Skip to content
dsh-hot
Release

feat(skill): generic-migration control skill (T1a) + S1-S10 generic-arm pilot

Source excerpt

内容 T1a(GAP-ANALYSIS P0):新增 skills/generic-migration/SKILL.md —— 框架无关的插件迁移方法论(LLM 在无框架资料条件下生成,人工过一遍无 dsh 泄漏:无版本号/API 名/卡片编号/具体命令),供论文三条件设计的 generic-skill 对照组使用。已加入 skill-composition 覆盖守卫的 NON_COMPOSITION_SKILLS(与 dsh-benchmark-case 同理,不属于 workflow 组合模型)。

Automatically summarized from source discussions. Sources and the full record are available below.

Review record and full evidence

Evidence & timeline

Verification

Not yet verified

Maintainer response

Untriaged

Author response

No response recorded

Earliest source found so far

Unknown

Sep 7, 2026, 03:38 PM

Research & review record

Lifecycle

Emerging

Source scope

13 automatically linked original sources; source relationships and independence are not human reviewed

Attribution confidence · 0%

First found by this site · Sep 7, 2026, 03:58 PM

Evidence, test conditions and updates
Research & review record · Reviewed propagation graph
06

Reviewed propagation graph

00

No source-to-source propagation relation recorded.

Source timeline

  1. GitHub PR

    feat(skill): generic-migration control skill (T1a) + S1-S10 generic-arm pilot

    Open source Opens in a new tab
  2. GitHub Issue

    Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  3. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  4. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  5. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  6. GitHub PR

    feat(paper): switch main line to capability-contingent skill effect

    Open source Opens in a new tab
  7. GitHub PR

    feat(paper): extend paired analysis to five model points (inverted-U)

    Open source Opens in a new tab
  8. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  9. GitHub PR

    feat(paper): reviewer-perspective revision (framing, disclosure, 16 refs, retitle)

    Open source Opens in a new tab
  10. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  11. GitHub Issue

    Comment on Benchmark 跑批结果总览:模型 × harness × 条件矩阵(S+H 全系列)

    Open source Opens in a new tab
  12. GitHub PR

    feat(benchmark): unified GLM-5.3-Flash 64-trial two-arm run (workplan §5 middle-config cell) + frozen GLM-5.2 kit

    Open source Opens in a new tab
  13. GitHub PR

    Comment on feat(benchmark): unified GLM-5.3-Flash 64-trial two-arm run (workplan §5 middle-config cell) + frozen GLM-5.2 kit

    Open source Opens in a new tab

Related stories

  • BenchmarkNot yet verified

    Investigation lead: feat(benchmark): S18 terminal sprite render trap (half-block SGR leak, trim ghosting, timer pinning)

    The lead source, “feat(benchmark): S18 terminal sprite render trap (half-block SGR leak, trim ghosting, timer pinning),” says: “Summary Adds benchmark task S18-terminal-sprite-render-trap (static, read-only report): a terminal half-block sprite renderer whose three independent rendering bugs (SGR background.” 36 related sources are linked for comparison to determine whether they describe the same event.

    42 sources· GitHub / Blog
  • BenchmarkNot yet verified

    Investigation lead: feat(benchmark): H22 not-listed trap — the package that installs but never registers

    The lead source, “feat(benchmark): H22 not-listed trap — the package that installs but never registers,” says: “Distilled from a real top-tier failure: anywhere-labs/dsh-desktop (22k★) failed our 50-plugin live verification on 09-01 with exactly this shape — dsh plugin add succeeds, the entr.” 31 related sources are linked for comparison to determine whether they describe the same event.

    32 sources· GitHub / Blog
  • ReleaseNot yet verified

    Investigation lead: fix(benchmark): 补齐S类诊断题的LLM评分并细化rubric

    The lead source, “fix(benchmark): 补齐S类诊断题的LLM评分并细化rubric,” says: “改了什么 S13、S14、S20原来仍按关键词打分,这次接入现有的LLM判分器。S11、S16、S17、S18、S19、S21、S22沿用#212已合入的迁移,进一步写清每项怎么给分、什么情况给半分、哪些错误建议会触发封顶。10题版本统一升到4.1.0,题面和fixture保持原样。.” 14 related sources are linked for comparison to determine whether they describe the same event.

    16 sources· GitHub / Blog