From next-task
Grades agent findings as HIGH/MEDIUM/LOW certainty (deterministic/heuristic/semantic) to gate actions: auto-fix HIGH, review MEDIUM, human-approve LOW.
How this skill is triggered — by the user, by Claude, or both
Slash command
/next-task:certainty-gradeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
All agent findings MUST include a certainty grade. Grade determines action path.
All agent findings MUST include a certainty grade. Grade determines action path.
| Grade | Basis | Action |
|---|---|---|
HIGH | Deterministic: regex match, static check, type error, compiler output | Auto-fix permitted |
MEDIUM | Heuristic: code ratio analysis, pattern frequency, structural smell | Flag for review |
LOW | AI judgment: semantic meaning, intent, contextual inference | Human gate required |
HIGH if finding_type == deterministic (provable without AI)MEDIUM if finding_type == heuristic (pattern-based, probabilistic)LOW if finding_type == semantic (requires AI reasoning)[HIGH] <finding>, [MEDIUM] <finding>, [LOW] <finding>HIGH → auto-apply fix if safe, log result
MEDIUM → surface to user, suggest fix, await confirmation
LOW → block action, require explicit human approval, explain reasoning
[HIGH] console.log() at src/foo.ts:42 — remove (debug artifact)
[MEDIUM] function doThing() lacks error handling — review
[LOW] variable naming may be misleading given domain context — human review
Used by: /next-task, /code-quality, all agents that produce findings.
b00t MUST grade all MCP tool outputs before acting on them.
npx claudepluginhub elasticdotventures/_b00t_ --plugin next-taskValidates code quality using certainty-graded rules to detect AI artifacts, anti-patterns, and b00t violations. Categorizes findings as auto-fixable, needs-review, or human-gate for pre-merge or implementation checks.
Triages static analysis findings from aide (secrets, complexity, clones, coupling) by reading code, assesses merit, and dismisses noise with findings_accept.
Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.