SKILLEMALL.ai

BF article-html-to-ppt

Author professional, editable PPTX decks from Markdown, HTML, text, PDF, data, or a user template. A capable model owns source understanding, narrative, slide content, visual encoding, component selection/composition, speaker notes, and any new native components; PPT Smith supplies source anchors, reviewed template components, deterministic execution, real rendering, and fail-closed QA. Use for bespoke decks, template-driven decks, and diagnostic standard compilations.

ClawHub Agent Skills author: 夜猫子弦月 v4.1.0-beta.1 MIT-0 80 files body ≈ 2 878 tokens Open the sourceclawhub.ai analyzed 2 d ago

Author professional, editable PPTX decks from Markdown, HTML, text, PDF, data, or a user template.

As a process F 34/100 · Will not run — References files that are not bundled: schemas/v4/presentation-ir.schema.json, schemas/v4/examples/

ProcedurePowerPointSoftware developmentWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
99
Quality 40%
75
Run on models
none yet
Process rating
F
34/100
Will not run
References files that are not bundled: schemas/v4/presentation-ir.schema.json, schemas/v4/examples/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Concealment en-hide-from-user README.en.md:281
    Instruction to hide actions from the user (negated — the text forbids it)
    Before Feishu/Lark export, confirm that the user intended cloud delivery. Do not silently upload sensitive drafts, internal PRDs, metrics, automation designs, or unpublished content.
    negated

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: schemas/v4/presentation-ir.schema.json
  • warning missing-ref reference to a missing file: schemas/v4/examples/

Process rating: all ten parameters 34/100

Will not run. References files that are not bundled: schemas/v4/presentation-ir.schema.json, schemas/v4/examples/
  • 0Tools and files. 2 referenced file(s) missing: schemas/v4/presentation-ir.schema.json, schemas/v4/examples/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 59 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2878 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +3Description length 473: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 59 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (6 of 20)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: suspicious
This appears to be a real PowerPoint-building skill, but it can run user- or model-provided Python code with broad local privileges and lacks clear sandboxing or script approval controls.
LLM: suspicious (high) · 10 Sept 2026