SkillAgentSearch skills...

sc

SC Thai rounds — pre-process a raw chapter, run QA1 or QA2 on one or more chapters, check a resolved chapter, or mine terms for the glossary

Install / Use

npx skills add bountonw/translate

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

50/100

Supported Platforms

Claude Code

Tags

Our assessment of sc

sc scores 50/100 on our quality scale, 4277th of 4,606 Development & Engineering skills we index.

Its Claude Commands is 2.2 KB long, written without headings and no code examples: moderately detailed.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
20/30
Structure
0/20
Description
15/15
Adoption
0/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so sc is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.

Automated pattern scan on 2026-10-26. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

sc compared with similar skills

All 4 of these similar skills score higher than sc; compare them before choosing.

SkillScoreStarsUpdatedFormat
sc (this skill)by bountonw500todayClaude Commands
claude-memby thedotmack100103.4ktodayCLAUDE.md
Agent-Reachby Panniantong100103.3k1d agoCLAUDE.md
taste-skillby Leonxlnx100102.9ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10088.4ktodayCLAUDE.md

Frequently asked questions

How do I install sc?
Run npx skills add bountonw/translate. The install tabs above show the steps for each supported agent.
Which AI agents does sc work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is sc safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is sc still maintained?
The repository was last updated today, so sc is actively maintained.

description: SC Thai rounds — pre-process a raw chapter, run QA1 or QA2 on one or more chapters, check a resolved chapter, or mine terms for the glossary argument-hint: pre SC13 | qa1 SC01 SC02 | qa2 SC01 | check SC01 | terms SC01 SC02 | <term question>

@th/SC/CLAUDE.md

Before anything else, read th/SC/CLAUDE.md in full. It is the conductor procedure for the SC rounds, it lives below the working directory, and it is not loaded automatically at session start — so if you have not read it in this session, you do not yet know the procedure and must not improvise one.

Then act on: $ARGUMENTS

  • pre SCNN — the pre-processing round on a raw chapter in th/SC/01_raw; section 1.A and section 4 of that file.
  • qa1 SCNN [SCNN ...] — round one, accuracy only; section 3.C and section 4. Chapters named together run in parallel, batches inside a chapter in sequence.
  • qa2 SCNN [SCNN ...] — round two, terms and clarity; section 3.D and section 4. It refuses a chapter whose QA1 markers are not yet resolved or whose terms have no adjudicated glossary rows.
  • qa3 SCNN — not built yet; say so and stop, per 1.D.
  • check SCNN — the translator has finished resolving; follow section 5 exactly. It begins by grepping the chapter for [[ before anything is dispatched.
  • editor SCNN or editor SCNN #12 #14 — turn the remaining markers, or the named ones, into editor parentheses for Google Docs; section 1.H.
  • terms SCNN [SCNN ...] — glossary mining; section 7.
  • Anything naming a term or asking a corpus question — answer it yourself by grep, per 1.G.
  • Anything else — ask rather than guess.

Two preflight checks before you dispatch anything, both of which fail runs for reasons unrelated to the audit:

  1. Cleanliness, per section 4.A of that file. Run git status --short -- th/SC and read it per chapter, never tree-wide: your chapter's file must be unmodified, while another chapter's manuscript is another session's work and never a reason to stop.
  2. The agents sc-batch-auditor, sc-run-check, sc-resolve-check and th-glossary-miner must be listed as available. If one is not, it is not registered, and dispatching it silently falls back to a generic agent with none of its instructions — stop and tell the translator instead.

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
Updated7h ago
Forks0

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low