agentleFS
Sign inStart free
pawacapawaca/dsh-edge/.agents/skills/dsh-code-review/SKILL.md

dsh-code-review

Skill26 starsChanged 35 days agoMITView on GitHub

Review dsh-edge pull requests for Cloudflare runtime correctness, upstream-wrapper boundaries, durable compatibility, credential safety, package integrity, and focused evidence. Use when judging review findings or deciding whether an Edge PR is ready to merge.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use dsh-doc-site-sync and dsh-doc-standards.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lucaslusSkill

    dsh-doc-site-sync

    Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content changes.

    Also in 5 projects that use this

  • lucaslusSkill

    dsh-doc-standards

    Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where should this be documented", or "this doc is too long".

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify the live base and exact head, inspect the complete diff, and read AGENTS.md.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review a dsh-edge PR

Verify the live base and exact head, inspect the complete diff, and read AGENTS.md. Prioritize correctness, security, persistent data, release artifacts, and required user behavior over style.

Blocking checks

  1. Upstream behavior is composed from exact published packages. Flag copied Harness source, workspace fallbacks, ranges, dist-tags, or dependencies supplied accidentally by the root install.
  2. Direct and Dynamic Loader artifacts preserve the intended parity. Tests must start promoted or packed artifacts when validating release behavior.
  3. Durable Object bindings, class names, SQL/KV/VFS data, session events, auth cookies, and routes remain compatible.
  4. DeepSeek and owner credentials remain request-scoped or Worker secrets and never enter durable state, VFS, responses, generated configuration, logs, fixtures, or tarballs.
  5. Each Worker mode stays within Cloudflare's 64 MiB uncompressed size limit and the startup budget, and Direct mode does not silently gain unsupported network, process, PTY, or native-binary behavior.
  6. Patch files are version-bound, narrowly justified, mechanically exercised, and removable when upstream supplies the capability.
  7. Installer and release changes are cross-platform, do not guess deployment success, preserve secrets, and verify the exact npm artifact.
  8. Product and legal prose describes an independent pawaca-maintained project and does not imply DeepSeek ownership or endorsement.

Judge evidence

Trace the real HTTP/WebSocket, Durable Object, installer, Worker, and browser entrypoints affected by the change. Confirm tests fail for the claimed regression rather than restating implementation details. Compare English and Chinese text semantically; a pairing hash proves synchronization, not translation quality.

Report each defect with location, impact, and evidence. Treat incoming findings as claims: fix valid in-scope defects, rebut stale or incorrect claims, and request a user decision only when the repair changes product, security, durable data, public API, or PR scope.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free