CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-ppt

Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.

52

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/codex-ppt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body is a well-structured, clearly sequenced orchestration guide with strong validation gates and a clean reference map, but it defers executable command detail to docs/ files that are missing from the bundle and is somewhat repetitive in its per-phase read instructions.

Suggestions

Ship the referenced docs/*.md and prompts/slide-worker.md files (or remove the references) so the progressive-disclosure navigation actually resolves.

Include a few inline executable command examples (e.g. an assemble_ppt.py invocation with arguments) instead of deferring all command detail to docs/.

Consolidate the repeated "Before X, read docs/Y.md" phrasing into a single per-phase reference table to reduce token redundancy.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence with no basic-concept filler, but the repeated "Before X, read docs/Y.md" pattern across 13 steps and overlap between Hard Constraints and workflow prose add tokens that could be consolidated.

2 / 3

Actionability

Guidance is concrete and specific (named scripts like scripts/prepare_slide_prompts.py and record_slide_result.py, named files like deck_spec.json and slide_jobs.json, explicit states), but no inline executable command examples are shown — invocation details are deferred to the docs/ files.

2 / 3

Workflow Clarity

A clearly sequenced 13-step workflow with explicit approval gates, validation checkpoints ("If any slide is pending, dispatched, or blocked, stop"), a QA repair feedback loop (regenerate with tighter prompt, use backend editing), and an Acceptance Criteria checklist.

3 / 3

Progressive Disclosure

The structure is exemplary — a concise overview with a well-signaled one-level-deep Reference Map — but the referenced docs/*.md (9 files) and prompts/slide-worker.md do not exist in the bundle (only references/ and scripts/ are present), so the navigation does not actually resolve.

2 / 3

Total

9

/

12

Passed

Description

57%

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

The description is specific and well-targeted to a clear niche, but it describes a single main action and lacks an explicit "Use when..." trigger clause, leaving the "when to use" guidance only implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants a visually unified, full-slide-image presentation from an article, report, paper, or outline."

Include common user terms such as "presentation", "slides", and "PowerPoint" alongside "PPT/PPTX decks".

Surface one or two additional concrete actions (e.g. assemble images into .pptx, generate per-slide images) to lift specificity toward the top anchor.

DimensionReasoningScore

Specificity

Names one concrete action ("Generate visually unified image-based PPT/PPTX decks") plus several source types, but offers a single primary action rather than the multiple distinct concrete actions (e.g. extract, fill, merge) the top anchor expects.

2 / 3

Completeness

Clearly answers "what" (generate image-based decks from source material), but there is no explicit "Use when..." trigger clause; the "when" is only implied via the list of source types, which caps completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Covers natural terms like "PPT/PPTX decks", "articles, reports, papers, notes, or outlines", but omits very common variations users would say such as "presentation", "slides", or "PowerPoint".

2 / 3

Distinctiveness Conflict Risk

The "image-based" deck-generation niche with named source formats is a clear, distinct domain unlikely to trigger for unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
ningzimu/codex-ppt-skill
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.