- name
SKILL.md
Файл навыка остаётся в репозитории издателя.
Вставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add AGIHunt/blurt --skill blurt-dictation-review -a cursor -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add AGIHunt/blurt --skill blurt-dictation-review -a claude-code -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add AGIHunt/blurt --skill blurt-dictation-review -a codex -yВставьте скопированную команду в терминал. Она установит этот SKILL.md в выбранного агента.
npx skills add AGIHunt/blurt --skill blurt-dictation-review -a grok -yОтправьте скопированное сообщение в чат Grok Bot. Бот загрузит этот SKILL.md с GitHub и добавит его к навыкам, общим для всех ваших ботов.
Install this skill: https://github.com/AGIHunt/blurt/tree/HEAD/.claude/skills/blurt-dictation-reviewОт издателя
The user dictates with Blurt all day. Their takes are the best test data there is: real voice, real pauses, real vocabulary. This skill turns them into fixes.
record.dictation.keep_audio) on. Then each take keeps its audio
($BLURT_HOME/dictation/audio/<id>.wav) and its streamed pieces (cuts, pauses, every polish window's input and
output) until the history retention (30 days). Without it only the text is there: say so and review the text alone.~/.blurt except through dictation_lab.py (cases) — no hand edits of the history or config.cloud_ref.py next to this file enforces the cap (ledger
spend.json, clips ≤ 120 s). Nothing else leaves the Mac.OPENROUTER_API_KEY=$(grep '^OPENROUTER_API_KEY=' /Users/john/workspace/ordo_projects/ordo_ai/ordo-backend/.env.prod | head -1 | cut -d= -f2- | tr -d "\"'") \
python3 -I .claude/skills/blurt-dictation-review/cloud_ref.py CLIP.wav [--language zh]
Default models: openai/whisper-large-v3 (≈ $0.03 / audio hour) and openai/gpt-transcribe (≈ $0.27 / hour). Never
print the key. On Chinese, Whisper is weaker than the local Qwen3-ASR (rare names 12 % vs 4.5 % errors), so read it as
a vote: two cloud models agreeing against Blurt is strong evidence of a recognition error; one alone is not. Cut the
disputed span out of a long take (ffmpeg -ss/-to) rather than sending it all.
uv run skills/blurt/scripts/dictation_lab.py review --since <ISO date> (or --last N). Each kept take comes back
with typed, raw (streamed ASR), heard_once (the whole take re-heard in one pass by the installed model, no
cuts), heard_diff, the pieces with pause_after and each window's polish_in / text, and flags:
fell_back:<reason>, heard_differently, seam_marks, spelled_letters, numeral_format.
For a take without audio, read ~/.blurt/dictation/history.jsonl (raw / polished / text / fell_back / reason).heard_once
has it right, the streaming (cuts, prior) caused it; if not, the model.pause_after ≥ 0.6 s and the window
that wrote it); or missing marks in dense speech.dictation_lab.py from-history ID then rerun CASE --config asr=qwen3-asr-1.7b-mlx,mode=whole …) and the
cloud second opinion below.dictation_lab.py from-history ID --corrected "<what they meant>" --tags term,punctuation --note "<why>".
Tags: term, code_switch, punctuation, filler, dropped, made_up, segmentation, clipped, slow (+ format, homophone).dictation_lab.py run --config mode=windows --json) plus
the eval sets (polish.py eval, tests/fixtures/polish_overdelete.jsonl), and the real-take replay of the
history text. Ship only what improves the cases without regressions; say the numbers.Review the user's own recent Blurt dictations (kept audio + what was typed) to find recognition, polish, punctuation and formatting errors, judge each one, save the real ones as Dictation Lab cases, a
---name: blurt-dictation-reviewdescription: Review the user's own recent Blurt dictations (kept audio + what was typed) to find recognition, polish…---# .claude/skills/blurt-dictation-review/SKILL.mdОбзор
Review the user's own recent Blurt dictations (kept audio + what was typed) to find recognition, polish, punctuation and formatting errors, judge each one, save the real ones as Dictation Lab cases, and turn them into fixes measured on the growing case set. Use when the user says "看一下今天的听写", "review my dictations", "复查一下识别问题", or reports a misrecognition they just had.
FAQ
Скачайте .claude/skills/blurt-dictation-review/SKILL.md у издателя или скопируйте путь и откройте репозиторий. PlugMCP только показывает навык в каталоге и не хранит файл.
Издатель хранит его в https://github.com/AGIHunt/blurt.
Claude, Cursor, Codex и Grok Build могут читать SKILL.md, который вы добавляете из репозитория издателя. Grok Bot устанавливает его, когда вы отправляете в чат ссылку на папку навыка на GitHub.