Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add piter902/survey-creator-skill --skill survey-creatorgit clone --depth 1 https://github.com/piter902/survey-creator-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/piter902/survey-creator-skill/survey-creator)<a href="https://agentmods.dev/skills/piter902/survey-creator-skill/survey-creator"><img src="https://agentmods.dev/badge/skills/piter902/survey-creator-skill/survey-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/piter902/survey-creator-skill/survey-creator"><img src="https://agentmods.dev/badge/skills/piter902/survey-creator-skill/survey-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.05854 |
| Opus 5.5 | $0.00038 | $0.02342 |
| Sonnet 5.5 | $0.00019 | $0.01171 |
| Haiku 4.5 | $0.00009 | $0.00585 |
Grade A, and why
survey-creator-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survey Creator
Generate HTML survey pages only.
Treat skills/survey-creator/ as the canonical generator root for this skill. All generator-private references, templates, validators, tests, examples, and docs live under this directory.
The workflow is:
- understand the user's intent
- analyze the prompt and infer the survey structure
- generate a schema draft from
references/ - validate that schema against the reference formats and field rules
- render a submittable HTML page from the validated schema
- verify the HTML does not blank-screen in desktop and mobile browser runtimes
- verify basic accessibility and form semantics
- make the generated submit payload conform to the submission contract
- validate the submit payload against the concrete schema so every questionId / optionId / childId / score belongs to that exact survey
Do not return raw JSON schema by default. Use the schema as an internal generation artifact unless the user explicitly asks to inspect it.
Load these references first
Before generating output, read only the files you need from:
references/schema-notes.mdreferences/field-guide-overview.mdreferences/id-rules.mdreferences/survey-welcom.jsonreferences/survey-fields.mdreferences/question-radio.jsonreferences/radio-fields.mdreferences/question-checkbox.jsonreferences/checkbox-fields.mdreferences/question-input.jsonreferences/input-fields.mdreferences/question-score.jsonreferences/score-fields.mdreferences/question-nps.jsonreferences/nps-fields.mdreferences/question-finish.jsonreferences/finish-fields.mdreferences/rich-text-rules.mdreferences/pagination-rules.mdreferences/submission-contract.mdreferences/child-input-rules.mdreferences/local-cache-rules.mdreferences/logic-rules.mdreferences/logic-specification.mdreferences/logic-example-library.mdreferences/toc-survey-ui-rules.mdreferences/toc-style-system.mdvalidators/README.mdvalidators/validate_reference_consistency.pyvalidators/validate_survey_schema.pyvalidators/validate_survey_payload.pyvalidators/validate_payload_against_schema.pyvalidators/validate_survey_html_runtime.pyvalidators/validate_survey_html_interaction_e2e.pyvalidators/validate_survey_html_accessibility.pyvalidators/render_survey_html.pyvalidators/build_validated_survey.pyvalidators/generate_sample_payload.pydocs/LEGALITY_GUARANTEE.mddocs/LEGALITY_MATRIX.mdtests/contract/README.mdrun_all_legality_checks.sh
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/LEGALITY_GUARANTEE.md 4.2 KB
- docs/LEGALITY_MATRIX.md 2.7 KB
- docs/PERFORMANCE_BENCHMARK.md 2.6 KB
- docs/PRE_RELEASE_CHECKLIST.md 15 KB
- docs/TECHNICAL_DETAILS.md 8.0 KB
- docs/TECHNICAL_DETAILS.zh-CN.md 7.9 KB
- docs/TOC_SURVEY_UI_SPEC.md 2.0 KB
- evals/evals.json 11 KB
- evals/real-world/cases/complex-all-types-business-regression/expected.json 114 B
- evals/real-world/cases/complex-all-types-business-regression/prompt.md 184 B
- evals/real-world/cases/complex-all-types-business-regression/schema.json 11 KB
- evals/real-world/cases/kindergarten-xhs-registration/expected.json 114 B
- evals/real-world/cases/kindergarten-xhs-registration/prompt.md 138 B
- evals/real-world/cases/kindergarten-xhs-registration/schema.json 6.7 KB
- evals/real-world/cases/thermos-meituan-satisfaction/expected.json 167 B
- evals/real-world/cases/thermos-meituan-satisfaction/prompt.md 205 B
- evals/real-world/cases/thermos-meituan-satisfaction/schema.json 5.8 KB
- evals/real-world/cases/wechat-pc-mobile-product-feedback/expected.json 103 B
- evals/real-world/cases/wechat-pc-mobile-product-feedback/prompt.md 187 B
- evals/real-world/cases/wechat-pc-mobile-product-feedback/schema.json 5.1 KB
- evals/real-world/cases/xhs-ai-native-creator-feedback/expected.json 101 B
- evals/real-world/cases/xhs-ai-native-creator-feedback/prompt.md 175 B
- evals/real-world/cases/xhs-ai-native-creator-feedback/schema.json 4.8 KB
- evals/real-world/README.md 963 B
- evals/real-world/run_real_world_evals.py 5.4 KB runs code
- examples/ai-design-tool-demand-demo.html 110 KB
- examples/ai-design-tool-demand-demo.json 12 KB
- examples/lead-qualification-sales-conversion.html 109 KB
- examples/lead-qualification-sales-conversion.json 11 KB
- examples/minimal-survey.html 99 KB
- examples/minimal-survey.json 1.1 KB
- examples/service-satisfaction-multi-finish.html 108 KB
- examples/service-satisfaction-multi-finish.json 9.8 KB
- examples/service-satisfaction-post-submit-redirect.html 110 KB
- examples/service-satisfaction-post-submit-redirect.json 12 KB
- examples/service-satisfaction-three-finish.html 105 KB
- examples/service-satisfaction-three-finish.json 7.0 KB
- references/checkbox-fields.md 4.8 KB
- references/child-input-rules.md 2.6 KB
- references/field-guide-overview.md 1.8 KB
- references/finish-fields.md 2.9 KB
- references/id-rules.md 2.1 KB
- references/input-fields.md 4.6 KB
- references/local-cache-rules.md 1.7 KB
- references/logic-condition-action-guide.md 8.7 KB
- references/logic-example-library.md 7.8 KB
- references/logic-rules.md 6.5 KB
- references/logic-specification.md 6.9 KB
- references/nps-fields.md 3.2 KB
- references/pagination-rules.md 2.4 KB
- references/question-checkbox.json 2.0 KB
- references/question-finish.json 693 B
- references/question-input.json 865 B
- references/question-nps.json 1.3 KB
- references/question-radio.json 1.9 KB
- references/question-score.json 1.4 KB
- references/radio-fields.md 4.2 KB
- references/rich-text-rules.md 1.7 KB
- references/schema-notes.md 5.8 KB
- references/score-fields.md 3.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 578 lines · 94 tokens per session scan A 147aa3f99fc9
survey-creator-skill is a skill published in the GitHub repository piter902/survey-creator-skill (6 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 5,854 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
open-ontologies
AI-native ontology engineering using 110 MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
review-trtmc-pr
Review a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, third-party dependency and license obligations, and exact-head validation evidence. Use for contributor self-review before marking a PR…
submit-github-bug-issue
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…
mc-zenn
Turn MulmoClaude work into a Zenn tech article (markdown) inside the workspace. On first use it sets up a Zenn project at github/zenn/ — clone an existing GitHub repo or zenn init a fresh one, idempotent and skipped when already initialized — then writes articles to github/zenn/articles/ .md tagged with the…
debug-trt-mismatch
Diagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.