landscape-scan

Name: landscape-scan
Author: MoizIbnYousaf

27stars5forks

How to install landscape-scan?

moizibnyousaf/marketing-cli/landscape-scan

$npx -y skills add MoizIbnYousaf/marketing-cli --skill landscape-scan

Installs into the current project.

Summary

Scan the current market landscape and produce a ground-truth ecosystem snapshot. Chains /last30days for live research, validates with user, and writes brand/landscape.md with a Claims Blacklist that hard-gates all content generation. Use when: "landscape", "ecosystem", "market sn

Files · 1

View on GitHub

SKILL.md

1	# /landscape-scan -- Ground-Truth Ecosystem Snapshot
2
3	Every claim your marketing makes sits on top of an assumption about the market.
4	"We're the first to..." "Nobody else does..." "The market is moving toward..."
5	When these assumptions are wrong, your positioning collapses on contact with
6	reality. Customers who Google your claims and find them false don't come back.
7
8	This skill builds a verified ecosystem snapshot that becomes the single source
9	of truth for all downstream content. The Claims Blacklist it produces hard-gates
10	every content skill -- if a claim is blacklisted, no skill writes it. Period.
11
12	No SaaS tools needed. Live web research + user validation.
13
14	---
15
16	## On Activation
17
18	1. Check if `brand/` directory exists in the project root.
19	2. If it does, read available files in priority order:
20	- `competitors.md` -- existing competitive intel (primary input)
21	- `positioning.md` -- current positioning angles and claims
22	- `audience.md` -- target market and buyer personas
23	- `voice-profile.md` -- brand personality (for tone of output)
24	- `learnings.md` -- past marketing learnings and corrections
25	3. Apply loaded brand context to focus the landscape scan -- existing competitor
26	data narrows the research query, positioning data identifies claims to verify.
27	4. If `brand/` does not exist or is empty, proceed without it -- this skill
28	works standalone by asking the user foundational questions.
29
30	---
31
32	## Iteration Detection
33
34	Before starting, check whether `./brand/landscape.md` already exists.
35
36	### If landscape.md EXISTS --> Refresh Mode
37
38	Do not start from scratch. Instead:
39
40	1. Read the existing landscape file.
41	2. Present a summary of the current state:
42	```
43	EXISTING LANDSCAPE SNAPSHOT
44	Last updated {date} by /landscape-scan
45
46	Ecosystem segments: {N}
47	Claims blacklisted: {N}
48	Market shifts tracked: {N}
49
50	Freshness: {days} days old (threshold: 14 days)
51
52	------------------------------------------
53
54	What would you like to do?
55
56	1. Full refresh -- re-run /last30days, revalidate everything
57	2. Verify claims -- check if blacklisted claims are still invalid
58	3. Add new segment -- expand to cover a new market area
59	4. Rebuild from scratch -- discard and start over
60	```
61
62	3. Process the user's choice:
63	- Option 1 --> Re-research with fresh /last30days query, merge with existing data
64	- Option 2 --> Focused validation of Claims Blacklist items only
65	- Option 3 --> Targeted research on a new ecosystem segment, merge into existing file
66	- Option 4 --> Full process from scratch
67
68	4. Before overwriting, show a diff of what changed and ask for confirmation.
69
70	### If landscape.md DOES NOT EXIST --> Full Scan Mode
71
72	Proceed to the full process below.
73
74	---
75
76	## The Core Job
77
78	Map current ecosystem reality so every downstream skill operates on verified
79	ground truth. The output has two critical components:
80
81	1. Ecosystem Snapshot -- what is actually happening in the market right now
82	(players, trends, shifts, emerging categories, consolidation, funding rounds)
83	2. Claims Blacklist -- specific claims your marketing MUST NOT make because
84	they are verifiably false, outdated, or easily disproven by a customer who
85	spends 30 seconds searching
86
87	The Claims Blacklist is not advisory. It is a hard gate. Every content-generating
88	skill reads `brand/landscape.md` and refuses to write blacklisted claims.
89
90	---
91
92	## Orchestration Flow
93
94	### Phase 1: Preflight
95
96	1. Read brand/ context files (see On Activation above).
97	2. Detect mode: create vs refresh (see Iteration Detection above).
98	3. Determine context level:
99	- L0 -- No brand/ files. Need to ask everything.
100	- L1 -- Have product name/description only.
101	- L2 -- Have competitors.md and/or positioning.md.
102	- L3 -- Have L2 + will run /last30days for live data.
103	- L4 -- Have L3 + existing landscape.md (refresh mode).
104	4. If `--dry-run` is set, report what WOULD happen and exit. Do not make any
105	network calls or write any files.
106
107	### Phase 2: Build Research Query
108
109	Extract search parameters from available context:
110
111	- Product/Category: from positioning.md `primary_gap` or user input
112	- Competitors: from competitors.md competitor names, or user input
113	- Target market: from audience.md `primary_persona`, or user input
114	- Time window: last 30 days (default), or user-specified
115
116	Build the research query (see `references/query-templates.md` for industry-specific
117	templates). The query should cover:
118
119	1. Market movements -- funding, acquisitions, pivots, shu

