CtrlK
BlogDocsLog inGet started
Tessl Logo

pptx-html-fidelity-audit

Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an HTML slide deck and asks to compare/audit/verify/fix the export — including phrases like "compare ppt with html", "fidelity audit", "fix the pptx", "ppt is cut off", "footer overlap", "italic missing in pptx", "re-export the deck", "pptx-html-fidelity-audit", or any case where a python-pptx → HTML round-trip needs verification or repair. Also trigger when the user shows you a deck.html and a deck.pptx side by side and is debugging visual differences.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 skill body: actionable code, a disciplined five-step workflow with a real verification gate, and clean one-level progressive disclosure to real bundle files. Its only weakness is mild verbosity in the reflective closing section and some step prose.

Suggestions

Tighten or cut the final 'Why geometry-based verification, not visual diff' section — its three-drawback list re-states trade-offs already implied by the workflow, saving ~150 tokens.

Compress the prose between Step 4's code blocks into a one-line lead-in per snippet; the code and the 'Customizing the rails' callout already carry the explanation.

Move the six drift-mode bullets under 'Why this is hard' into a one-line summary, since the same modes reappear as severity rubric rows in Step 3 — this removes a near-duplicate enumeration.

DimensionReasoningScore

Conciseness

The body is dense with novel domain knowledge (rail constants, Cursor/hero_budget patterns, drift taxonomy) that Claude does not already know, but a few stretches — the closing 'Why geometry-based verification, not visual diff' essay and some explanatory prose around the steps — are mildly editorial and could be trimmed. It is efficient overall, not padded with basics.

4 / 5

Actionability

Provides copy-paste-ready executable code (Cursor class, hero_layout, add_run, rail constants) and concrete commands (extract_pptx.py, verify_layout.py with --content-max-y / --canvas-h flags) covering the common slide types and verification gate.

5 / 5

Workflow Clarity

Five explicitly sequenced steps with a hard validation checkpoint — 'Zero violations is the gate for this re-export is shippable' and verify_layout.py returning nonzero on violations — plus a feedback loop (re-export → verify → fix). Because validation is present, the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with one-level-deep references that all exist (references/layout-discipline.md, font-discipline.md, audit-table-template.md; scripts/extract_pptx.py, verify_layout.py), each signaled with explicit 'read when …' conditions, keeping the bulk out of the main file.

5 / 5

Total

19

/

20

Passed

Description

100%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 dense, exemplary description that names specific actions, enumerates concrete user trigger phrases, and explicitly covers both capability and invocation conditions with minimal conflict risk. It is long but every clause carries load-bearing specificity rather than fluff.

DimensionReasoningScore

Specificity

Enumerates concrete actions — 'Audit a python-pptx export', 'identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing)', and 're-export with strict footer-rail + cursor-flow layout discipline' — giving comprehensive, specific coverage rather than generic verbs.

5 / 5

Completeness

Explicitly answers both what (audit → identify drift → re-export) and when ('Use this skill whenever the user has a .pptx ... asks to compare/audit/verify/fix the export'), including a second concrete trigger ('shows you a deck.html and a deck.pptx side by side').

5 / 5

Trigger Term Quality

Packs in natural user phrases ('fix the pptx', 'ppt is cut off', 'footer overlap', 'italic missing in pptx', 're-export the deck') plus the skill name and file extensions (.pptx, deck.html, deck.pptx), with bilingual triggers in the frontmatter list, covering synonyms and variants users actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a narrow, well-defined niche — python-pptx exports round-tripped from HTML slide decks — with distinctive triggers unlikely to fire for unrelated presentation or PDF skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
Reviewed

Table of Contents

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.