content-engine

Name: content-engine
Author: affaan-m

232kstars35kforks

How to install content-engine?

affaan-m/ecc/content-engine

$npx -y skills add affaan-m/ECC --skill content-engine

Installs into the current project.

Summary

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

Files · 1

View on GitHub

SKILL.md

1	# Content Engine
2
3	Build platform-native content without flattening the author's real voice into platform slop.
4
5	## When to Activate
6
7	- writing X posts or threads
8	- drafting LinkedIn posts or launch updates
9	- scripting short-form video or YouTube explainers
10	- repurposing articles, podcasts, demos, docs, or internal notes into public content
11	- building a launch sequence or ongoing content system around a product, insight, or narrative
12
13	## Non-Negotiables
14
15	1. Start from source material, not generic post formulas.
16	2. Adapt the format for the platform, not the persona.
17	3. One post should carry one actual claim.
18	4. Specificity beats adjectives.
19	5. No engagement bait unless the user explicitly asks for it.
20
21	## Source-First Workflow
22
23	Before drafting, identify the source set:
24	- published articles
25	- notes or internal memos
26	- product demos
27	- docs or changelogs
28	- transcripts
29	- screenshots
30	- prior posts from the same author
31
32	If the user wants a specific voice, build a voice profile from real examples before writing.
33	Use `brand-voice` as the canonical workflow when voice consistency matters across more than one output.
34
35	## Voice Handling
36
37	`brand-voice` is the canonical voice layer.
38
39	Run it first when:
40
41	- there are multiple downstream outputs
42	- the user explicitly cares about writing style
43	- the content is launch, outreach, or reputation-sensitive
44
45	Reuse the resulting `VOICE PROFILE` here instead of rebuilding a second voice model.
46	If the user wants Affaan / ECC voice specifically, still treat `brand-voice` as the source of truth and feed it the best live or source-derived material available.
47
48	## Hard Bans
49
50	Delete and rewrite any of these:
51	- "In today's rapidly evolving landscape"
52	- "game-changer", "revolutionary", "cutting-edge"
53	- "here's why this matters" unless it is followed immediately by something concrete
54	- ending with a LinkedIn-style question just to farm replies
55	- forced casualness on LinkedIn
56	- fake engagement padding that was not present in the source material
57
58	## Platform Adaptation Rules
59
60	### X
61
62	- open with the strongest claim, artifact, or tension
63	- keep the compression if the source voice is compressed
64	- if writing a thread, each post must advance the argument
65	- do not pad with context the audience does not need
66
67	### LinkedIn
68
69	- expand only enough for people outside the immediate niche to follow
70	- do not turn it into a fake lesson post unless the source material actually is reflective
71	- no corporate inspiration cadence
72	- no praise-stacking, no "journey" filler
73
74	### Short Video
75
76	- script around the visual sequence and proof points
77	- first seconds should show the result, problem, or punch
78	- do not write narration that sounds better on paper than on screen
79
80	### YouTube
81
82	- show the result or tension early
83	- organize by argument or progression, not filler sections
84	- use chaptering only when it helps clarity
85
86	### Newsletter
87
88	- open with the point, conflict, or artifact
89	- do not spend the first paragraph warming up
90	- every section needs to add something new
91
92	## Repurposing Flow
93
94	1. Pick the anchor asset.
95	2. Extract 3 to 7 atomic claims or scenes.
96	3. Rank them by sharpness, novelty, and proof.
97	4. Assign one strong idea per output.
98	5. Adapt structure for each platform.
99	6. Strip platform-shaped filler.
100	7. Run the quality gate.
101
102	## Deliverables
103
104	When asked for a campaign, return:
105	- a short voice profile if voice matching matters
106	- the core angle
107	- platform-native drafts
108	- posting order only if it helps execution
109	- gaps that must be filled before publishing
110
111	## Quality Gate
112
113	Before delivering:
114	- every draft sounds like the intended author, not the platform stereotype
115	- every draft contains a real claim, proof point, or concrete observation
116	- no generic hype language remains
117	- no fake engagement bait remains
118	- no duplicated copy across platforms unless requested
119	- any CTA is earned and user-approved
120
121	## Related Skills
122
123	- `brand-voice` for source-derived voice profiles
124	- `crosspost` for platform-specific distribution
125	- `x-api` for sourcing recent posts and publishing approved X output

