Azure AI
microsoft/GitHub-Copilot-for-Azure
A skill your agent uses for Azure AI: Search, Speech, OpenAI, Document Intelligence.
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths.
Install Repo Conventions
$ npx skills add juspay/neurolink --skill repo-conventions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install juspay/neurolink repo-conventions --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.yama/skills/repo-conventions .claude/skills/repo-conventions && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .claude/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventionsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add juspay/neurolink --skill repo-conventions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install juspay/neurolink repo-conventions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.yama/skills/repo-conventions .agents/skills/repo-conventions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .agents/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juspay/neurolink --skill repo-conventions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install juspay/neurolink repo-conventions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.yama/skills/repo-conventions .cursor/skills/repo-conventions && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .cursor/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/juspay/neurolink.git --path .yama/skills/repo-conventions--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add juspay/neurolink --skill repo-conventions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install juspay/neurolink repo-conventions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.yama/skills/repo-conventions .gemini/skills/repo-conventions && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .gemini/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install juspay/neurolink repo-conventionsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add juspay/neurolink --skill repo-conventions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .github/skills && cp -r skills-src/.yama/skills/repo-conventions .github/skills/repo-conventions && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .github/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juspay/neurolink --skill repo-conventions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install juspay/neurolink repo-conventions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.yama/skills/repo-conventions .opencode/skills/repo-conventions && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "repo-conventions" agent skill from https://github.com/juspay/neurolink/tree/release/.yama/skills/repo-conventions into .opencode/skills/repo-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "repo-conventions", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
repo-conventions- GitHub stars
- 148
- Token cost
- ~1.3k tokens
- SKILL.md length
- 620 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths.
- Tasks that involve Text to speech and voice
- SKILL.md covers Do NOT comment on — CI already…, The critical rules the review…, Security — the CRITICAL bar and What the review spends itself on, plus 3 more sections
- Calls node
What it does
Repo Conventions is an agent skill from juspay/neurolink. NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Text to speech and voice. It works with Model Context Protocol, OpenAI, Vercel AI SDK and TypeScript. The repository describes itself as: The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide… The licence is MIT.
When your agent uses it
- Tasks that involve Text to speech and voice
Example prompts
- “/repo-conventions”
What it can do on your machine
Read from SKILL.md and the folder at commit 81f1070. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Repo Conventions loads about 1.3k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 620 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from juspay/neurolink at commit 81f1070, republished under its MIT licence (© juspay). 620 words, ~1,344 tokens.
Download SKILL.mdSave it as
.claude/skills/repo-conventions/SKILL.md (or your agent's skills folder).- name
- repo-conventions
- description
- NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
Reviewing a change in NeuroLink
Authoritative sources in this checkout (the repository root is ../):
../CLAUDE.md— the engineering rules, long form. When a finding violates one, cite the specific rule (e.g. "Critical Rule 1: dynamic imports only in the registry").../CONTRIBUTING.md— contribution and commit conventions.
This skill is the review-focused digest; those files win on any conflict.
Do NOT comment on — CI already owns it
Formatting, lint and type errors — including CLAUDE.md rules 2 and 7–15 — are
enforced by ESLint + Prettier + tsc and the custom AST rules in eslint-rules/
(interface vs type, type file locations, barrel rules, double assertions,
e2e-only tests). Re-reporting mechanical violations buries the findings that
matter. Also skip: performance micro-costs, naming and prose taste, dependency
choice.
The critical rules the review DOES enforce (cite the rule number)
- Rule 1 — dynamic imports only in the registry. Providers are imported
dynamically inside factory functions in
providerRegistry.ts; a static provider import is a circular-dependency bug. - Rule 3 — Gemini tools + JSON-schema structured output are mutually
exclusive. Gated on
isGeminiProviderinstructuredOutputPolicy.ts, NOT on Vertex as a whole (Vertex Claude supports both). Claude paths must defaultmax_tokensviaresolveClaudeMaxTokens, never a hardcoded 4096; truncation must surface (jsonRepaired/jsonTruncated), never silently. - Rule 4 — CLI ≠ SDK. Manual MCP connections are CLI-only; CLI concerns must not leak into the SDK path.
- Rule 5 — backward compatibility of the public SDK API. Non-negotiable. Name the unmodified callers a change breaks; use the code graph to find them.
- Rule 6 —
formatProviderErrorreturns the error, never throws. - Rule 15 — tests are end-to-end only. Suites drive
dist/index.jsor the built CLI (node dist/cli/index.js); ONE module graph per suite — mixingsrc/anddist/imports breaks stubs/spies/instanceofsilently. A determinism exception must be declared in the file header and in the ESLintallowlist. - Provider
executeStreamgoes throughBaseProvider.stream()tool-merge. - Factory + Registry is the extension pattern (providers, processors, chunkers, rerankers) — a new extensible thing that bypasses it is a finding.
Security — the CRITICAL bar
Hardcoded secrets or credentials in source; secrets leaking into logs (confirm
transformParamsForLogging / secret stripping before logging provider params);
injection, unsafe eval/innerHTML/dynamic require, SSRF, path traversal; unsafe
handling of user or model input. Every CRITICAL claim must be anchored in the
change: quote the exact added line(s) from the diff. Placeholder values (docs,
tests, "sk-your-key-here", ${ENV_VAR} references) are NOT leaked secrets — a
fabricated credential-leak report is worse than a missed real one.
