slide-maker

Name: slide-maker
Author: tuan3w

32stars2forks

How to install slide-maker?

tuan3w/obsidian-vault-agent/slide-maker

$npx -y skills add tuan3w/obsidian-vault-agent --skill slide-maker

Installs into the current project.

Summary

Create slide presentations from topics, URLs, PDFs, git repos, or vault notes. Use this skill when the user asks to make slides, create a presentation, build a deck, or says "slides about X". Handles research, synthesis, outline, and creation. Default output is reveal.js HTML; pp

Files · 1

View on GitHub

SKILL.md

1	<Purpose>
2	End-to-end slide creation: from raw sources or a topic to a polished
3	presentation. Handles research, synthesis, outlining, and slide generation.
4	Produces self-contained reveal.js HTML by default (easy to edit, preview in any
5	browser). Can delegate to pptx skill when PowerPoint output is requested.
6	</Purpose>
7
8	<Use_When>
9	- User asks to create slides or a presentation about a topic
10	- User provides sources (URLs, PDFs, repos, vault notes) and wants slides
11	- User wants to edit an existing HTML or pptx slide deck
12	- User uses /slides or /slide-maker
13	</Use_When>
14
15	<Do_Not_Use_When>
16	- User wants a research note, not slides (use /research)
17	- User just wants to read/extract text from a pptx (use pptx skill directly)
18	</Do_Not_Use_When>
19
20	<Workspace>
21	All intermediate files go in `temp/slides/` (gitignored). Structure:
22	```
23	temp/slides/
24	├── research/ # Source research files (one per source)
25	├── images/ # Downloaded images (diagrams, charts, screenshots)
26	├── outline.md # Approved outline
27	└── output.html # Draft before copying to notes/slides/
28	```
29
30	Create workspace + output directories at the start of every session:
31	```bash
32	mkdir -p temp/slides/research temp/slides/images notes/slides
33	```
34
35	Final output always goes to `notes/slides/<presentation-name>.html` (or
36	`.pptx`). Images used by the presentation are copied to
37	`notes/slides/images/`. The `temp/slides/` workspace is for intermediate files
38	only.
39	</Workspace>
40
41	<Steps>
42
43	## Stage 1: PARSE — Classify Inputs
44
45	Parse $ARGUMENTS and any user context. Classify each input:
46
47	\| Input type \| Detection \| Strategy \|
48	\|------------\|-----------\|----------\|
49	\| URL \| starts with http(s):// \| WebFetch + download images \|
50	\| Git repo \| github.com or git URL \| clone to temp, read key files \|
51	\| PDF \| .pdf extension \| Read tool (for local) or download \|
52	\| Vault note \| `(Type) Name` or [[wikilink]] \| Read via MCP or Read tool \|
53	\| Existing slides (.html) \| .html extension \| Editing mode \|
54	\| Existing slides (.pptx) \| .pptx extension \| Delegate to pptx skill \|
55	\| Raw topic \| none of the above \| WebSearch + WebFetch \|
56
57	Auto-detect research depth:
58	- Quick mode: 1-2 simple sources or a short topic → inline research, no subagents
59	- Thorough mode: 3+ sources, complex topic, or broad request → parallel research agents
60
61	Present what was detected:
62	```
63	Detected sources:
64	1. [URL] blog post — will fetch + extract
65	2. [URL] paper PDF — will download and read
66	3. "transformer architecture" — will web search
67
68	Mode: thorough (3 sources → parallel research)
69	Proceeding to research...
70	```
71
72	Don't wait for confirmation unless something is ambiguous.
73
74	## Stage 2: DISCOVER — Understand the Goal
75
76	Before researching, understand what the user actually needs. Ask **up to 5
77	focused questions** in a single message. Adapt questions to what's already known
78	— skip anything the user already specified.
79
80	Questions to consider (pick the ones that aren't already answered):
81
82	1. Goal & context — What's this presentation for? (class lecture, team
83	meeting, conference talk, pitch, self-study, sharing with a friend?)
84	2. Audience — Who's watching? (technical experts, general audience, exec
85	stakeholders, students?) What do they already know?
86	3. Language — What language should the slides be in? (Don't assume English —
87	the user may want slides in their native language or a mix)
88	4. Angle & emphasis — What's the ONE thing the audience should walk away
89	with? Any specific aspects to emphasize or skip?
90	5. Vibe & format — Formal or casual? Dense/technical or visual/storytelling?
91	Any color or style preferences? Dark or light theme?
92
93	How to ask — be conversational, not interrogation-style:
94
95	```
96	Before I start researching, a few quick questions so I build the right deck:
97
98	1. What's this for — conference talk, team meeting, class?
99	2. Who's the audience? What do they already know about [topic]?
100	3. What language should the slides be in?
101	4. Any specific angle — what should the audience walk away remembering?
102	5. Style preference — formal/minimal, bold/visual, dark/light theme?
103
104	(Skip any that don't apply — I'll use sensible defaults)
105	```
106
107	After the user responds, synthesize their answers into a creative brief
108	that guides all downstream stages. Save it to `temp/slides/brief.md`:
109
110	```markdown
111	# Creative Brief
112
113	Topic: [topic]

