fork-analysis
fork-analysis is a Branching, merging & history skill for AI agents, published by agigante80 in the actual-mcp-server repository on GitHub. Skillspace rates fork-analysis F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Analyse every GitHub fork of this repo, and every meaningful BRANCH within each fork, to find features and functionality the forks added that upstream does not have, as a source of ideas to implement. For each newly-identified idea it opens a gate-ready GitHub tracking ticket (crediting the origin fork and original author, linking the exact code to review, flagging that the imported external code MUST get a security review, and requiring positive plus negative scenarios and test cases before implementation). Maintains docs/audit/FORK_ANALYSIS.md as a cache so unchanged fork branches are skipped on the next run. Use whenever the user asks to "analyse the forks", "what do the forks add", "scan forks for features", "fork feature scan", "any new ideas from forks", or wants to harvest fork ideas, even if they do not say the word "fork-analysis".
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 33
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.
Our review
- Architecture
- 93 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- base64 decode (possible obfuscation)
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.