Add pptify-slides-creation plugin for editable PowerPoint slides

[kimtth]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Adds the pptify-slides-creation plugin for generating production-ready, editable PowerPoint (PPTX) decks with GitHub Copilot — from narrative strategy to coordinate-explicit slide specifications and audit-driven quality gates.

Agent

• pptify-slides-builder — guides the end-to-end deck workflow, from narrative strategy to coordinate-explicit JSON specifications and build scripts.

Skills

• pptify-context-prep — pick a business/storytelling framework, convert and summarize source material, analyze reference PPTX decks, and load bundled design profiles before authoring a spec.
• pptify-slide-spec — author or repair coordinate-explicit JSON deck specs (layout-tree groups, objects, bounding boxes, tables, images, lines, shapes, and a collision-safe type scale).
• pptify-visual-assets — plan and place icons, images, SVGs, and infographics with placement and decision guidance.
• pptify-tooling — import-only PPTX extraction and style-analysis helpers for reference-deck analysis and package inspection.
• pptify-quality-gates — validate and repair deck specs and PPTX packages against an 11-dimension audit checklist (collisions, overflows, hierarchy, asset layering, reference alignment).

The plugin is standalone: it provides guidance, design context, and import-only analysis APIs — there is no install step and no bundled setup/runtime scripts.

Validation completed locally:

npm run plugin:validate
npm run build

Both commands completed successfully, and pptify was validated as a plugin.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

Additional Notes

Preview (50 layouts)

• Office viewer - pptx

Preview (81 layouts)

• Office viewer - pptx

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct (../CODE_OF_CONDUCT.md) and will be licensed under the MIT License.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔒 PR Risk Scan Results

Scanned 17 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	1
ℹ️ Info	0

Severity	Rule	File	Line	Match
🟠	package-exec-command	docs/README.skills.md	31	| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` | Run the AgentRC readiness assessment on the curre

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🔍 Skill Validator Results

⚠️ Warnings or advisories found

Scope	Checked
Skills	5
Agents	1
Total	6

Severity	Count
❌ Errors	0
⚠️ Warnings	3
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	Found 5 skill(s)
ℹ️	[pptify-context-prep] 📊 pptify-context-prep: 2,300 BPE tokens [chars/4: 2,830] (detailed ✓), 11 sections, 0 code blocks
ℹ️	[pptify-context-prep] ⚠ No code blocks — agents perform better with concrete snippets and commands.
ℹ️	[pptify-quality-gates] 📊 pptify-quality-gates: 1,175 BPE tokens [chars/4: 1,391] (detailed ✓), 6 sections, 1 code blocks
ℹ️	[pptify-slide-spec] 📊 pptify-slide-spec: 2,131 BPE tokens [chars/4: 2,118] (detailed ✓), 12 sections, 1 code blocks
ℹ️	[pptify-tooling] 📊 pptify-tooling: 983 BPE tokens [chars/4: 1,191] (detailed ✓), 8 sections, 0 code blocks
ℹ️	[pptify-tooling] ⚠ No code blocks — agents perform better with concrete snippets and commands.
ℹ️	[pptify-visual-assets] 📊 pptify-visual-assets: 1,966 BPE tokens [chars/4: 2,280] (detailed ✓), 7 sections, 0 code blocks
ℹ️	[pptify-visual-assets] ⚠ No code blocks — agents perform better with concrete snippets and commands.
ℹ️	Found 1 agent(s)

Full validator output

Found 5 skill(s)
[pptify-context-prep] 📊 pptify-context-prep: 2,300 BPE tokens [chars/4: 2,830] (detailed ✓), 11 sections, 0 code blocks
[pptify-context-prep]    ⚠  No code blocks — agents perform better with concrete snippets and commands.
[pptify-quality-gates] 📊 pptify-quality-gates: 1,175 BPE tokens [chars/4: 1,391] (detailed ✓), 6 sections, 1 code blocks
[pptify-slide-spec] 📊 pptify-slide-spec: 2,131 BPE tokens [chars/4: 2,118] (detailed ✓), 12 sections, 1 code blocks
[pptify-tooling] 📊 pptify-tooling: 983 BPE tokens [chars/4: 1,191] (detailed ✓), 8 sections, 0 code blocks
[pptify-tooling]    ⚠  No code blocks — agents perform better with concrete snippets and commands.
[pptify-visual-assets] 📊 pptify-visual-assets: 1,966 BPE tokens [chars/4: 2,280] (detailed ✓), 7 sections, 0 code blocks
[pptify-visual-assets]    ⚠  No code blocks — agents perform better with concrete snippets and commands.
Found 1 agent(s)
Validated 1 agent(s)
✅ All checks passed (5 skill(s), 1 agent(s))

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[aaronpowell]

As mentioned with #1848 this is ill suited for distribution through this repo.

[kimtth]

@aaronpowell

As mentioned with #1848 this is ill suited for distribution through this repo.

Based on your feedback in #1848, the committed version removes all external code dependencies. Users can create PPTX slides without any external code.

I removed all external code in a previous commit and consolidated the external tool descriptions into the documentation. External tools are now optional and are not installed or configured unless explicitly requested by the user.

[kimtth]

@aaronpowell
Please review the feedback generated by Copilot. Here is a list of implementations in the main branch that rely heavily on external code and may also fall under the same rationale.

---

To gauge where the bar sits, I ran the same two criteria — (1) a narrow, specific workflow and (2) bundling/running a large amount of external code — across main. Several skills already merged meet both, and more heavily than the reworked pptify does:

Strongest matches (large bundled runtime code + niche workflow)

• skills/azure-architecture-autopilot — ~6,200 lines of bundled Python (cli.py, generator.py, icons.py + 605 icons). The SKILL states the diagram engine is "embedded within the skill" and "directly uses the bundled Python scripts."
• skills/quality-playbook — a ~2,980-line quality_gate.py, plus it bundles its own agents, a LICENSE.txt, a version stamp, and directs users to an external GitHub repo to install. Very specific multi-phase ("Council of Three") workflow — the closest analog to pptify.
• skills/mini-context-graph — a full importable Python package (~1,270 lines across 10 files under scripts/tools/). The SKILL instructs the model to from scripts.contextgraph import ... and run it — a bundled application, not documentation.

Clear matches (substantial single-purpose code, vendor/domain-specific)

• skills/eyeball (~700-line tools/eyeball.py)
• skills/terraform-azurerm-set-diff-analyzer (~780-line analyzer)
• skills/python-pypi-package-builder (~740-line scaffold.py)
• skills/namecheap (~570-line single-vendor API client)
• skills/datanalysis-credit-risk (~355-line single-domain pipeline)
• skills/sql-server-table-reconciliation (~330-line reconcile.py)
• skills/optimize-simplicite-logs (vendor-specific log parser)
• skills/nano-banana-pro-openrouter (single vendor/model image script)

Borderline (ship runnable code but broadly useful — only criterion 2 applies)
excalidraw-diagram-generator, drawio, draw-io-diagram-generator, code-tour, md-to-docx, pr-dashboard, publish-to-pages, acquire-codebase-knowledge.

On agents: the .agent.md files are prompt definitions and don't bundle/run code themselves, so they don't independently trip criterion 2 — the exception is quality-playbook, which ships agents inside the skill folder that orchestrate and copy its bundled quality_gate.py.