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 petar-djukic/writing-skills --skill match-voicegit clone --depth 1 https://github.com/petar-djukic/writing-skillsWrote 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/petar-djukic/writing-skills/match-voice)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/match-voice"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/match-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/petar-djukic/writing-skills/match-voice"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/match-voice.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 | $0.00118 | $0.09396 |
| Opus 5 | $0.00059 | $0.04698 |
| Sonnet 5 | $0.00024 | $0.01879 |
| Haiku 4.5 | $0.00012 | $0.00940 |
Grade A, and why
match-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 7d 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 — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renamed from voice-rewrite (2026-07). The name match-voice previously
belonged to the stylometry skill, now match-structure — if you invoked
match-voice before this date expecting measurement, you want
match-structure. This skill rewrites.
match-voice (Ollama rewrites, Claude judges)
The objective, and its constraint
Minimize the Pangram AI score — subject to the gate holding and the anchors being appropriate to the draft. The constraint is not decoration. Optimizing the score alone has a known optimum, and it is not prose you want.
Recorded run (GH-219): a hand-written, twice-hand-edited published article went from AI 77.8% to AI 0.0%, Mixed to Human, all 25 paragraphs "improved". By the score alone, a total success. What it produced:
| before | after |
|---|---|
| The grouping does two jobs. | Grouping serves two primary purposes. First, … |
| Let the orchestrator run git, not the agents. | Git operations are executed by the orchestrator rather than the agents. |
| One structural detail deserves attention before it becomes a bug. | A specific structural detail must be noted. |
The local register metrics moved the other way in the same run:
passive_enabling_per_500w 0.0 → 0.5, salad_rate_per_100 5.5 → 8.3,
opening_diversity 0.72 → 0.67. Academic passive-voice prose scores zero.
Two facts sit behind this. Pangram rated the author's own hand-written prose
77.8% AI, and filter-tells catches only 24% of real AI documents (GH-192).
Neither detector is a reliable proxy for "reads as human" on its own. The
score is evidence, and a score that falls while the register metrics worsen is
evidence of the wrong thing.
The cause of that run was anchors, not the objective: retrieval was showing the model IEEE papers for a punchy blog post (GH-216). Fix the anchors and the objective is reachable without the failure mode — which is why the driver now reports the anchors it selected, not only the pool it selected them from, before it starts.
What ships with it
33 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.
- references/authorship-lever.md 2.4 KB
- references/burstiness-validation.md 13 KB
- references/critique-prompt.md 3.9 KB
- references/model-choice.md 4.8 KB
- references/prompts.md 5.8 KB
- scripts/burstiness.py 19 KB runs code
- scripts/critique.py 13 KB runs code
- scripts/drive.py 64 KB runs code
- scripts/match_voice.py 6.5 KB runs code
- scripts/protected_terms.py 15 KB runs code
- scripts/retrieve.py 4.6 KB runs code
- scripts/rewrite.py 35 KB runs code
- scripts/test_match_voice.py 19 KB runs code
- scripts/testdata/test_anchor_reporting.py 15 KB runs code
- scripts/testdata/test_assemble_locks.py 7.0 KB runs code
- scripts/testdata/test_assemble_yaml.py 3.5 KB runs code
- scripts/testdata/test_burstiness.py 17 KB runs code
- scripts/testdata/test_citation_identity.py 2.8 KB runs code
- scripts/testdata/test_cohere_backend.py 24 KB runs code
- scripts/testdata/test_cohere_contract.py 8.5 KB runs code
- scripts/testdata/test_contract_protection.py 7.6 KB runs code
- scripts/testdata/test_critique.py 9.7 KB runs code
- scripts/testdata/test_dashes_rhythm.py 6.9 KB runs code
- scripts/testdata/test_drive_pangram.py 5.0 KB runs code
- scripts/testdata/test_env_ownership.py 1.3 KB runs code
- scripts/testdata/test_manifest.py 11 KB runs code
- scripts/testdata/test_out_naming.py 1.5 KB runs code
- scripts/testdata/test_protected_terms.py 11 KB runs code
- scripts/testdata/test_retry_notes.py 9.0 KB runs code
- scripts/testdata/test_rewrite_error_cause.py 2.5 KB runs code
- scripts/testdata/test_verify_markup.py 8.3 KB runs code
- scripts/testdata/test_wait_server.py 3.9 KB runs code
- scripts/verify.py 20 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.
- 7d ago Changed · +120 lines db404863bb84
- 12d ago First seen · 557 lines · 118 tokens per session scan A f81fcf101460
match-voice is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It adds 118 tokens to every session and 9,396 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.