CtrlK
BlogDocsLog inGet started
Tessl Logo

sn-ppt-standard

Standard and fast PPT pipeline. All LLM / VLM / T2I calls are wrapped in a single CLI entry (scripts/run_stage.py). The main agent's job is simple: emit ONE shell command per stage, never write loops, never write prompts. Standard mode plans thoroughly with a three-sample deck preview checkpoint (three concatenated deck images plus a preview URL), web research, image search, and user-selected final output format (PPTX or PDF) for polished, delivery-ready presentations. Fast mode builds a complete draft immediately with autonomous decisions, then provides structured refinement suggestions so the user can iterate quickly. Supports AI-generated infographics (U1) for diagrams and flowcharts, web image search (Serper) for real photos, and ECharts for data charts.

60

Quality

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is highly actionable with a clearly sequenced pipeline and strong validation/error-recovery loops. It is held back by redundancy across overlapping sections and heavy inline detail that could be moved into reference files.

Suggestions

Consolidate the duplicated model-pitfall / reasoning-model guidance and the repeated python-pptx prohibition into a single canonical section to reduce redundancy.

Extract the WebUI/bridge provider configuration and MSYS path-conversion pitfalls into a dedicated reference file, keeping only a brief pointer inline.

Merge the two manual-fallback descriptions (Stage failure handling vs. SN API timeout fallback) into one procedure to avoid restating the same steps.

DimensionReasoningScore

Conciseness

The content is largely domain-specific and non-obvious (CLI subcommands, model pitfalls, MSYS path handling), but notable redundancy exists: the SN API model pitfall and reasoning-model handling overlap, the manual fallback appears twice, and the python-pptx prohibition is restated in three sections.

2 / 3

Actionability

Provides fully executable bash commands with exact flags, concrete concurrency/page-range splits, exact JSON status formats, specific env var overrides, and step-by-step fallback procedures — copy-paste ready.

3 / 3

Workflow Clarity

The pipeline is explicitly sequenced (preflight through export) with validation checkpoints (HTML content check before export, file-size spot-check after batch-page-html, ask_user waits, resume semantics) and clear error-recovery feedback loops with retry limits.

3 / 3

Progressive Disclosure

Real one-level-deep references exist (references/html_constraints.md, references/style_catalog.md) and are signaled, but a large volume of detailed operational content (model pitfalls, manual fallback, WebUI/bridge provider config, MSYS pitfalls) remains inline in a ~470-line body that could be externalized.

2 / 3

Total

10

/

12

Passed

Description

67%

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 distinct, clearly conveying a two-mode PPT generation pipeline with concrete tooling. Its main weakness is the absence of explicit 'Use when' trigger guidance and thin natural-language trigger terms.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers such as 'make slides', 'generate a PPT', 'create a presentation', or '制作PPT'.

Reduce reliance on internal jargon (LLM/VLM/T2I, U1, Serper, ECharts) in favor of user-facing terms to broaden trigger coverage.

Include common variations like 'slides', 'deck', and 'PowerPoint' alongside 'PPT' and 'presentations'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across two modes (three-sample deck preview checkpoint, web/image search, PPTX/PDF export) plus specific tooling (U1 infographics, Serper, ECharts), matching the comprehensive anchor.

3 / 3

Completeness

The 'what' is clearly answered, but there is no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Some natural terms appear ('PPT', 'presentations') but coverage is thin and dominated by technical jargon ('LLM / VLM / T2I', 'U1', 'Serper', 'ECharts'); common variations like 'slides', 'deck', or 'PowerPoint' are absent.

2 / 3

Distinctiveness Conflict Risk

The skill carves a clear self-contained niche (single-CLI PPT pipeline) explicitly distinguished from sibling skills (sn-image-base, sn-ppt-entry), making mis-triggering unlikely.

3 / 3

Total

10

/

12

Passed

Validation

75%

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

Validation12 / 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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository
OpenSenseNova/SenseNova-Skills
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.