折鸢

Corpus Hub contributor since 2026-10-22

折鸢's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

41files

3,311lines

★ 10GitHub stars on repo

Totals across every corpus @zy839971925-zyy appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the Agent--deep-research-Workflow-Skills corpus

zy839971925-zyy/Agent--deep-research-Workflow-Skills: A general-purpose reasoning and deep-research workflow for AI agents with semantic state, traceable evidence, validation, and change…

Look up how Agent--deep-research-Workflow-Skills implements ai-agent-skill, ai-agent-skills, ai-agent-tools, with answers cited to file and line.
Reuse a worked example: the commit “Update reasoning workflow to 2.1.1 and rewrite bilingual README” (41 files · Python).
Answer from Agent--deep-research-Workflow-Skills's real Python source instead of memory (AI, prompts and agents).

Example questions

Where does Agent--deep-research-Workflow-Skills handle “Update reasoning workflow to 2.1.1 and rewrite bilingual README”?
How does Agent--deep-research-Workflow-Skills implement ai-agent-skill?
What does skills do in Agent--deep-research-Workflow-Skills?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository zy839971925-zyy/Agent--deep-research-Workflow-Skills with XERJ (https://hub.xerj.org/corpus/zy839971925-zyy--agent--deep-research-workflow-skills).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/zy839971925-zyy/Agent--deep-research-Workflow-Skills Agent--deep-research-Workflow-Skills && git -C Agent--deep-research-Workflow-Skills checkout 97efc58e257fd5fca5ade059e2ef504dd36551d4
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Agent--deep-research-Workflow-Skills --url http://127.0.0.1:9200 --prefix agent-deep-research-work --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus zy839971925-zyy--agent--deep-research-workflow-skills · AI, prompts and agents
Related corpora: agno, xerj-blogposts, Tipatask/tipatask, dagoSte/squadra
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 10

zy839971925-zyy/Agent--deep-research-Workflow-Skills

97efc58e25 Update reasoning workflow to 2.1.1 and rewrite bilingual README

selected commit: 41 files · 3,311 lines · Python · skills, tests

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus zy839971925-zyy--agent--deep-research-workflow-skillsAIMITai-agent-skillai-agent-skillsai-agent-toolsai-agentsai-agents-automationcodex agreed 2026-10-22

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/zy839971925-zyy/badge.svg)](https://hub.xerj.org/contributors/zy839971925-zyy)

Included with the author's permission (email, 2026-10-22), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.