Ready to supercharge your AI agents?

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

SOP: Context Exploring · yogsoth-ai | DecimalAI

researchby yogsoth-ai

SOP: Context Exploring

yogsoth-ai/context-exploring

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

SOP: Read context/INDEX.md and sort the whole directory into three ARA material types (report line, process line, images), locate the north-star file, and draft a feeding plan for the ARA compiler

SkillScore64Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 13 of 21 test cases with the skill, and 4 of 21 without it.

Without skill18%

With skill64%

Checks it passed that the model alone missed

Uses ## 投喂计划 as the root heading of the markdown block.
Maps process line artifacts to trace/exploration_tree.yaml.
Maps evidence assets to evidence/figures or evidence/tables.

and 13 more in the full report

11 fixed3 passed either way7 still failing1 broke

Pass-rate lift: +45 pp
Tokens: -8%
Agent turns: 0%
Response time: -43%

Model gemini-3.6-flashMeasured 8/22/2026v114 of 22 cases passed with skill · 21 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-context-exploring/SKILL.md https://app.decimal.ai/s/yogsoth-ai-context-exploring/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-context-exploring, 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-context-exploring/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-context-exploring

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

How does the procedure define a research arc candidate when grouping context notes?

What was checked, without and with the skill
Checked	Without skill	With skill
Defines an arc candidate as a set of continuous files advancing the same topic.	Missed	Passed

case-18 · 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.md52 linessingle file

SOP: Context Exploring

Key question: 这批 context/ 里,对生成一份 ARA 最重要的素材分别是哪些,怎么分类喂给 compiler?

Why this matters (gap-3 的担子在这里)

ARA 的 compiler 是逆向抽取器:它只抽源里已有的探索过程,绝不补写 (compiler Rule 9/14)。所以 ARA 的 exploration_tree 丰不丰满,不取决于 compiler, 取决于 context/ 有没有记下失败路径 / 被否方案 / 迭代 pivot。这把担子精确落在本 SOP:必须主动打捞过程线,而不是只挑末次成功 report。

Procedure

读 context/INDEX.md。 它是总账:列 File / Phase / Topic / Checkpoints / Last Updated。正常 context 必有 INDEX;若缺失,停下并提示用户先维护 INDEX (不做无-INDEX 降级)。
默认整目录 = 一份 ARA。 同时把文件按 Phase/Topic 聚成 arc 候选 (一条研究弧 = 一组连续推进同一 Topic 的文件)。
三类素材分拣(这是本 SOP 的核心判断):
- 报告线 → claims / problem:末次 experiment-execution 的最终 report、结论性产出、被确认的设计。这是 logic/claims.md + logic/problem.md 的源。
- 过程线 → exploration_tree:失败尝试、被否决的方案、迭代中的 pivot、 "我们本来想 X 但发现 Y 所以转向 Z"。这是 trace/exploration_tree.yaml 的源。 主动打捞:逐个 checkpoint 扫,凡是 dead_end / decision / pivot 痕迹都收。
- 图片 → evidence:研究产出的图表 / 图示 / 截图。这是 evidence/figures + evidence/tables 的源。(正常 context 会有;没有就这类为空,不报错。)
定位 north-star 文件:INDEX 里 Phase 标含 "North Star" 的那篇(通常是 *-north-star-*.md)。交给下游 north-star-align 深读。

草拟投喂计划(交接物,markdown 块,严格用下列 heading):

## 投喂计划
### 主干文件
- <path>  — 报告线,claims/problem 源
### trace 素材
- <path>  — 过程线:<失败/被否/pivot 一句话>

Track record

Benchmark

13 / 21

test cases passed, vs 4 / 21 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/context-exploring/SKILL.md

View on GitHub ↗

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

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

yogsoth-ai/context-reviewTactic: Review a context/ directory — sort material into ARA types, locate and align the north-star, and produce a feeding plan for the compilerClose match+55 pp pass-rate lift

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: Context Exploring

Why this matters (gap-3 的担子在这里)

Procedure

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills