comp-consistency SKILL.md skillA
comp-consistency from fourteen1416/academic-agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fourteen1416/academic-agent-toolkit/comp-consistency@git:20260927.a059f3aPins git:20260927.a059f3a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fourteen1416/academic-agent-toolkit
- Path
academic-toolkit/skills/comp-consistency/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260927.a059f3a, committed Sep 27, 2026
- First version recorded
- Sep 23, 2026
- Size
- 1,845 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
Use when a competition paper must be checked against canonical results JSON, code outputs, figures, and headline metrics.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Competition Code-Paper Consistency Read `RESULTS.md`, `figures/all_results.json`, `paper/main.tex`, and declared figures. Create `CONSISTENCY_REPORT.json` with `ok`, `claims`, and each claim's paper location, result-ledger path, observed values, and comparison status. Any missing metric, mismatched value, or untraceable claim sets `ok` to false. Auxiliary sweep: also run `python tools/paper_data_check.py --mode pdf --workspace <工作区>` (repo-root relative; `--mode`/`--workspace` 均为必填) and fold its findings into `CONSISTENCY_REPORT.json` — it cross-checks paper numbers against the result ledger and is the mandatory machine backstop for this step. The contract and `ok` semantics above remain unchanged. ## 退出判据（Verification） 本步完成前逐项自检（不达标即视为未完成）： - [ ] 数值口径逐项对账（正文/图表/代码/账本四向） - [ ] 不一致项给出处置（改文/改图/说明）而非忽略 - [ ] 百分比、精度、单位变体已纳入比对 - [ ] 报告为机器可读结构，可供审计引用 ## 常见合理化（Common Rationalizations） | 合理化 | 现实 | |---|---| | "数值差一点点不算问题" | 评审会按数值对账：同一量出现两个值即判不可信。 | | "只对正文和表" | 图与代码同属公开产物，四向不对账就有缺口。 | | "以前对过一遍了" | 任何一处改动都会让旧结论失效；本步必须重跑。 | > 本段与 `skills/_utils/anti_rationalization.md`（全局版）配套：本表是本步专属， > 全局版覆盖跨步骤通用借口。新增借口时优先落到本表（更贴岗位），能泛化再上升。
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/comp-consistency@sha256:edd1569bea8adcaeThe line at the top of this page pins the label git:20260927.a059f3a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_npzyebmps67ruapi)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 23, 2026 and Sep 27, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260927.a059f3a latest | 2026-09-27 | a059f3a | 1,845 B | A | view · diff |
| git:20260927.0c37720 | 2026-09-27 | 0c37720 | 1,897 B | A | view · diff |
| git:20260923.a358745 | 2026-09-23 | a358745 | 1,837 B | A | view · diff |
| git:20260923.2013b81 | 2026-09-23 | 2013b81 | 1,906 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1845 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
fourteen1416/academic-agent-toolkit · 12 stars · license a license file GitHub does not identify · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_npzyebmps67ruapi GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/comp-consistency GET https://markdownregistry.com/api/v1/blob/edd1569bea8adcaea6ca99974c3eb851e81a74b7ff0816a4c82d2a9b903e88d5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.