evidence-selfloop
evidence-selfloop is a Plan & work review gates skill for AI agents, published by WILLOSCAR in the research-units-pipeline-skills repository on GitHub. Skillspace rates evidence-selfloop D (61/100) and it passed the safety scan; the rating is based on static analysis only.
Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose. Writes `output/EVIDENCE_SELFLOOP_TODO.md`. **Trigger**: evidence self-loop, evidence loop, evidence gaps, binding gaps, blocking_missing, 证据自循环, 证据缺口回路. **Use when**: C4 outputs exist (`outline/evidence_bindings.jsonl`, `outline/evidence_drafts.jsonl`) but writing looks hollow or C5 is BLOCKED due to thin evidence. **Skip if**: you are still pre-C3 (no notes/evidence bank yet), or you want to draft anyway and accept a lower evidence bar. **Network**: none. **Guardrail**: analysis-only; do not edit evidence/writing artifacts; do not invent facts/citations; only write the TODO report.
- Grade
- D
- Quality
- 61 / 100
- Safety
- Passed
- GitHub stars
- 487
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
- 76 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Repo-internal: written for the repository it lives in. Depends on this pipeline's own stages and outline artifacts.
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- 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.