SKILLEMALL.ai
GitHub ↗ RU Sign in

AC humanize-ppt

A presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.

nexu-io/open-design Agent Skills author: nexu-io Apache-2.0 44 files · 9 scripts body ≈ 3 501 tokens Open the sourcegithub.com↗ analyzed 6 d ago

A presentation system for agent-made PPTs — born for the talk, not just the template.

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

ProcedurePowerPointMarketingAI and agentsMedia and videotype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
90
Run on models
none yet
Process rating
C
60/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 44. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "requires-skills"
    • note edit-residue the text marks something as outdated (lines 131): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 60/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 42 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3501 tokens
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    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)
    • +3Output format is not stated: the model decides each time
    • -36 of 9 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +5Description quotes 2 example trigger phrases
    • +3Description length 674: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 42 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (8 of 17)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    In the sandbox The scripts kept to themselves

    The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

    Запущено 9 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

    Из них 7 не дошли до работы, и об их поведении мы ничего не узнали.

    scripts/humanize_ppt_v1.pyне запустился: humanize_ppt_v1.py: error: the following arguments are required: --source, --out
    scripts/humanize_ppt_v2.pyне запустился: humanize_ppt_v2.py: error: the following arguments are required: --out
    scripts/humanize_ppt_v3.pyне запустился: humanize_ppt_v3.py: error: the following arguments are required: --out
    scripts/humanize_ppt_v4.pyне запустился: humanize_ppt_v4.py: error: the following arguments are required: --out
    scripts/humanize_ppt_v5.pyне запустился: humanize_ppt_v5.py: error: the following arguments are required: --out
    scripts/humanize_ppt.pyне запустился: humanize_ppt.py: error: the following arguments are required: --out
    scripts/pptx_qa.pyничего за пределами своей папки
    scripts/preview_outline_html.pyне запустился: preview_outline_html.py: error: the following arguments are required: --slide-plan, --out
    scripts/smoke_check.pyничего за пределами своей папки

    14 Oct 2026