skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
kisev.github.io64 installs

code-review

Review one GitLab merge request or local WIP for concrete risks and proportionate fixes, preserving agreed scope and prior decisions in follow-ups. Include GitLab labels, SemVer, and manual publication commands for remote reviews. Use when the user asks to review a GitLab merge request or local work-in-progress changes. Russian discovery terms: ревью кода.

How do I install this agent skill?

npx skills add https://kisev.github.io --skill code-review
view source ↗

Is this agent skill safe to install?

No partner audit is available yet. Read the source before installing.

What does this agent skill do?

code-review

The environment contract is the installed tree's references/requirements.json, stitched by the distribution build when skills update installed it: it lists every external tool this skill needs (git, glab, uv/uvx) with its check command, a copy-ready install command, and the channel source_revision. In the first session, before any other work, run python3 scripts/check_environment.py from the skill directory and show its output: the runner prints one OK/FAIL line per tool and, for every failure, the exact install command to hand to the user. The runner installs nothing and makes no network call; never install a tool automatically, print the command instead. The runtime is the Python 3.12+ application in apps/reviewmatic, run ephemerally from Git with uvx; it is not published to npm or PyPI and needs no uv tool install. Select the same source channel as the skill: an exact vX.Y.Z release tag for stable, or the moving dev branch for development. Read source_revision from references/requirements.json and set REVIEWMATIC_FROM='git+https://github.com/kisev/skills.git@<sha>#subdirectory=apps/reviewmatic' once — a session never resolves the tip with git ls-remote. An archive installed before this contract carries the legacy references/runtime-pin.json instead; when references/requirements.json is absent, read source_revision there. Only when neither file is present (a development checkout without them) resolve the dev tip once with git ls-remote https://github.com/kisev/skills.git refs/heads/dev and pin that exact commit the same way. Treat every reviewmatic found on PATH as a foreign, possibly outdated binary and ignore it; the only runtime is the pinned uvx --from "$REVIEWMATIC_FROM" install, and a PATH hit is never diagnosed or inspected as if it were part of this review. Run every CLI command, including returned continuation actions, as uvx --from "$REVIEWMATIC_FROM" reviewmatic ..., and verify the pin right after the first invocation with reviewmatic runtime-info: compare the printed resolved commit to the pinned SHA in REVIEWMATIC_FROM (unknown or a mismatch means a stale uvx cache or an unpinned install — re-pin with the exact @<sha> and add --refresh-package reviewmatic before continuing). Open the session's first response with the version banner, assembled entirely locally: the skill version from references/requirements.json (version), the reviewmatic version and resolved install commit from reviewmatic runtime-info, and the glab --version line — no network call belongs to the banner.

Drive a remote-MR review through the one-process reviewmatic run path. At its start the run asks one poll — the critic composition and the engine of every critic (a subagent on the current session's model or the mechanical ocr CLI): present the printed fenced poll block verbatim, collect the user's choice with the host's native interactive question tool (recommended composition / single model subagent / subagent+OCR / custom), fill the selection template from that answer yourself, and run the printed command — the user never writes JSON. Ground the critic pool in the host's agent inventory (agents/*.md in the harness-global and project config directories, and the agent key of the global and project opencode.json; only agents the user configured — never the bundled agent assets of installed packages or plugins under node_modules/, which deploy only through configure agent), propose multi-critic options only when candidate agents carry distinct models or engines, and never propose two critics on the same single model — that is not independent review. The step-by-step start-review/record-* flow remains supported as the explicitly marked repair path. references/local-review.md owns the separate local-WIP mode.

Apply references/simplification-criteria.md for the optional simplification criteria.

Apply references/context-package.md for the context-package template and verification rules.

The normal tail is decision → shared render → edit the generated prose file → reviewmatic record-prose → resume and finalize. Head drift retains authorship and asks for a fresh reviewmatic record-delta verification of changes and affected conclusions. Original checks remain historical; never replace their digests or treat a mapped source position as proof of a finding's truth.

The orchestrator reads artifacts by path and passes them by path: contracts come from runtime responses, never from reading runtime sources or complete JSON schemas, and the whole context package is never read into the main window (the reading discipline in references/workflow.md pins the budget).

Apply references/necessity-doctrine.md for shared necessity and completion doctrine.

Apply references/documentation-review.md for documentation impact review.

Apply references/portable-gitlab-contracts-v2.md for the portable GitLab contracts.

Apply references/gitlab-workflow.md for the GitLab workflow.

Apply references/interaction-contract.md for evidence and mutation rules.

Apply references/inverted-tail.md as the linking reference directs.

Apply references/finding-examples.md as the linking reference directs.

Apply references/remote-review-stages.md as the linking reference directs.

Apply references/semver.md as the linking reference directs.

Apply references/architecture-checklist.md as the linking reference directs.

Apply references/review-state-machine.md as the linking reference directs.

Apply references/review-panel.md as the linking reference directs.

Apply references/incremental-review.md as the linking reference directs.

Apply references/run-path.md for the primary remote-MR review run path.

Apply references/output-format.md as the linking reference directs.

Apply references/publication.md as the linking reference directs.

Apply references/repair.md as the linking reference directs.

Apply references/poll-glossary.md for the polling vocabulary.

Each runbook stands on the current snapshot. history_context is advisory: past findings, reasons, and decisions inform critics and arbitration but never require ledger coverage, old IDs, revisions, or update_issue. Return prepared finding_id values unchanged. The runtime owns identities and bindings, while the agent owns analysis, semantic targets, fixes, and missing judgments.

Review preparation depends on the reviewmatic backend. Finished runbook commands execute directly through glab without reviewmatic. Backend collection, repair, refresh and finalization remain supported; the runtime has no interactive TUI.

Before asking the user, apply references/question-guidelines.md. Resolve the session arguments (mr=, mode=, fix=, locale=, profile=) through references/session-modes.md: auto stops on any unresolved argument without assumptions, manual confirms its recommendations in one round, and the no_reply thread matrix plus the Conventional Comments label enforcement are defined there.

Follow references/workflow.md. Apply references/language-policy.md for user-facing prose. Preserve exact code, commands, paths, IDs, JSON fields, and quotations.

The one-page map of the whole review line — every stage, authoring surface, and emergency path, pinned to this runtime — is the repository page docs/reference/code-review.md.

Related skills

Every archive in this collection stays usable on its own. These declared companions are recommended installs from the same source recorded in this skill's frontmatter source field:

  • code-simplify (uses) — panel critics and the arbitrator apply its shared simplification criteria.
  • humanize (uses) — applied to drafted thread replies before publication.
  • release-review (recommends) — release MRs route to it for the release verdict.
  • task-prepare (recommends) — full preparation of out-of-MR follow-ups is a separate invocation.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/kisev.github.io/code-review">View code-review on skillZs</a>