People who liked this also viewed

6 picks

Type

content-engine

232kstars35kforks

View on GitHub

How to install content-engine?

affaan-m/ecc/content-engine

$npx -y skills add affaan-m/ECC --skill content-engine

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Content Engine
2
3	Build platform-native content without flattening the author's real voice into platform slop.
4
5	## When to Activate
6
7	- writing X posts or threads
8	- drafting LinkedIn posts or launch updates
9	- scripting short-form video or YouTube explainers
10	- repurposing articles, podcasts, demos, docs, or internal notes into public content
11	- building a launch sequence or ongoing content system around a product, insight, or narrative
12
13	## Non-Negotiables
14
15	1. Start from source material, not generic post formulas.
16	2. Adapt the format for the platform, not the persona.
17	3. One post should carry one actual claim.
18	4. Specificity beats adjectives.
19	5. No engagement bait unless the user explicitly asks for it.
20
21	## Source-First Workflow
22
23	Before drafting, identify the source set:
24	- published articles
25	- notes or internal memos
26	- product demos
27	- docs or changelogs
28	- transcripts
29	- screenshots
30	- prior posts from the same author
31
32	If the user wants a specific voice, build a voice profile from real examples before writing.
33	Use `brand-voice` as the canonical workflow when voice consistency matters across more than one output.
34
35	## Voice Handling
36
37	`brand-voice` is the canonical voice layer.
38
39	Run it first when:
40
41	- there are multiple downstream outputs
42	- the user explicitly cares about writing style
43	- the content is launch, outreach, or reputation-sensitive
44
45	Reuse the resulting `VOICE PROFILE` here instead of rebuilding a second voice model.
46	If the user wants Affaan / ECC voice specifically, still treat `brand-voice` as the source of truth and feed it the best live or source-derived material available.
47
48	## Hard Bans
49
50	Delete and rewrite any of these:
51	- "In today's rapidly evolving landscape"
52	- "game-changer", "revolutionary", "cutting-edge"
53	- "here's why this matters" unless it is followed immediately by something concrete
54	- ending with a LinkedIn-style question just to farm replies
55	- forced casualness on LinkedIn
56	- fake engagement padding that was not present in the source material
57
58	## Platform Adaptation Rules
59
60	### X
61
62	- open with the strongest claim, artifact, or tension
63	- keep the compression if the source voice is compressed
64	- if writing a thread, each post must advance the argument
65	- do not pad with context the audience does not need
66
67	### LinkedIn
68
69	- expand only enough for people outside the immediate niche to follow
70	- do not turn it into a fake lesson post unless the source material actually is reflective
71	- no corporate inspiration cadence
72	- no praise-stacking, no "journey" filler
73
74	### Short Video
75
76	- script around the visual sequence and proof points
77	- first seconds should show the result, problem, or punch
78	- do not write narration that sounds better on paper than on screen
79
80	### YouTube
81
82	- show the result or tension early
83	- organize by argument or progression, not filler sections
84	- use chaptering only when it helps clarity
85
86	### Newsletter
87
88	- open with the point, conflict, or artifact
89	- do not spend the first paragraph warming up
90	- every section needs to add something new
91
92	## Repurposing Flow
93
94	1. Pick the anchor asset.
95	2. Extract 3 to 7 atomic claims or scenes.
96	3. Rank them by sharpness, novelty, and proof.
97	4. Assign one strong idea per output.
98	5. Adapt structure for each platform.
99	6. Strip platform-shaped filler.
100	7. Run the quality gate.
101
102	## Deliverables
103
104	When asked for a campaign, return:
105	- a short voice profile if voice matching matters
106	- the core angle
107	- platform-native drafts
108	- posting order only if it helps execution
109	- gaps that must be filled before publishing
110
111	## Quality Gate
112
113	Before delivering:
114	- every draft sounds like the intended author, not the platform stereotype
115	- every draft contains a real claim, proof point, or concrete observation
116	- no generic hype language remains
117	- no fake engagement bait remains
118	- no duplicated copy across platforms unless requested
119	- any CTA is earned and user-approved
120
121	## Related Skills
122
123	- `brand-voice` for source-derived voice profiles
124	- `crosspost` for platform-specific distribution
125	- `x-api` for sourcing recent posts and publishing approved X output

People who liked this also viewed

6 picks

Type