People who liked this also viewed

6 picks

Type

slide-maker

32stars2forks

View on GitHub

How to install slide-maker?

tuan3w/obsidian-vault-agent/slide-maker

$npx -y skills add tuan3w/obsidian-vault-agent --skill slide-maker

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	<Purpose>
2	End-to-end slide creation: from raw sources or a topic to a polished
3	presentation. Handles research, synthesis, outlining, and slide generation.
4	Produces self-contained reveal.js HTML by default (easy to edit, preview in any
5	browser). Can delegate to pptx skill when PowerPoint output is requested.
6	</Purpose>
7
8	<Use_When>
9	- User asks to create slides or a presentation about a topic
10	- User provides sources (URLs, PDFs, repos, vault notes) and wants slides
11	- User wants to edit an existing HTML or pptx slide deck
12	- User uses /slides or /slide-maker
13	</Use_When>
14
15	<Do_Not_Use_When>
16	- User wants a research note, not slides (use /research)
17	- User just wants to read/extract text from a pptx (use pptx skill directly)
18	</Do_Not_Use_When>
19
20	<Workspace>
21	All intermediate files go in `temp/slides/` (gitignored). Structure:
22	```
23	temp/slides/
24	├── research/ # Source research files (one per source)
25	├── images/ # Downloaded images (diagrams, charts, screenshots)
26	├── outline.md # Approved outline
27	└── output.html # Draft before copying to notes/slides/
28	```
29
30	Create workspace + output directories at the start of every session:
31	```bash
32	mkdir -p temp/slides/research temp/slides/images notes/slides
33	```
34
35	Final output always goes to `notes/slides/<presentation-name>.html` (or
36	`.pptx`). Images used by the presentation are copied to
37	`notes/slides/images/`. The `temp/slides/` workspace is for intermediate files
38	only.
39	</Workspace>
40
41	<Steps>
42
43	## Stage 1: PARSE — Classify Inputs
44
45	Parse $ARGUMENTS and any user context. Classify each input:
46
47	\| Input type \| Detection \| Strategy \|
48	\|------------\|-----------\|----------\|
49	\| URL \| starts with http(s):// \| WebFetch + download images \|
50	\| Git repo \| github.com or git URL \| clone to temp, read key files \|
51	\| PDF \| .pdf extension \| Read tool (for local) or download \|
52	\| Vault note \| `(Type) Name` or [[wikilink]] \| Read via MCP or Read tool \|
53	\| Existing slides (.html) \| .html extension \| Editing mode \|
54	\| Existing slides (.pptx) \| .pptx extension \| Delegate to pptx skill \|
55	\| Raw topic \| none of the above \| WebSearch + WebFetch \|
56
57	Auto-detect research depth:
58	- Quick mode: 1-2 simple sources or a short topic → inline research, no subagents
59	- Thorough mode: 3+ sources, complex topic, or broad request → parallel research agents
60
61	Present what was detected:
62	```
63	Detected sources:
64	1. [URL] blog post — will fetch + extract
65	2. [URL] paper PDF — will download and read
66	3. "transformer architecture" — will web search
67
68	Mode: thorough (3 sources → parallel research)
69	Proceeding to research...
70	```
71
72	Don't wait for confirmation unless something is ambiguous.
73
74	## Stage 2: DISCOVER — Understand the Goal
75
76	Before researching, understand what the user actually needs. Ask **up to 5
77	focused questions** in a single message. Adapt questions to what's already known
78	— skip anything the user already specified.
79
80	Questions to consider (pick the ones that aren't already answered):
81
82	1. Goal & context — What's this presentation for? (class lecture, team
83	meeting, conference talk, pitch, self-study, sharing with a friend?)
84	2. Audience — Who's watching? (technical experts, general audience, exec
85	stakeholders, students?) What do they already know?
86	3. Language — What language should the slides be in? (Don't assume English —
87	the user may want slides in their native language or a mix)
88	4. Angle & emphasis — What's the ONE thing the audience should walk away
89	with? Any specific aspects to emphasize or skip?
90	5. Vibe & format — Formal or casual? Dense/technical or visual/storytelling?
91	Any color or style preferences? Dark or light theme?
92
93	How to ask — be conversational, not interrogation-style:
94
95	```
96	Before I start researching, a few quick questions so I build the right deck:
97
98	1. What's this for — conference talk, team meeting, class?
99	2. Who's the audience? What do they already know about [topic]?
100	3. What language should the slides be in?
101	4. Any specific angle — what should the audience walk away remembering?
102	5. Style preference — formal/minimal, bold/visual, dark/light theme?
103
104	(Skip any that don't apply — I'll use sensible defaults)
105	```
106
107	After the user responds, synthesize their answers into a creative brief
108	that guides all downstream stages. Save it to `temp/slides/brief.md`:
109
110	```markdown
111	# Creative Brief
112
113	Topic: [topic]

People who liked this also viewed

6 picks

Type