Borrowing it
Nothing to install: this file belongs to epam/ai-dial-chat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/epam/ai-dial-chat/development/.claude/skills/dial-docs/SKILL.mdgit clone --depth 1 https://github.com/epam/ai-dial-chatWrote 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/epam/ai-dial-chat/dial-docs)<a href="https://agentmods.dev/skills/epam/ai-dial-chat/dial-docs"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/dial-docs/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/epam/ai-dial-chat/dial-docs"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/dial-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 12 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 12 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 14 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 15 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00142 | $0.01094 |
| Opus 5.5 | $0.00057 | $0.00438 |
| Sonnet 5.5 | $0.00028 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00109 |
Grade A, and why
dial-docs 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 yesterday.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DIAL Docs
Ground-truth design docs live in docs/. This skill is the index. Open only the doc that matches your task — don't read all of them.
Index
| Doc | Read it when |
|---|---|
docs/architecture.md |
Orienting on the overall app: structure, layers, major decisions. |
docs/technical-requirements.md |
You need the product/technical requirements behind a feature. |
docs/auth/auth-bff-encrypted-cookie.md |
Changing the auth flow: stateless BFF, OIDC login/callback, encrypted session cookie, transparent refresh, federated logout, cross-pod stateless decryption. |
docs/auth/testing-current-auth-implementation.md |
Writing or running auth tests: what exists today (GET /api/v1/auth/me, global SessionGuard, refresh) and how to exercise it. |
docs/auth/auth-diagrams/ |
You need the picture: Mermaid .mmd + .svg for architecture, provider registry, login, refresh, logout, cross-pod, cookie structure. |
docs/legacy-chat-migration-guide.md |
Moving a deployment from the legacy DIAL Chat (0.x) to 1.0: what changed, the checklist, and the legacy → new environment-variable mapping. |
docs/theme-customization.md |
Theming: the themes service and config.json format, the color tokens the app reads, logos and favicon, the light/dark/system picker, legacy theme migration. |
docs/chat-overlay-migration-guide.md |
Embedding the chat: the overlay package, postMessage protocol and handshake, OverlayFeature flags, and migrating from the legacy @epam/ai-dial-overlay. |
docs/custom-viewers.md |
Working on Custom Viewers: an application's own iframe page replacing the conversation view — configuration, query params, the data sent, the events handled, sandbox limits. |
docs/mcp-apps.md |
Working on MCP Apps: tool discovery, message matching, the inline preview and canvas, the BFF proxy endpoints, the separate-origin sandbox, caching, deployment, known limits. |
docs/responses-api-integration.md |
Working on completions dispatch: how deployments declaring responses_api are routed and normalized. |
docs/observability.md |
Configuring OpenTelemetry, interpreting HTTP/generation/runtime metrics, importing Grafana dashboards, or troubleshooting missing telemetry. |
docs/host-install-matrix.md |
An embedding host asks what to put in its own package.json for a given set of libs. Generated from the manifests; do not hand-edit. |
docs/reusable-chat-workflows.md |
Adopting the reusable skill-import, file-attachment or prompt-selector workflows in another chat host: public imports, what the host keeps, release alignment, and what the packed fixtures do and do not prove. |
apps/chat-api/README.md |
The full environment-variable reference: every supported variable, its default, and its effect. apps/chat-api/.env.template is the annotated source. |
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.
- yesterday Changed · +1 lines · +15 tokens per session 67f8f8cdd97d
- 9d ago Changed · +1 lines 11c359d7040d
- 16d ago Changed · +1 lines · +19 tokens per session 083200db159a
- 1mo ago Changed · +1 lines 74315423318d
- 1mo ago Changed · +1 lines 800254d61ec9
- 1mo ago First seen · 33 lines · 108 tokens per session scan A 9b62717d970c
dial-docs is a skill published in the GitHub repository epam/ai-dial-chat (502 stars, last pushed today), licensed Apache-2.0. It adds 142 tokens to every session and 1,094 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
box
Box manages cloud files, sharing, search, and metadata.
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…
mantis-report
Generates a human-readable security review packet compiled from confirmed findings and exploit chains. Use at the end of a review cycle to produce stakeholder-facing documentation. Don't use for auditing code or verifying patches directly.
structuring-radiology-reports
Converts free-text radiology narratives into structured findings and impression — with measurements, laterality, anatomy, and follow-up recommendations — after OpenMed NER. Use when the user has a CT/MRI/X-ray/ultrasound/mammography report and needs the sections split (technique, comparison, findings, impression)…