CtrlK
BlogDocsLog inGet started
Tessl Logo

sn-ppt-workbench

Open the AI PPT editing WebUI for previously generated SenseNova HTML slides. Use when the user asks to preview, inspect, edit, or open an existing/generated PPT deck in the WebUI/workbench without regenerating slides. Accepts an explicit deck_dir or auto-detects the newest local ppt_decks entry containing HTML pages. Does not run style/outline/page-html/export generation.

71

Quality

88%

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

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.

Highly actionable with clear workflow sequencing and error handling, but it loses points on token efficiency and progressive disclosure because the Gateway Auth Setup material is duplicated inline instead of being delegated to the existing references/gateway-auth.md file.

Suggestions

Replace the inline 'Gateway Auth Setup' section with a one-line pointer to references/gateway-auth.md to remove duplication and improve both conciseness and progressive disclosure.

Signal the reference file with standard markdown link syntax (e.g. 'See [gateway-auth.md](references/gateway-auth.md)') so the reference is clearly navigable from the body.

Trim the remote-URL discovery and env-var fallback lists to the minimal actionable set, moving exhaustive fallback orderings into a reference if more detail is ever needed.

DimensionReasoningScore

Conciseness

Mostly concrete commands and env vars, but the inline 'Gateway Auth Setup' section (~30 lines including a duplicated env-var table) restates content already in references/gateway-auth.md, so it could be tightened rather than scoring fully lean.

2 / 3

Actionability

Provides copy-paste-ready, fully executable invocations — 'python3 $SKILL_DIR/scripts/open_workbench.py --deck-dir …' with real flags — plus concrete node subcommands, matching the score-3 anchor.

3 / 3

Workflow Clarity

Clear sequenced Hard Rules, ordered auto-detect paths, explicit status handling (ok/skipped/failed) with error-recovery guidance, and the stop-then-start restart pitfall provide explicit checkpoints and feedback loops.

3 / 3

Progressive Disclosure

references/gateway-auth.md exists but is never linked from the body, while its auth-setup content is duplicated inline — matching the score-2 anchor of references present but not clearly signaled with content that should be separate left inline.

2 / 3

Total

10

/

12

Passed

Description

100%

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 strong, third-person description that names concrete actions, gives explicit natural trigger terms, and sharply distinguishes itself from generation skills via explicit anti-triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Open the AI PPT editing WebUI', 'preview, inspect, edit, or open', 'auto-detects the newest local ppt_decks entry', 'Accepts an explicit deck_dir' — matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Clearly states what ('Open the AI PPT editing WebUI for previously generated SenseNova HTML slides') and an explicit 'Use when the user asks to preview, inspect, edit, or open…' trigger, satisfying both what and when.

3 / 3

Trigger Term Quality

Covers natural user phrasing — 'preview, inspect, edit, or open an existing/generated PPT deck in the WebUI/workbench' and 'without regenerating slides' — giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

'without regenerating slides' and 'Does not run style/outline/page-html/export generation' carve a clear niche and explicitly prevent conflicts with the generation skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 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

Total

13

/

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.