SKILLEMALL.ai
GitHub ↗ RU Sign in

BF slide-maker

Build, redesign, and critique clean, presentation-grade slide decks (.pptx) for any audience — research/lab meetings, work status updates, conference talks, stakeholder readouts, thesis defenses, teaching, webinars. Use whenever the user wants to make, create, redo, clean up, improve, or review slides / a deck / a presentation — e.g. "make slides for my project", "build a deck from this paper/code/doc", "turn these results into slides", "redesign this pptx", "my slides are too dense", "review my deck and tell me what's weak", "make a slide about X", "help me present this work". Works with or without a template (matches theirs, else designs a clean one) and with or without source material (mines provided code/docs/figures, else web-researches and fact-checks), in any language (e.g. English or 中文). Interviews first, then runs an actor–critic loop until an independent critic consents. Trigger even without the words "skill", "deck", or "pptx".

ClawHub Agent Skills author: Leo-Lyu v5.3.0 MIT-0 80 files body ≈ 70 136 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 49/100 · Will not run — References files that are not bundled: scripts/archetypes_html.py, scripts/ingest.py, scripts/maps.py

AnalyzerPowerPointSoftware developmentOperations and projectsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
99
Quality 40%
61
Run on models
none yet
Process rating
F
49/100
Will not run
References files that are not bundled: scripts/archetypes_html.py, scripts/ingest.py, scripts/maps.py
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 references/handoff-and-iteration.md:110
    Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment; documentation of a security skill)
    pass `--deliverables`. So don't tell the user a PDF is sitting next to the deck — offer it, and
    honesty claimsecurity skill

Files scanned: 42. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 70136 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/archetypes_html.py
  • warning missing-ref reference to a missing file: scripts/ingest.py
  • warning missing-ref reference to a missing file: scripts/maps.py
  • warning missing-ref reference to a missing file: scripts/formats.py
  • warning missing-ref reference to a missing file: scripts/deckkit.py
  • warning missing-ref reference to a missing file: scripts/lint_deck.py
  • warning missing-ref reference to a missing file: scripts/codex_delivery_gate.py
  • warning missing-ref reference to a missing file: scripts/extract_deck.py
  • warning missing-ref reference to a missing file: scripts/audience_brief.py
  • warning missing-ref reference to a missing file: scripts/plan_wordcount.py
  • warning missing-ref reference to a missing file: scripts/presets.py
  • warning missing-ref reference to a missing file: scripts/check_surface.py
  • warning missing-ref reference to a missing file: scripts/check_register_pixels.py
  • warning missing-ref reference to a missing file: scripts/check_register_guard.py
  • warning missing-ref reference to a missing file: scripts/bespoke_kits.py
  • warning missing-ref reference to a missing file: scripts/palette_audit.py
  • warning missing-ref reference to a missing file: scripts/anchor_proof.py
  • warning missing-ref reference to a missing file: scripts/icons.py
  • warning missing-ref reference to a missing file: scripts/designed_charts.py
  • warning missing-ref reference to a missing file: scripts/image_fx.py
  • warning missing-ref reference to a missing file: references/examples/build_example_generic.py
  • warning missing-ref reference to a missing file: references/examples/style_example.py
  • warning missing-ref reference to a missing file: references/examples/section_example.py
  • warning missing-ref reference to a missing file: scripts/assemble.py
  • warning missing-ref reference to a missing file: scripts/anim.py
  • warning missing-ref reference to a missing file: scripts/codex_handoff_guard.py
  • warning missing-ref reference to a missing file: scripts/check_image_provenance.py
  • warning missing-ref reference to a missing file: assets/**/sources.json
  • warning missing-ref reference to a missing file: scripts/fetch_images.py

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: scripts/archetypes_html.py, scripts/ingest.py, scripts/maps.py
  • 0Tools and files. 29 referenced file(s) missing: scripts/archetypes_html.py, scripts/ingest.py, scripts/maps.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 70136 tokens: crowds the task out of the window
  • 85Steps. 167 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 33 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (106 tags): a typed call is more reliable
  • low No test case covers injection arriving through data

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 953: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -2140 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 8 example trigger phrases
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 167 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (39 of 39)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: clean
This skill is a broad slide-deck builder with real local and network capabilities, but the inspected behavior is disclosed, purpose-aligned, and scoped to making and reviewing presentations.
LLM: benign (medium) · VirusTotal: · 4 Sept 2026