Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Pikapika260214/rw-consulting-ppt --skill ppt-to-editablegit clone --depth 1 https://github.com/Pikapika260214/rw-consulting-pptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pikapika260214/rw-consulting-ppt/ppt-to-editable)<a href="https://agentmods.dev/skills/pikapika260214/rw-consulting-ppt/ppt-to-editable"><img src="https://agentmods.dev/badge/skills/pikapika260214/rw-consulting-ppt/ppt-to-editable/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pikapika260214/rw-consulting-ppt/ppt-to-editable"><img src="https://agentmods.dev/badge/skills/pikapika260214/rw-consulting-ppt/ppt-to-editable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 148 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 112 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.09884 |
| Opus 5 | $0.00028 | $0.04942 |
| Sonnet 5 | $0.00011 | $0.01977 |
| Haiku 4.5 | $0.00006 | $0.00988 |
Grade A, and why
ppt-to-editable scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT to Editable v3 Two-Mode Preview
This is the two-mode preview package for the ppt-to-editable skill. It keeps the proven v3.1 single-page engine and supports high-quality multi-page PPTX conversion through independent per-slide workers.
This release intentionally exposes only two product modes: single-page PNG/sample-slide conversion, and multi-page multi-Agent high-quality conversion. The previous multi-page sequential token-saving experiment is retired because its output quality was unstable. A valid multi-page run should use this folder's own scripts/ and references/, not a separate local development folder.
Convert an existing visual slide master into a more editable PowerPoint file. This skill starts from an already visible page: image-only PPTX, full-slide PNGs, screenshots, scanned/PDF pages, or approved generated slide images.
This skill does not generate a new consulting deck from notes, bullets, research, or page outlines. Use the separate deck-generation skill for that. This skill is a conversion layer.
Core Rule
Do not ship a visible text-overlay result where the original text-bearing image remains underneath editable text. That is duplicate text, not useful editability.
The final PPTX must either:
- use a clean/textless background plus editable PowerPoint text; or
- reconstruct simple elements as native PPT objects and keep only complex visuals as tight source-derived crops.
OCR is required for quality runs that start from images. OCR is not only for reading words; it provides source text geometry for text removal, editable text placement, line breaks, and QA.
For a multi-slide deck, do not run one mode over the whole deck by default. Use scripts/deck_controller.py to split the deck into per-slide jobs, route each slide independently, run OCR review gates per slide, and assemble only reviewed slide outputs into the final deck.
Preflight Gate Sequence
Before a quality conversion run, complete the gate sequence and preserve the user's answers in a gates.json file. The controller enforces this file before it creates slide jobs.
What ships with it
53 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 312 B
- references/clean-background-hybrid-contract.md 6.0 KB
- references/deck-routing-and-qa.md 8.1 KB
- references/multi-agent-slide-protocol.md 16 KB
- references/ocr-layout-recovery.md 4.6 KB
- references/ocr-to-plan-review-guide.md 1.9 KB
- references/reconstruction-contract.md 9.4 KB
- references/reconstruction-qa.md 5.2 KB
- references/source-crop-tools.md 10 KB
- references/source-reconstruction-plan-schema.md 9.9 KB
- references/text-layout-manifest.md 5.0 KB
- references/visual-fidelity-contract.md 5.5 KB
- references/visual-fidelity-execution.md 14 KB
- references/worker-compact-protocol.md 3.2 KB
- requirements.txt 119 B
- scripts/apply_crop_report_to_plan.py 5.1 KB runs code
- scripts/apply_line_alignment_patch.py 3.1 KB runs code
- scripts/apply_manifest_role_presets.py 2.1 KB runs code
- scripts/build_crop_debug_sheet.py 3.4 KB runs code
- scripts/check_ocr_runtime.py 8.2 KB runs code
- scripts/check_reconstruction_plan_text_fit.py 12 KB runs code
- scripts/check_reconstruction_visual_strategy.py 7.3 KB runs code
- scripts/deck_controller.py 144 KB runs code
- scripts/extract_source_crops.py 14 KB runs code
- scripts/fit_manifest_to_source_bboxes.py 5.0 KB runs code
- scripts/fit_manifest_typography.py 5.8 KB runs code
- scripts/inspect_pptx_editability.py 6.5 KB runs code
- scripts/judge_line_alignment.py 9.3 KB runs code
- scripts/make_clean_badge_composites.py 12 KB runs code
- scripts/make_textless_crops.py 15 KB runs code
- scripts/ocr_to_reconstruction_plan_scaffold.py 6.7 KB runs code
- scripts/package_clean_background_deck.py 17 KB runs code
- scripts/package_reconstruction_deck.py 16 KB runs code
- scripts/preflight_ocr_runtime.py 3.5 KB runs code
- scripts/prepare_worker_dispatch.py 7.7 KB runs code
- scripts/refine_source_bboxes_by_ink.py 4.7 KB runs code
- scripts/render_manifest_alignment_preview.py 8.5 KB runs code
- scripts/render_manifest_first_preview.py 8.2 KB runs code
- scripts/render_pptx_qa.ps1 3.7 KB runs code
- scripts/render_pptx_qa.py 12 KB runs code
- scripts/run_rapidocr.py 3.5 KB runs code
- scripts/run_reconstruction_qa.py 12 KB runs code
- scripts/set_manifest_field.py 1.3 KB runs code
- scripts/setup_ocr_runtime.py 6.5 KB runs code
- scripts/trace_manifest_to_line_boxes.py 8.0 KB runs code
- scripts/visual_strategy_rules.py 12 KB runs code
- scripts/write_slide_qa_summary_from_single_page.py 29 KB runs code
- tests/test_integrated_controller_contract.py 61 KB runs code
- tests/test_render_helper_contract.py 2.1 KB runs code
- tests/test_semantic_text_grouping.py 3.5 KB runs code
- tests/test_slide_qa_summary_from_single_page.py 8.0 KB runs code
- tests/test_token_economy_3_2.py 11 KB runs code
- tests/test_visual_strategy_hardening_3_1.py 17 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 597 lines · 55 tokens per session scan A bdfc85e6732b
ppt-to-editable is a skill published in the GitHub repository Pikapika260214/rw-consulting-ppt (421 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 9,884 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.