SKILLEMALL.ai
GitHub ↗ RU Sign in

BB transcript-fixer

Corrects speech-to-text transcription errors with dictionary rules and Claude's built-in AI (no external API key required); Native AI Correction is the default, Stage 1 alone is incomplete, and Stage 3 API is only for automation without Claude Code. Builds personalized correction databases, loads person-name ASR variants from the configured global people roster, and reads per-domain contexts for homophones. Before correcting a person name, the agent must consult both the global roster and the owning project's identity roster; project rosters are not auto-loaded, and occurrence frequency is never identity evidence. Use for ASR/STT output with recognition errors, homophones, garbled technical terms, person-name errors, or mixed Chinese/English, and for cleaning meeting notes, lecture transcripts, interviews, or any speech-recognition text—even when the user only says “fix this transcript,” “clean up these meeting notes,” or mentions a garbled name.

Not recommendedcritical or high security findings
daymade/claude-code-skills Agent Skills author: daymade 80 files body ≈ 9 957 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Corrects speech-to-text transcription errors with dictionary rules and Claude's built-in AI (no external API key required); Native AI Correction is the…

As a process B 73/100 · Nearly there — weak spots: result and completion, execution cost, running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
76/100
safety, quality, tests
Safety 60%
78
Quality 40%
73
Run on models
none yet
Process rating
B
73/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Result and completion w 14
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

  • high Dangerous commands cmd-persistence references/team_collaboration.md:218
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -Action $action -Trigger $trigger -TaskName "SyncTranscriptCorrections"
Medium and low: 4
  • low Dangerous commands cmd-cron-mention references/team_collaboration.md:209
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/ensure_deps.py:36
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    print("   Install uv first: curl -LsSf https://astral.sh/uv/install.sh | sh")
    code literal
  • low Secrets in code secret-high-entropy-token scripts/tests/test_common_words_safety.py:714
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Test…_06(unittest.TestCase):
    fixture
  • low Secrets in code secret-high-entropy-token scripts/tests/test_common_words_safety.py:789
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    class Test…_08(unittest.TestCase):
    fixture

Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9957 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 31, 177): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 73/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 8 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 9957 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 62 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (15 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 960: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -35 of 14 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 2 example trigger phrases
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 62 items
  • +4Reference files are cited in the instructions (23 of 23)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.