learning-from-corrections
learning-from-corrections is a Session review & learning skill for AI agents, published by noemuch in the bridge repository on GitHub. Skillspace rates learning-from-corrections D (62/100) and it passed the safety scan; the rating is based on static analysis only.
Use when the user says they adjusted the design in Figma, mentions "fix", "correct", "learn from", "I changed", "diff", "what changed", or wants the system to incorporate manual Figma edits back into the spec. Diffs the current Figma state against the last snapshot, classifies each change as a DS learning or a hardcoded flag, persists learnings, and patches the active recipe.
- Grade
- D
- Quality
- 62 / 100
- Safety
- Passed
- GitHub stars
- 152
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 96 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Category is a classifier prediction; no model has read this skill 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.