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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-create-with-human-voicegit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-with-human-voice)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-with-human-voice"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-with-human-voice/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-with-human-voice"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-with-human-voice.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 | $0.00035 | $0.02926 |
| Opus 5 | $0.00017 | $0.01463 |
| Sonnet 5 | $0.00007 | $0.00585 |
| Haiku 4.5 | $0.00003 | $0.00293 |
Grade A, and why
sk-create-with-human-voice 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 6d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-with-human-voice
create-with-human-voice is the voice-application workflow packet of the sk-doc family.
It takes prose you are writing or have written and brings it up to the Human Voice Rules,
or reports how far off it is without touching a byte.
The standard lives here and exists exactly once, at
references/hvr-rules.md. This packet owns both halves: the
standard itself, and the workflow that applies it, meaning what may be touched, in what
order, with what arithmetic, and how the result is proved. Nothing in this packet restates
a rule the standard already carries, and no consumer holds a second copy.
Keyword triggers: human voice rules, apply human voice, rewrite in human voice, make this sound human, sounds ai-generated, reads like ai wrote it, remove ai tells, ai writing tells, voice pass, de-ai the writing.
1. WHEN TO USE
Activation Triggers
- Someone says a draft reads like a machine wrote it, and wants it fixed.
- A document is about to ship and needs a voice pass before it does.
- Someone asks how a passage scores against the Human Voice Rules, without wanting edits.
- You are about to write documentation prose and want the standard in force from the first sentence rather than bolted on afterwards.
- A sibling workflow needs the HVR step of its own pipeline actually performed rather than gestured at.
When NOT to Use
- The target is a whole document needing structure, DQI and validators. That is
sk-create-quality-control, which owns the file-level audit. This mode owns the voice, and the audit calls it for that step. - The artifact does not exist yet. A README, changelog, agent, command, catalog, playbook, benchmark, diagram or repo rule is scaffolded by its own sibling mode, which then applies this standard to the prose it produced.
- The text is code, output, a quotation or a generated file. See
references/scope-and-exemptions.md. A voice edit there is a defect, not an improvement. - The request is about brand or product tone. The Human Voice Rules are a linguistic standard for documentation, not a tone-of-voice guide.
What ships with it
28 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.
- assets/voice-report-template.md 3.0 KB
- changelog/v1.0.0.0.md 3.2 KB
- changelog/v1.1.0.0.md 2.6 KB
- manual-testing-playbook/manual-testing-playbook.md 22 KB
- manual-testing-playbook/scope-gate/accuracy-outranks-the-standard.md 7.8 KB
- manual-testing-playbook/scope-gate/code-and-quotations-untouched.md 8.9 KB
- manual-testing-playbook/scope-gate/document-about-the-standard.md 7.9 KB
- manual-testing-playbook/scope-gate/exempt-spans-are-named.md 8.3 KB
- manual-testing-playbook/scoring-and-rescan/rescan-after-rewrite.md 8.7 KB
- manual-testing-playbook/scoring-and-rescan/score-does-not-edit.md 7.7 KB
- manual-testing-playbook/tell-detection/hard-blocker-terms.md 8.9 KB
- manual-testing-playbook/tell-detection/judgment-pass-not-covered-by-the-scanner.md 8.7 KB
- manual-testing-playbook/tell-detection/word-sense-is-a-candidate.md 9.0 KB
- README.md 10 KB
- references/hvr-rules.md 21 KB
- references/README.md 1.6 KB
- references/scope-and-exemptions.md 7.5 KB
- references/scoring-and-verification.md 7.1 KB
- scripts/hvr_scan.py 26 KB runs code
- scripts/README.md 3.3 KB
- scripts/tests/fixtures/voice-ai-draft.md 357 B
- scripts/tests/fixtures/voice-carried-spans.md 601 B
- scripts/tests/fixtures/voice-claim-bearing-term.md 506 B
- scripts/tests/fixtures/voice-clean.md 235 B
- scripts/tests/fixtures/voice-dirty.md 503 B
- scripts/tests/fixtures/voice-judgment-only.md 643 B
- scripts/tests/fixtures/voice-two-senses.md 360 B
- scripts/tests/test_hvr_scan.py 5.9 KB runs code
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.
- 6d ago Changed 2f0e212c1175
- 8d ago First seen · 256 lines · 35 tokens per session scan A 35dd7cd811aa
sk-create-with-human-voice is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,926 once invoked, about $0.0002 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.