Zairan Mir

Corpus Hub contributor since 2026-10-20

Zairan Mir'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

11files

1,231lines

★ 5GitHub stars on repo

Totals across every corpus @Mir-Zairan 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 shoga-speaks corpus

Mir-Zairan/shoga-speaks: 🦜 Claude Code plugin that explains everything in your language, script and role: Roman-Urdu, Urdu, Hinglish, Hindi, Dutch. Plain-language…

Look up how shoga-speaks implements accessibility, ai-coding-assistant, anthropic, with answers cited to file and line.
Reuse a worked example: the commit “Fixes from an adversarial test pass: term lines, cards, markers, comm…” (11 files · TypeScript, JavaScript).
Answer from shoga-speaks's real TypeScript source instead of memory (AI, prompts and agents).

Example questions

How does shoga-speaks implement accessibility?
What does hooks do in shoga-speaks?

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

Search the GitHub repository Mir-Zairan/shoga-speaks with XERJ (https://hub.xerj.org/corpus/mir-zairan--shoga-speaks).
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/Mir-Zairan/shoga-speaks shoga-speaks && git -C shoga-speaks checkout b8cd16d60b07ae4a6dfe52659f860502327ccfbb
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./shoga-speaks --url http://127.0.0.1:9200 --prefix shoga-speaks --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 mir-zairan--shoga-speaks · AI, prompts and agents
Related corpora: griptape, react-spectrum, HoussemDjeghri/self-review, Antarsoft/morphness
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 5

Mir-Zairan/shoga-speaks

b8cd16d60b Fixes from an adversarial test pass: term lines, cards, markers, comm…

selected commit: 11 files · 1,231 lines · TypeScript, JavaScript · hooks, tests, scripts

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

selected · in licence reviewcorpus mir-zairan--shoga-speaksAIMITaccessibilityai-coding-assistantanthropicclaudeclaude-codeclaude-code-plugin agreed 2026-10-20

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/Mir-Zairan/badge.svg)](https://hub.xerj.org/contributors/Mir-Zairan)

Included with the author's permission (email, 2026-10-20), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.