backlog-refiner
backlog-refiner is an Issues & backlog tracking skill for AI agents, published by axelixlabs in the axelix repository on GitHub. Skillspace rates backlog-refiner 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.
Refine and triage GitHub backlog by finding open issues that are stale, obsolete, or resolved by another path. Use this skill whenever the user asks about stale issues, backlog hygiene, issue triage, closing old tickets, reviewing open GitHub issues, whether an issue still applies, or reconciling issue text with the actual codebase—including when the ticket’s proposed fix was abandoned in favor of a different solution. Use it for axelixlabs repositories or whenever the goal is to cross-check GitHub issues against the current repo state (not just by last-updated dates). Triggers often include “refine backlog,” “which issues can we close,” “is this issue still valid,” or “audit open issues.”
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 105
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
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- LGPL-3.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
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.