ppt-master

AI-driven multi-format SVG content generation system. Converts source documents (PDF/DOCX/URL/Markdown) into high-quality SVG pages and exports to PPTX through multi-role collaboration. Use when user asks to "create PPT", "make presentation", "generate PPT", "make slides", or ...

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/ppt-master/SKILL.md

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered, highly actionable pipeline skill with excellent workflow gating and validation feedback loops. Its weaknesses are verbosity from inlined architecture and historical rationale, and broken progressive-disclosure navigation where many referenced workflow/template/docs paths are absent from the bundle.

Suggestions

Move the inlined Step 3 template architecture (three-kinds matrix, segment-ownership, fusion, and same-kind conflict tables) into docs/templates-architecture.md and keep only a brief dispatch summary plus the link in SKILL.md.

Restore or remove the missing referenced paths — the workflows/*.md, templates/icons/README.md, templates/layouts|brands|charts _index.json, docs/faq.md, docs/templates-architecture.md, and templates/*_reference.md files are cited but absent from the bundle, breaking navigation.

Trim explanatory rationale Claude does not need (e.g. rule 9's 'tried on a feature branch and abandoned' history and the redundant restatements of the serial-execution rule) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and copy-paste commands, but it carries several padded narrative sections — the ~110-line inlined Step 3 template architecture (which the skill itself says is fully specified in docs/templates-architecture.md), rule 9's abandoned-feature-branch rationale, and the long EMF/WMF blockquote — that could be tightened or moved out.	3 / 5
Actionability	Highly actionable throughout: every step gives concrete copy-paste bash commands (python3 ${SKILL_DIR}/scripts/...), situation-to-command tables cover the common cases (source formats, import situations, acquire-via paths), and file paths are explicit — matching the fully-executable anchor.	5 / 5
Workflow Clarity	Steps 1–7 are strictly sequenced with per-step 🚧 GATE prerequisites, ✅ checkbox checkpoints, explicit validation gates (svg_quality_checker.py with fix→regenerate→re-run feedback), and failure feedback loops (image acquisition retry-once→Needs-Manual→continue), satisfying the anchor for clear sequence plus error-recovery loops.	5 / 5
Progressive Disclosure	Structure and signaling of the existing references/*.md files are clear, but a large set of referenced paths do not exist in the bundle (no workflows/, templates/, or top-level docs/ directory — e.g. workflows/topic-research.md, templates/layouts/layouts_index.json, docs/faq.md, templates/design_spec_reference.md all missing), and the Step 3 template architecture is inlined in SKILL.md instead of living in its referenced doc.	3 / 5
	Total	16 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-targeted description that clearly states both capability and trigger conditions for a presentation-generation skill. Its main flaw is the truncated "or ..." ending of the trigger-phrase list, which leaves the when-clause incomplete and drops coverage of common synonyms like PowerPoint and .pptx.

Suggestions

Complete the truncated trigger list — replace "or ..." with the remaining natural phrases users say, e.g. "create PowerPoint", "make a deck", "convert this to slides", or "generate a .pptx".

Add the PowerPoint/PPTX synonyms and the .pptx file extension to the trigger clause so keyword coverage reaches the common variations users actually say.

Optionally name one or two more concrete capabilities (e.g. speaker-notes generation, AI image generation, entrance animations) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "Converts source documents (PDF/DOCX/URL/Markdown) into high-quality SVG pages and exports to PPTX" — with format-level granularity, matching the anchor that lists several specific actions with minor gaps; not 5 because image generation, animations, speaker notes, and quality-check are not mentioned.	4 / 5
Completeness	Explicitly answers both what (convert sources to SVG and export PPTX via multi-role collaboration) and when ("Use when user asks to 'create PPT'..."), but the when-clause is truncated mid-list with "or ...", leaving it just short of the fully complete anchor-5 example.	4 / 5
Trigger Term Quality	Includes four natural trigger phrases ("create PPT", "make presentation", "generate PPT", "make slides") giving good keyword coverage, but the list is literally cut off with "or ..." and misses common synonyms/extensions like PowerPoint, PPTX, .pptx, and deck.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — multi-format source-to-PPTX generation via an SVG pipeline — with distinct, unambiguous trigger phrases and minimal overlap with unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (577 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 16 missing, 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/ppt-master/SKILL.md
Commit: f5ef65b

Reviewed: ~17 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.