Show full SKILL.md (228 more words)Show less
What the review spends itself on
Logic and correctness bugs, races, unhandled rejections; provider / MCP /
streaming / proxy-pool changes; missing error handling; backward compatibility
(rule 5); missing coverage in the matching test/continuous-test-suite-*.ts
for new behaviour.
Out-of-diff impact — use the code graph when available
The diff alone does not show the damage a change does elsewhere. Orient once (architecture overview, impact radius of the changed files, affected flows), order the file-by-file pass by blast radius, and for each changed export check its callers and dependents — signature, return shape, nullability, thrown errors, async behaviour, side effects an UNMODIFIED caller does not handle. Name the exact out-of-diff call sites. If the graph is unavailable, say impact analysis was skipped — never fabricate impact claims.
Hot paths — report at MAJOR or higher, and name the blast radius
| Path | Why |
|---|---|
src/lib/core/baseProvider.ts | Central stream() tool-merge every provider rides |
src/lib/factories/providerRegistry.ts | Dynamic-import registry — the circular-dep tripwire |
src/lib/types/** | The public surface rule 5 protects |
src/lib/server/routes/*ProxyRoutes.ts | Pool engines holding subscription credentials |
src/lib/auth/** | Token stores, OAuth refresh |
src/lib/mcp/** | What tools an agent can reach |
src/lib/context/**, src/lib/memory/** | Compaction/memory — silent data loss lives here |
Discipline
- Review file by file; skip lockfiles, generated or minified assets,
dist/,build/,coverage/, images. - Read code from THIS checkout — the platform is for the pull request's comments and metadata only.
- Conventional Commits with a required scope; ONE commit per pull request (squash-merged). Releases are generated from commit history.
© juspay, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .yama/skills/repo-conventions of juspay/neurolink.
Open the folder on GitHubat commit 81f1070
Compare with similar skills
Repo Conventions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Repo Conventions this skilljuspay/neurolink | 148 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Azure AImicrosoft/GitHub-Copilot-for-Azure | 255 | 1 repos | ~852 | Automated safety check: Pass | MIT | |
| Agent Squad for TypeScript2FastLabs/agent-squad | 7.8k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| Agent Inspectrajudandigam/agent-inspect | 165 | — | ~424 | Automated safety check: Pass | MIT | |
| Ydc Openai Agent SDK IntegrationLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.4k | Automated safety check: Notes | MIT | |
| Claude APIKocoro-lab/Kocoro | 414 | 7 repos | ~4.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Agent Squad for TypeScript
2FastLabs/agent-squad
Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.
Agent Inspect
rajudandigam/agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents.
Ydc Openai Agent SDK Integration
LeoYeAI/openclaw-master-skills
Integrate OpenAI Agents SDK with You.com MCP server - Hosted and Streamable HTTP support for Python and TypeScript.
Claude API
Kocoro-lab/Kocoro
Build apps with the Claude API or Anthropic SDK. An agent skill from Kocoro-lab/Kocoro.
Opik
comet-ml/opik-mcp
Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST).
More from juspay/neurolink
Neurolink Guide
juspay/neurolink
Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.
GitHub Commenting
juspay/neurolink
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules.
Related
Categories
Questions about Repo Conventions
What does Repo Conventions do?
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Repo Conventions is an agent skill from juspay/neurolink. NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths.
When should I use Repo Conventions?
Repo Conventions fits situations like: tasks that involve Text to speech and voice.
How do I install Repo Conventions in Claude Code?
Run `npx skills add juspay/neurolink --skill repo-conventions -a claude-code`. Or copy the skill folder (.yama/skills/repo-conventions in juspay/neurolink) into .claude/skills/repo-conventions in your project. Claude Code loads it when a task matches its description.
How do I install Repo Conventions in Codex?
Run `npx skills add juspay/neurolink --skill repo-conventions -a codex`. Or copy the skill folder (.yama/skills/repo-conventions in juspay/neurolink) into .agents/skills/repo-conventions in your project. Codex loads it when a task matches its description.
Can I use Repo Conventions in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add juspay/neurolink --skill repo-conventions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repo-conventions, .gemini/skills/repo-conventions, .github/skills/repo-conventions and .opencode/skills/repo-conventions in your project.
What does Repo Conventions need to run?
Going by SKILL.md and its folder, Repo Conventions needs the command-line tools its instructions call (node).
Does Repo Conventions access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Repo Conventions safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Repo Conventions use?
Repo Conventions is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Repo Conventions use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Repo Conventions?
Skills that share tags, products or a category with Repo Conventions: Azure AI (microsoft/GitHub-Copilot-for-Azure, 255 stars), Agent Squad for TypeScript (2FastLabs/agent-squad, 7.8k stars), Agent Inspect (rajudandigam/agent-inspect, 165 stars) and Ydc Openai Agent SDK Integration (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Repo Conventions?
juspay (a GitHub organization) maintains it in juspay/neurolink, which has 148 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 11, 2026.
Source: juspay/neurolink on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.