documentation by brycewang-stanford
政策含义(cpa-policy-implication) brycewang-stanford/cpa-policy-implication
Use when drafting or strengthening the policy-implications section of a 《中国行政管理》 manuscript. Frames implications as actionable for government practice but firmly grounded in the paper's own analysis — not the empty four-verb filler. 本技能服务于《中国行政管理》(Chinese Public Administration, CPA)。
What it changes View full report → Passed 17 of 23 test cases with the skill, and 3 of 23 without it.
Without skill 13%
With skill 74%
Checks it passed that the model alone missed The report marks 【与异质性衔接】 as 否. The report marks 【与异质性衔接】 as 是. The output contains the field tag 【可操作性】.and 6 more in the full report
14 fixed3 passed either way6 still failing0 broke
Pass-rate lift +61 pp
Tokens +18%
Agent turns 0%
Response time -20% Model gemini-3.6-flashMeasured 9/1/2026 v1 17 of 23 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cpa-policy-implication/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cpa-policy-implication/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cpa-policy-implication, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/brycewang-stanford-cpa-policy-implication/ and pins it in .decimal/skills.lock
$ decimalai skills add brycewang-stanford-cpa-policy-implicationCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cpa-policy-implication/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cpa-policy-implication/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt 请评估段落:“必须强化组织领导,健全保障机制,推进协同治理,完善绩效考核,重视人才培养。”请核算四件套(强化/完善/健全/推进/加强/重视)的频次并按标准模板输出诊断。
What was checked, without and with the skill Checked Without skill With skill The report records 5 hits for generic action verbs. Passed PassedThe report rates operability as generic or empty. Passed PassedThe output includes the tag 【下一步】cpa-abstract. Missed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 77 lines single file
政策含义(cpa-policy-implication)
触发时机
文末是"强化 / 完善 / 健全 / 推进"四件套
政策建议很多,但每一条都和本文证据无关、放到任何论文都成立
审稿人指出"对策建议空泛,未建立在分析之上"
《中国行政管理》的定位:可操作,但必须有据
与经济学期刊(《经济研究》偏"意义层 / 制度层启示")不同,《中国行政管理》面向政府实践,政策建议可以也应该更具体、更可操作 。但这把双刃剑的另一面是:每一条建议都必须从本文的发现 / 机制直接推出 ,否则就退化成"对策套话"。
判断红线:把本文的实证 / 案例发现遮住,这条建议还成立 → 它就是空话,删掉或重写。
从发现到建议的推导链
每条政策含义都走"发现 → 机制 → 建议"三步:
本文发现:[具体发现,带方向 / 条件]
→ 这是因为:[本文识别的机制 / 过程]
→ 因此建议:[针对该机制的、指明"谁在哪个环节做什么"的具体措施]
反例(断链):发现"数字化考核加重基层负担",却建议"加强基层党的建设"——发现与建议无逻辑关联。
结构(推荐三段,每段一条推导链)
本文的研究具有以下政策含义。
第一,[针对核心发现]——本文发现……,这一效应主要通过[机制]实现。
因此,[某层级 / 某部门]应在[具体环节]……,重点关注[本文识别出的高风险情境 / 群体]。
第二,[针对异质性 / 条件]——本文进一步发现效应在[某情境]下更强。
这意味着政策应[差异化 / 分类施策],对[该情境]……。
第三,[针对边界 / 风险]——本文也发现……,提示在推进[某项改革]时应防范……。
Track record Benchmark 17 / 23
test cases passed, vs 3 / 23 without
Adoption
Users 1
Times used 5 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported brycewang-stanford / awesome-journal-skills
Chinese-Public-Administration-Skills/skills/cpa-policy-implication/SKILL.md
View on GitHub ↗ License MITImported 8/10/2026Version v1