Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

SOP: ARA Compile · yogsoth-ai | DecimalAI

researchby yogsoth-ai

SOP: ARA Compile

yogsoth-ai/ara-compile

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/

SkillScore86Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 17 of 20 test cases with the skill, and 6 of 20 without it.

Without skill32%

With skill86%

Checks it passed that the model alone missed

Passes the failure report directly to the user.
Hands off the resulting output to ara-rigor-review.
Rejects splitting the task across parallel subagents.

and 13 more in the full report

13 fixed6 passed either way2 still failing1 broke

Pass-rate lift: +55 pp
Tokens: -29%
Agent turns: 0%
Response time: -58%

Model gemini-3.6-flashMeasured 8/22/2026v119 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-ara-compile/SKILL.md https://app.decimal.ai/s/yogsoth-ai-ara-compile/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-ara-compile, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yogsoth-ai-ara-compile/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-ara-compile

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-ara-compile/SKILL.md https://app.decimal.ai/s/yogsoth-ai-ara-compile/SKILL.md

Raw file: /s/yogsoth-ai-ara-compile/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-ara-compile.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

When formatting arguments for compiling `context/report.md` into an ARA package, what flag and directory path should be used to store the output so it does not get re-ingested as context during future reviews?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies --output ../ara/ as the output directory argument.	Missed	Passed

case-09 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

SOP: ARA Compile

Key question: 怎么把投喂计划喂给外部 compiler,一次抽出一份内部一致的 ARA?

Preflight

先确认外部 compiler skill 可 load(ARA skills 已装:npx @ara-commons/ara-skills)。若不可用,提示用户安装并停下,不要静默继续。

Why one inline call, not multi-subagent

ARA 的 cross-layer binding(claim→proof→evidence、tree→claim)必须全局一致。分批 compile 会各自从 C01 起撞 ID、断 tree,汇总等于重缝半成品 —— 正是 ARA 要消灭的事。compiler 自带覆盖度循环(max 3 轮)+ 内建 Task 工具;真需要并行由它内部自理,本 SOP 不越俎拆分。

Procedure

把投喂计划整理成 compiler 的 $ARGUMENTS:
- 主干文件清单 + trace 素材清单 + 图片清单的路径(compiler 按路径读);
- 标注哪些是主干(报告线 → claims/problem);
- 大方向作为约束文本(约束 PAPER.md 的 title/abstract);
- --output ../ara/(与 context/ 平级,天然不会被下次 review 当 context 吃回去)。
例:
```
compiler context/2026-06-06-01-30-stage7-...md context/2026-06-05-...stage6...md \
  context/figures/*.png \
  --output ../ara/ \
  主干=stage7(报告线);其余为过程线/图片;大方向:<从 north-star-align 来的一段>
```
一次 inline 运行:Skill load compiler,传上面的 $ARGUMENTS。 compiler 跑 4 阶段(语义解构 → 认知映射 → src 层 → 探索图抽取)+ 覆盖度循环
- Seal Level 1。
Seal Level 1 不过:compiler 自带 fix-iterate(2–3 轮),本 SOP 不接管; 若仍不过,把失败报告透传给用户,停。

Output

Track record

Benchmark

17 / 20

test cases passed, vs 6 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yogsoth-ai / de-anthropocentric-research-engine

skills/ara-compile/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

SOP: ARA Compile

Preflight

Why one inline call, not multi-subagent

Procedure

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills