Pipecat is an open-source Python framework for building real-time conversational agents that work with voice, video, images, and other media. It is for creating voice assistants, companions, business agents, and multi-agent systems from modular conversation pipelines.
Borrowing it
Nothing to install: this file belongs to pipecat-ai/pipecat. 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/pipecat-ai/pipecat/main/.claude/skills/prose-review/SKILL.mdgit clone --depth 1 https://github.com/pipecat-ai/pipecatWrote 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/pipecat-ai/pipecat/prose-review)<a href="https://agentmods.dev/skills/pipecat-ai/pipecat/prose-review"><img src="https://agentmods.dev/badge/skills/pipecat-ai/pipecat/prose-review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01062 |
| Opus 5 | $0.00014 | $0.00531 |
| Sonnet 5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
prose-review 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the prose this work adds — comments, docstrings, changelog entries — against
the "Writing for Future Readers" section of AGENTS.md, which is the authority.
This skill is the operational check.
The reader you are writing for has never seen this change. They open the file months from now and see only the code as it stands. Detail that feels important while making a change — what the code used to do, why an alternative was rejected, that the fix was verified — is invisible context to them, and often actively misleading.
Scope
| Argument | Diff to review |
|---|---|
staged |
git diff --cached -U0 |
branch (default) |
git diff $(git merge-base main HEAD) -U0 |
<path> |
git diff $(git merge-base main HEAD) -U0 -- <path> |
The branch and <path> scopes diff against the merge base, so they cover
committed and uncommitted work — prose written moments ago still needs review.
Review added lines only (^\+): comments, docstrings, and any
changelog/*.md content. Untouched prose is out of scope. Read the surrounding
code for each hit — the judgment depends on what the code already shows.
The Test
For each added line, ask: does this describe the code as it now stands, or does it narrate the change that produced it?
Rewrite or delete anything that:
- Describes what the code used to do, or contrasts old behavior with new
- Argues the change is correct, or records that it was tested or verified
- Names an alternative that was considered and rejected
- Only restates what the adjacent code already shows
- Uses shorthand that made sense mid-task but won't to someone reading cold
Rationale survives only when its absence would puzzle a future reader — a constraint or non-obvious decision the code itself cannot express. Keep those, and prefer stating the constraint over recounting the discovery.
Calibration
Do not pattern-match on words like "previously", "instead of", "no longer", or "used to". They appear constantly in correct prose. Judge the sentence's subject: the code, or the change.
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.
- 9d ago First seen · 111 lines · 28 tokens per session scan A 799253af706d
prose-review is a skill published in the GitHub repository pipecat-ai/pipecat (15,323 stars, last pushed today), licensed BSD-2-Clause. It adds 28 tokens to every session and 1,062 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 2026-08-30.
Other skills, from other repositories
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
writing-agent-relay-workflows
Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test hardening, channels…
choosing-swarm-patterns
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…
using-agent-relay
Use when you are a registered relay agent (a spawned worker, or a lead that called registeragent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup…