SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill text-to-speechgit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/text-to-speech)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/text-to-speech"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/text-to-speech/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/benchflow-ai/skillsbench/text-to-speech"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/text-to-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00549 |
| Opus 5 | $0.00013 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
text-to-speech 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- TTS Audio Mastering — 91% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: TTS Audio Mastering
This skill focuses on producing clean, consistent, and delivery-ready TTS audio for video tasks. It covers speech cleanup, loudness normalization, segment boundaries, and export specs.
1. TTS Engine & Output Basics
Choose a TTS engine based on deployment constraints and quality needs:
- Neural offline (e.g., Kokoro): stable, high quality, no network dependency.
- Cloud TTS (e.g., Edge-TTS / OpenAI TTS): convenient, higher naturalness but network-dependent.
- Formant TTS (e.g., espeak-ng): for prototyping only; often less natural.
Key rule: Always confirm the native sample rate of the generated audio before resampling for video delivery.
2. Speech Cleanup (Per Segment)
Apply lightweight processing to avoid common artifacts:
- Rumble/DC removal: high-pass filter around 20 Hz
- Harshness control: optional low-pass around 16 kHz (helps remove digital fizz)
- Click/pop prevention: short fades at boundaries (e.g., 50 ms fade-in and fade-out)
Recommended FFmpeg pattern (example):
- Add filters in a single chain, and keep them consistent across segments.
3. Loudness Normalization
Target loudness depends on the benchmark/task spec. A common target is ITU-R BS.1770 loudness measurement:
- Integrated loudness: -23 LUFS
- True peak: around -1.5 dBTP
- LRA: around 11 (optional)
Recommended workflow:
- Measure loudness using FFmpeg
ebur128(or equivalent meter). - Apply normalization (e.g.,
loudnorm) as the final step after cleanup and timing edits. - If you adjust tempo/duration after normalization, re-normalize again.
4. Timing & Segment Boundary Handling
When stitching segment-level TTS into a full track:
- Match each segment to its target window as closely as possible.
- If a segment is shorter than its window, pad with silence.
- If a segment is longer, use gentle duration control (small speed change) or truncate carefully.
- Always apply boundary fades after padding/trimming to avoid clicks.
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.
- 8d ago First seen · 63 lines · 26 tokens per session scan A 91e8f7dc19ff
text-to-speech is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
rag-eval
NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.