People who liked this also viewed

6 picks

Type

landscape-scan

27stars5forks

View on GitHub

How to install landscape-scan?

moizibnyousaf/marketing-cli/landscape-scan

$npx -y skills add MoizIbnYousaf/marketing-cli --skill landscape-scan

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /landscape-scan -- Ground-Truth Ecosystem Snapshot
2
3	Every claim your marketing makes sits on top of an assumption about the market.
4	"We're the first to..." "Nobody else does..." "The market is moving toward..."
5	When these assumptions are wrong, your positioning collapses on contact with
6	reality. Customers who Google your claims and find them false don't come back.
7
8	This skill builds a verified ecosystem snapshot that becomes the single source
9	of truth for all downstream content. The Claims Blacklist it produces hard-gates
10	every content skill -- if a claim is blacklisted, no skill writes it. Period.
11
12	No SaaS tools needed. Live web research + user validation.
13
14	---
15
16	## On Activation
17
18	1. Check if `brand/` directory exists in the project root.
19	2. If it does, read available files in priority order:
20	- `competitors.md` -- existing competitive intel (primary input)
21	- `positioning.md` -- current positioning angles and claims
22	- `audience.md` -- target market and buyer personas
23	- `voice-profile.md` -- brand personality (for tone of output)
24	- `learnings.md` -- past marketing learnings and corrections
25	3. Apply loaded brand context to focus the landscape scan -- existing competitor
26	data narrows the research query, positioning data identifies claims to verify.
27	4. If `brand/` does not exist or is empty, proceed without it -- this skill
28	works standalone by asking the user foundational questions.
29
30	---
31
32	## Iteration Detection
33
34	Before starting, check whether `./brand/landscape.md` already exists.
35
36	### If landscape.md EXISTS --> Refresh Mode
37
38	Do not start from scratch. Instead:
39
40	1. Read the existing landscape file.
41	2. Present a summary of the current state:
42	```
43	EXISTING LANDSCAPE SNAPSHOT
44	Last updated {date} by /landscape-scan
45
46	Ecosystem segments: {N}
47	Claims blacklisted: {N}
48	Market shifts tracked: {N}
49
50	Freshness: {days} days old (threshold: 14 days)
51
52	------------------------------------------
53
54	What would you like to do?
55
56	1. Full refresh -- re-run /last30days, revalidate everything
57	2. Verify claims -- check if blacklisted claims are still invalid
58	3. Add new segment -- expand to cover a new market area
59	4. Rebuild from scratch -- discard and start over
60	```
61
62	3. Process the user's choice:
63	- Option 1 --> Re-research with fresh /last30days query, merge with existing data
64	- Option 2 --> Focused validation of Claims Blacklist items only
65	- Option 3 --> Targeted research on a new ecosystem segment, merge into existing file
66	- Option 4 --> Full process from scratch
67
68	4. Before overwriting, show a diff of what changed and ask for confirmation.
69
70	### If landscape.md DOES NOT EXIST --> Full Scan Mode
71
72	Proceed to the full process below.
73
74	---
75
76	## The Core Job
77
78	Map current ecosystem reality so every downstream skill operates on verified
79	ground truth. The output has two critical components:
80
81	1. Ecosystem Snapshot -- what is actually happening in the market right now
82	(players, trends, shifts, emerging categories, consolidation, funding rounds)
83	2. Claims Blacklist -- specific claims your marketing MUST NOT make because
84	they are verifiably false, outdated, or easily disproven by a customer who
85	spends 30 seconds searching
86
87	The Claims Blacklist is not advisory. It is a hard gate. Every content-generating
88	skill reads `brand/landscape.md` and refuses to write blacklisted claims.
89
90	---
91
92	## Orchestration Flow
93
94	### Phase 1: Preflight
95
96	1. Read brand/ context files (see On Activation above).
97	2. Detect mode: create vs refresh (see Iteration Detection above).
98	3. Determine context level:
99	- L0 -- No brand/ files. Need to ask everything.
100	- L1 -- Have product name/description only.
101	- L2 -- Have competitors.md and/or positioning.md.
102	- L3 -- Have L2 + will run /last30days for live data.
103	- L4 -- Have L3 + existing landscape.md (refresh mode).
104	4. If `--dry-run` is set, report what WOULD happen and exit. Do not make any
105	network calls or write any files.
106
107	### Phase 2: Build Research Query
108
109	Extract search parameters from available context:
110
111	- Product/Category: from positioning.md `primary_gap` or user input
112	- Competitors: from competitors.md competitor names, or user input
113	- Target market: from audience.md `primary_persona`, or user input
114	- Time window: last 30 days (default), or user-specified
115
116	Build the research query (see `references/query-templates.md` for industry-specific
117	templates). The query should cover:
118
119	1. Market movements -- funding, acquisitions, pivots, shu

People who liked this also viewed

6 picks

Type