taw-commit
taw-commit is a Commits & pushing skill for AI agents, published by nghiahsgs in the taw-kit repository on GitHub. Skillspace rates taw-commit F (53/100) and it passed the safety scan; the rating is based on static analysis only.
taw-kit's unified commit skill: stages files, scans for secrets/env/build-artefact leaks, generates a conventional commit message by READING the actual diff (not guessing), then commits. Two modes: CONTEXT mode (called by taw orchestrator — uses .taw/checkpoint.json phase info, writes strict [P<n>] format) and SMART mode (ad-hoc — infers type+scope+subject from diff content). Replaces the old git-auto-commit + commit-message-smart skills (merged). User never types git commands. Always prefixes output with "taw:" so you know which tool did it.
- Grade
- F
- Quality
- 53 / 100
- Safety
- Passed
- GitHub stars
- 32
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.