing a specific solution yet).
68
69	### 6. Note methodology and limits
70
71	A short section at the end:
72
73	- Sources consulted: docs, blog posts, pricing pages, external analyses.
74	- Gaps: what you couldn't find out (and would need a customer conversation or a demo account to verify).
75	- Confidence: where you're confident in observations vs. where you're inferring.
76
77	### 7. File location and naming
78
79	- Folder: `research/`. Create if it doesn't exist.
80	- Filename: `YYYY-MM-DD - Competitive - [Topic slug].md`. Example: `2026-04-20 - Competitive - Onboarding UX.md`.
81	- Frontmatter: `tags: Research, Competitive`, `created: YYYY-MM-DD`.
82
83	### 8. Link the research
84
85	- Daily journal: under `## Notes`.
86	- Related epic (if any): add a link in that epic's `## Breakdown > Explore` section.
87
88	### 9. Output summary
89
90	```
91	✅ Research: [[YYYY-MM-DD - Competitive - Topic]]
92	✅ Linked in today's journal
93
94	Products compared: [N]
95	Questions answered: [N]
96	Sources cited: [N]
97	Gaps flagged: [N]
98
99	💡 Key pattern: [One-line top insight]
100
101	Next step: run `/opportunity-solution-tree` to convert insights into opportunities.
102	```
103
104	## Notes
105
106	- Sourced over speculative. If you can't find evidence, say so.
107	- A matrix is a structure, not a verdict. Don't prescribe "we should do X because Competitor Y does it."
108	- Competitive research ages fast. Add the source date for anything older than 6 months. A year-old blog post about a product's onboarding is probably wrong now.
109	- The Extended Opportunity Solution Tree framework pairs well with this - use `/opportunity-solution-tree` next to turn patterns into opportunity hypotheses.

People who liked this also viewed

6 picks

Type