How this skill is triggered — by the user, by Claude, or both
Slash command
/feflow:evidence-ledgerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- 被追踪任务即将 externalize(PR / merge / deploy)
优先条件:
若无 Item,可退化为临时证据摘要,不必报硬错误。
minimal适用于:
至少收集:
partial适用于:
在 minimal 基础上补充:
full适用于:
在 partial 基础上补充:
incident-overlay用于事故或 hotfix 任务,额外补充:
git branch -a | grep {ITEM-ID}git log --all --grep="{ITEM-ID}",提取 hash、作者、时间、messagegit tag --contains {commit-hash}依赖 gh CLI,不可用时标记「需手动补充」:
gh pr list --search "{ITEM-ID}",获取编号、标题、状态、reviewergh pr checks,获取各检查项 pass/fail/pending写入 .feflow/items/{ITEM-ID}/evidence/evidence.md
直接输出内联证据摘要
frontmatter 至少应含:
item_idgenerated_atevidence_levelevidence_source: auto正文按级别选取需要的区块:
只在存在相应材料时才做对比:
dev-plan.md,可对比声明范围与实际改动范围implementation-log.md,可对比记录步骤与实际提交/检查test-report.md,可对比报告中的验证项与实际证据不具备前置材料时,跳过该类对比,不要硬报缺失。
发现差异时标记为 ⚠️ 偏差,并说明它影响的是范围信任、验证信任,还是发布信任。
| 场景 | 处理 |
|---|---|
| 无匹配提交 | 警告「未找到包含 {ITEM-ID} 的提交」,允许退化为文件级证据 |
gh 不可用 | 跳过 PR/CI/Deploy,标记待补充 |
| 部分信息缺失 | 已获取的正常输出,缺失项按级别判断为 required / expected / optional |
npx claudepluginhub lxqmoma/feflow --plugin feflowGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.