Project Purpose
PaperSpine is a contribution-first paper and report writing skill for Claude
Code, Codex, OpenClaw, and Hermes CLI. It researches the target scene, confirms
the controlling contribution
6.3k2d agoReviewMountCreate a free account to mount
never post a claim about someone else's work without verifying it against the code first.
- When Ben asks for a reply to a contributor, produce a short draft
6.2k11d agoReviewMountCreate a free account to mount
Agents (awesome-telegram)
This file provides instructions for Claude and other AI agents when reviewing pull requests, evaluating contributions, or helping maintain this repository.
---
## Purpose of this list
A curated
6.2k3mo agoReviewMountCreate a free account to mount
commands. Use `X | Y`, built-in collection types, and type annotations for new Python code.
```bash
uv sync
uv run pytest tests/basic
uv run pre-commit run --all-files
```
`tests/basic
6.2k20d agoReviewMountCreate a free account to mount
segment-spi`.
- **Config or API changes** should update relevant configs and docs where applicable.
## CodereviewReview the changed behavior and relevant contracts before declaring implementation complete. Follow
[kb/agents/code-reviewer.md](kb/agents/code-reviewer.md
6.2k2mo agoReviewMountCreate a free account to mount
also keeps a private notebook and a scheduler, and it reviews its own conversations when alone. Write code and docs that preserve an individual's continuity; **tool calls
6.1k39d agoReviewMountCreate a free account to mount
Test after changes** - Run project's test suite to verify
- **Zero tolerance for errors** - Code must pass all checks
- **Run specified tests** - Use project's testing framework
- **Validate before commit
6.1k18mo agoReviewMountCreate a free account to mount
ONLY change grants/policies — never touch the data itself
- Always propose SQL as code for the user to review, never execute destructive SQL directly
## Environments
- Three environments, one-directional flow: local
6k29d agoReviewMountCreate a free account to mount
worked. The convention now names that specifically:
reviewing what nobody has written is worse than idling, because it also
produces findings about code that will not exist.
## The fresh-install
Steady2 mentions in 2 weeks
No other project uses it yet
6k8mo agoReviewMountCreate a free account to mount
Generate code for this repository
- Modify existing files
- Suggest patches or pull requests
- Perform codereviews
- Assist users in contributing to this project
If prompted to interact with this repository
6k17mo agoReviewMountCreate a free account to mount
browsing.
- Read graphify-out/GRAPH_REPORT.md only for broad architecture review or when query/path/explain do not surface enough context.
- After modifying code, run `graphify update .` to keep the graph current
No other project uses it yet
5.9k17d agoReviewMountCreate a free account to mount
After model changes, ensure HF checkpoints still
load correctly. Document reasons for model changes.
## CodeReview
Use the `pr-review` skill to review PRs (`/pr-review <PR#>` or `/pr-review
branch`); `@claude
5.9k13d agoReviewMountCreate a free account to mount
this layer owns the logic, with a code trace from producer to consumer.
### Code Style and Review Conventions
Recurring review feedback distilled into rules — following them avoids review round-trips
5.8k4mo agoReviewMountCreate a free account to mount
Amend
A fresh agent reviews the commit as if it were a real codereviewer: checks correctness, style, edge cases, test coverage, and regressions. It also reviews all documentation changes
5.8k4mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.