Tessl • The management layer for AI agent skills

The body is an exemplary instruction-only skill: lean and assumption-respecting, with fully executable tool guidance, a clearly sequenced workflow with validation and repair loops at every fragile step, and a well-signaled one-level reference structure verified against the actual bundle. No changes needed.

Dimension	Reasoning	Score
Conciseness	The body is dense, prescriptive prose ("Two rounds at most; then mention what is left"; "Never edit `.kun-ppt-review/`; the tools own it") with no explanations of concepts Claude already knows and no padding — about 75 lines for a multi-tool workflow. Every section carries operational content, matching the 'every token earns its place' anchor.	5 / 5
Actionability	Guidance is fully executable: exact tool names and parameters (`ppt_preview` with `directions` and one `recommended`, `replace: true`, `allowQaErrors`, `repairHint`), concrete thresholds (body text at least 14 pt, 40 px margins on 960 x 540, at most six generated images per deck), exact paths, and a concrete deliverable format. Per the rubric's code-vs-instruction note, the absence of code is not penalized because the instruction guidance is this specific.	5 / 5
Workflow Clarity	An eight-step workflow (Understand, Plan, Direction, Build, Fix lint, Review, Export, Deliver) with explicit validation checkpoints and feedback loops: preview lint issues are fixed and re-previewed, geometry errors trigger "apply each `repairHint`... and export again", `allowQaErrors` is gated behind two failed repair rounds, and delivery requires `ppt_export` returning `validated: true`. This matches the anchor with explicit validation, error-recovery loops, and checkpoints.	5 / 5
Progressive Disclosure	The body is a lean overview with a References section headed "Load only what the current step needs" that maps each file to a load condition (e.g. charts.md "only when a slide has a chart", design-policy.md "once per deck"). All referenced paths were verified to exist in the bundle, references are one hop deep (styles.md indexes leaf files the body already points to directly), and detail is appropriately split out of SKILL.md.	5 / 5
	Total	20 / 20 Passed

Description

66%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.

The description states a concrete, well-scoped 'what' in third person with distinct PowerPoint/PPTD niche language, but it entirely lacks a 'when to use' trigger clause, capping completeness. Adding trigger phrases and common synonyms would close the gap.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants a new presentation, a rebuilt deck, or a native .pptx file" — this would raise completeness from 3 to 5.

Include the natural synonyms users actually say — "presentation", "slides", and the ".pptx" extension — alongside "PowerPoint decks".

State the boundary in the description (small edits to an existing .pptx belong to office-editing tools) to reduce conflict risk with closely related skills.

Dimension	Reasoning	Score
Specificity	"Create, revise, review, and export native, editable PowerPoint decks from PPTD source" lists four concrete lifecycle actions plus a concrete source format, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because capabilities the skill actually covers (charts, themes, image slots, delegation) are not mentioned.	4 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent trigger guidance; "in the main conversation" is a scope note, not a when-condition. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3, and it is not lower because the 'what' is clearly stated.	3 / 5
Trigger Term Quality	"PowerPoint" and "decks" are natural user terms, giving good keyword coverage, but common synonyms "presentation", "slides", and the ".pptx" extension are missing and "PPTD" is internal jargon. This sits above anchor 3 (which lacks natural variations) but below anchor 5 (comprehensive synonym/extension coverage).	4 / 5
Distinctiveness Conflict Risk	"native, editable PowerPoint decks from PPTD source" carves a mostly distinct niche with minor overlap risk against generic .pptx-editing skills, since "revise... PowerPoint decks" could trigger for small edits that belong to office-editing tools. It is not 5 because the description itself states no boundary against those closely related skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 5 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: KunAgent/Kun
Path: resources/bundled-skills/slides/SKILL.md
Revision: 0d84061

Reviewed: 15 days ago

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.

slides

Table of Contents

Is this your skill?