post to GitHub directly** — no comments, reviews, or replies. Draft when asked and hand the text to the user.
## Code formatting
- `make style` and `make fix-copies` should
Steady2 mentions in 2 weeks
No other project uses it yet
35k2mo agoReviewMountCreate a free account to mount
Grid routing/distributor/queue logic
## After making code changes
- Call out any high risk areas touched
- Note cross-binding impact and any follow-up issues needed
## Reviewing pull requests
See `.github/pr_review.md
No other project uses it yet
35k15d agoReviewMountCreate a free account to mount
working in the OpenClaude repository. Read it before changing code, and also follow [CONTRIBUTING.md](CONTRIBUTING.md) for contributor policy, PR expectations, review follow-up, and project scope.
## Project Snapshot
OpenClaude
34k33d agoReviewMountCreate a free account to mount
continue.
## Code style
- Write comments and documentations in English.
- Write documentation for your code.
- When introducing a workaround, leave sufficient comments explaining why it is needed and any known limitations
34k51d agoReviewMountCreate a free account to mount
path aliases: `@/*`, `@process/*`, `@renderer/*`
- Prefer `type` over `interface` (per Oxlint config)
- English for code comments; JSDoc for public functions
### Internationalization (i18n)
New or changed user-facing text must use i18n
Steady5 mentions in 2 weeks
No other project uses it yet
34k8mo agoReviewMountCreate a free account to mount
security review and testing. Illustrative status does not excuse incorrect or insecure guidance.
- When reviewingcode-heavy contributions, request a shorter conceptual revision with upstream implementation links. Successful execution
34k42d agoReviewMountCreate a free account to mount
data or migration risk. Otherwise **Needs review**, saying what to look at.
- **Complexity Simple**: small, one area, no native code, migration, or API change. **Complex**: several areas,
native code, connection/core
34k9mo agoReviewMountCreate a free account to mount
still marks that skill active.
Use explicit team orchestration for feature development, bug investigation, codereview, UX audit, and similar multi-lane work when coordination value outweighs overhead.
Team mode
Steady18 mentions in 2 weeks
No other project uses it yet
34k7mo agoReviewMountCreate a free account to mount
intended behavior
differs from the existing spec, do not silently implement the code first:
discuss the change with maintainers and update the affected specs as part of
the design
Steady5 mentions in 2 weeks
No other project uses it yet
34k10mo agoReviewMountCreate a free account to mount
Agent Guide for Telegram Desktop
This guide defines repository-wide instructions for coding agents working with the Telegram Desktop codebase.
## AI Tasks
In this repository "task" is a specific term
33k15d agoReviewMountCreate a free account to mount
review focused UI library examples, including an adversarial product UX review.
## App And Demo Skills
For working on Remix code in demos or writing Remix app code, use the root
33k8d agoReviewMountCreate a free account to mount
projects that are not deployed on Vercel, greenfield projects with no traffic, or general codereview.
## Requirements
- Node.js 20+
- Vercel CLI with `vercel metrics`, `vercel usage`, `vercel contract`, and `vercel
Steady4 mentions in 2 weeks
18 projects use a version of this
33k6mo agoReviewMountCreate a free account to mount
Common tasks table in `.agents/feature-map/INDEX.md`.
- Look up a code path in `.agents/feature-map/PATHS.md` to find its component.
- The step-by-step review procedure is `.agents/feature-map/VERIFYING.md`.
- Onyx overloads words such as Persona
33k6d agoReviewMountCreate a free account to mount
panic impossible.
- Do not suppress unused production code with underscore names or `#[allow(dead_code)]`; remove it, connect it, or track it. Underscore names remain valid for required but intentionally
No other project uses it yet
33k48d agoReviewMountCreate a free account to mount
Podman Development

## Persona
This guide is for AI coding assistants (for example Claude, ChatGPT, Copilot). Use it for context on codebase layout, development patterns, testing
Steady8 mentions in 2 weeks
1 project uses a version of this
33k5mo agoReviewMountCreate a free account to mount
Checks**: Execute only when tagging final releases; should not be executed during daily tasks, codereviews, simple edits, simple debugging, or trivial hardcoded changes. Run on demand before releasing
33k23d agoReviewMountCreate a free account to mount
must push
- If push fails, resolve and retry until it succeeds
## MCP Tools: code-review-graph
**This project has a knowledge graph. Start with the code-review-graph
MCP tools
No other project uses it yet
33k5mo agoReviewMountCreate a free account to mount
implement structural fixes. Ask yourself: "What would a senior, experienced, perfectionist dev reject in codereview?" Fix all of it.
2. REVIEWABLE FILES: When creating new code, follow the rules
33k10d agoReviewMountCreate a free account to mount