skillshare-code-review — Claude Code skill: review changes
skillshare-code-review is a Claude Code skill that reviews changes in skillshare before a pull request or after one opens. It starts on requests to inspect a diff, branch, commit range, or PR.
MIT ★ 3,269 updated 2026-10-29
npx skills add runkids/skillshare --skill skillshare-code-review -a claude-codeWhat skillshare-code-review does
The skill reviews a change in the skillshare repository across five passes: correctness, project rules, the spec, consumers of changed concepts, and cleanup. It first runs python3 scripts/ai-context.py pull-requests, then gathers context from the spec, repository rules, and affected concepts.
The agent checks each finding against the code and reports its file, line, and failure scenario. Reviews are read-only by default. With the fix argument, the skill applies confirmed fixes, adds a failing test for each correctness fix, and runs a focused check in the devcontainer. It uses Python 3, Git, and GitHub CLI gh; project checks must not run on the host.
What it helps with
- catch bugs in a diff before opening a pull request
- compare a change with repository rules and its spec
- find consumers that were not updated after a behavior change
Example prompts for the agent
- Review the current skillshare branch before I open a pull request.
- Review pull request 42 in the skillshare repository.
- Check the changes in
cmd/against the project rules and fix confirmed issues.
How to install skillshare-code-review
1Skills CLI (Vercel)
npx skills add runkids/skillshare --skill skillshare-code-review -a claude-code2Manually: put the files in place
~/.claude/skills/skillshare-code-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skillshare-code-review/
1Skills CLI (Vercel)
npx skills add runkids/skillshare --skill skillshare-code-review -a codex2Manually: put the files in place
.agents/skills/skillshare-code-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add runkids/skillshare --skill skillshare-code-review -a cursor2Manually: put the files in place
.cursor/skills/skillshare-code-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install runkids/skillshare .skillshare/skills/skillshare-code-review2Manually: put the files in place
.github/skills/skillshare-code-review/SKILL.md1Skills CLI (Vercel)
npx skills add runkids/skillshare --skill skillshare-code-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/runkids/skillshare --path .skillshare/skills/skillshare-code-reviewManually: put the files in place
.devin/skills/skillshare-code-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about skillshare-code-review
How do I install skillshare-code-review in Claude Code?
Run npx skills add runkids/skillshare --skill skillshare-code-review -a claude-code. The skill file is installed at ~/.claude/skills/skillshare-code-review/SKILL.md.
What does skillshare-code-review do?
It reviews a skillshare change in five passes and verifies each finding against the code. It stays read-only unless the fix argument is provided.
What does skillshare-code-review need to run?
The initial context step needs Python 3 and the repository's scripts/ai-context.py. The review uses Git and GitHub CLI gh; project checks run in the devcontainer.
Source text
SKILL.md · MIT
--- name: skillshare-code-review description: >- Review a skillshare change before it becomes a pull request, or review an open pull request. Use this skill whenever the user asks to: review a diff, branch, commit range or PR, check a change before opening a PR, run a pre-Codex review, or find what a change missed. It checks correctness, the repository's documented rules, the originating issue or spec, every consumer of a changed concept, and cleanup (reuse, simplification, efficiency, depth of fix), then verifies each finding against the code before reporting it. Read-only unless the user asks for fixes. argument-hint: "[base ref | PR number | path] [fix]" metadata: targets: [claude, universal] --- Review one change in five independent passes, verify every finding, and report them by pass. $ARGUMENTS names the target (a base ref, a PR number, or a path) and may end with `fix`. **Scope**: Read-only by default. With `fix`, apply findings as the end of Step 5 describes. Never commit, push, or comment on GitHub unless the user asks. Before acting, run `python3 scripts/ai-context.py pull-requests`. Its Review Rounds section defines what a review must sweep before Codex sees the change; this skill is how that sweep runs. ## Step 1: Pin the diff | $ARGUMENTS | Diff | |---|---| | empty | `git diff origin/main...HEAD` plus `git diff HEAD` (uncommitted work counts) | | a ref | `git diff <ref>...HEAD` plus `git diff HEAD` | | a PR number | check the PR out in a new scratch worktree (`git worktree add`, then `gh pr checkout <n>` inside it) and review there with `git diff origin/<base>...HEAD`, so Step 4 reads the PR's code, not the current branch | | a path | that file or directory, reviewed whole | Run `git fetch origin` first so the base is current. Stop here if the ref does not resolve or the diff is empty. In a shared checkout, list files changed by another session (`git status`) and leave them out of scope. ## Step 2: Gather context once 1. **Spec**: in order, issue references in commit messages or the PR body (`gh issue view <n>`), a path in $ARGUMENTS, or a matching file in `specs/`. If none exists, the Spec pass reports "no spec". 2. **Rules**: `AGENTS.md`, plus the topics for the touched areas. Run `python3 scripts/ai-context.py list` and pick by path: `cmd/` and `internal/` → `cli-development`; `ui/` or `website/src/` → `frontend`; docs, READMEs, `skills/` → `documentation`; `wiki/` → `ai-context`. 3. **Concepts**: name each flag, field, error, config key, API route, or behavior the diff adds or alters. The Consumer pass sweeps these. ## Step 3: Run five passes in parallel Launch one subagent per pass in a single message, using your tool's default subagent model; do not name a model the tool may not have. If your tool has no subagents, run the passes yourself one after another. Give each the diff command, the context from Step 2, and its brief below. Each returns findings as `file:line`, a one-sentence claim, and a concrete scenario (input or state → wrong result). A finding without a scenario is not reported. 1. **Correctness**: bugs the change introduces. Wrong results, crashes, data loss, broken error paths, races, and security gaps: path or symlink escapes, secrets in output, bypassed audits or trust prompts. Ignore style. 2. **Rules**: breaches of `AGENTS.md` and the loaded topics. Cite the file and rule. 3. **Spec**: requirements missing or partial, behavior nobody asked for, and requirements implemented wrongly. Quote the spec line for each. 4. **Consumers**: for each concept from Step 2, grep every consumer and state dimension that the pull-requests topic's Review Rounds section lists, plus `skills/skillshare/references` and `ui/src/i18n/locales`. Report each consumer the diff did not update, and each state dimension the change crosses without a test. Translations count as consumers: for every changed file under `website/docs/`, check the same path under each `website/i18n/<locale>/docusaurus-plugin-content-docs/current/`, and for `README.md`, each translated README. Report each copy that exists but was not updated to match, with the English lines it is missing. 5. **Cleanup**: code that re-implements an existing helper (name it), complexity a simpler form would remove, wasted work on hot paths, and fixes applied as a special case where the shared mechanism should change. Labelled as judgement calls. ## Step 4: Verify For every finding, read the cited code yourself and decide: - **CONFIRMED**: the scenario happens; you can name the line where it goes wrong. - **PLAUSIBLE**: the code allows it, but it depends on state you could not check. Say which. - **Dropped**: the code prevents it, the scenario needs an unsupported workflow (see the pull-requests topic), or it duplicates another finding. Count drops; do not list them. ## Step 5: Report Use the user's language. Keep the passes separate and do not rerank across them: a change can pass the spec and still break a rule. ``` ## Correctness (n) 1. CONFIRMED path:line: claim. Scenario: ... ## Rules (n) ## Spec (n) or: no spec ## Consumers (n) ## Cleanup (n) Dropped: n. Not checked: <passes or areas skipped, and why>. ``` End with the single most severe confirmed finding per pass, or "clean". With `fix`: apply the CONFIRMED findings that do not change intended behavior, add a failing test first for each correctness fix, rerun the narrowest check that proves it (in the devcontainer, as the `testing` topic describes), and report each finding as fixed, skipped (why), or no change needed. ## Rules - Do not run `go test`, `make test`, `skillshare`, or frontend scripts on the host. Checks run in the devcontainer, as the `testing` topic describes. - A finding is a claim until Step 4 confirms it. Never report an unverified finding as fact. - Review the diff, not the whole package. Pre-existing problems go in one line under "Not checked" as follow-ups.
© runkids · MIT · runkids/skillshare