- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add kyy-logs/code-review-skill --skill code-review -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add kyy-logs/code-review-skill --skill code-review -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add kyy-logs/code-review-skill --skill code-review -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add kyy-logs/code-review-skill --skill code-review -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/kyy-logs/code-review-skill/tree/HEAD/skills/code-reviewDo publicador
Check for code defects, test quality, and change impact, and confirm that the issues found are closed.
references/, scripts/, and assets/ are relative to the directory containing the SKILL.md read for this run.docs/work/, code paths, and project rules all belong to the reviewed project.CODE_REVIEW_SKILL_DIR below is the absolute path of the skill installation directory. Set it on every shell invocation, or replace it directly with the actual absolute path; do not assume variables persist across different shell invocations.bash; no executable bit is needed.python is invoked by default, and CODE_REVIEW_PYTHON can specify the interpreter's absolute path.
For installation, see the release repository README; the in-repo entry point is scripts/install.py.The artifact root {output_root} defaults to docs/work; override it with project .code-review/config.json output_dir or CODE_REVIEW_OUTPUT_DIR. This run's artifacts are written to {output_root}/active/{slug}/.
Check items are not hardcoded in this file; they are driven by the
references/probes.yamlregistry. Probe implementation details are inreferences/probes/<probe-name>.md; this file covers main workflow orchestration and shared probe execution boundaries.Execution boundary: static review by default. For coverage checks, prefer reusing an existing report; when measurement is needed, coverage commands may be run within what this round's task allows. Other checks remain read-only evidence. Do not modify the reviewed source code during review. Test and CI output are review evidence; all tests green does not mean the behavior is correct.
Determine the review scope:
Choose a mode; when unspecified, review uncommitted changes by default. The base/head below are recorded as concrete commit IDs.
git diff <base> -- to collect staged and unstaged changes;
use git ls-files --others --exclude-standard -z to collect untracked files,
and review their full contents as newly added code.git diff <base> <head> --.
When head is omitted, use the current HEAD and review only that commit range.Read the corresponding source:
git show <head>:<path> to read the target version,
and read base when an older version is needed. File scans use only on-disk files consistent with the target version.Record and hand off: save the mode, base, target (working tree or head), changed-file list, and diff, for use by all probes. Use NUL separators when processing the file list programmatically, and pass each path as a quoted argument.
After collecting scope, initialize a new run before dispatching:
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" init {slug}
The returned JSON gives review_dir, output_dir, line_target, and branch_target.
Existing active directories, archived runs, or event history with the same slug are rejected.
Use a unique slug for a new review; explicitly continuing the same run reuses its directory without init.
Never dispatch two runs writing the same directory. Pass the actual directory and effective targets to all probes,
overriding the registry's coverage defaults. Init creates the report template.
Source inspection is read-only; the workflow writes reports, probe JSON, policy.json, events, and archive metrics.
Read the registry and determine the probe list: Read references/probes.yaml and decide by requires:
errorskipped, stating what is missingRun probes in parallel:
Dispatch: the main executor dispatches an independent agent per probe according to the registry, providing the review scope, diff, project root, skill path, and that probe's inputs and , and including in the dispatch prompt "Execution boundary" above and "Shared probe constraints" in this step. Also pass any provided requirements, acceptance criteria, and change context as text or file paths, and ask each probe to read relevant material. Note missing inputs without inventing them. If dependency source or contract material is already available, pass its path, version, and origin for on-demand reuse; do not pre-download all dependencies.
Any of the following conditions blocks merge. This round's report lists the blocking items; the table below gives the follow-up handling requirements:
See section 4 of references/output-schema.md for how execution status and input errors are determined.
Script validation verifies consistency between report records and counts; it cannot prove the checks were sufficient.
{output_root}/active/{slug}/code-review.md, generated per the sections and filling requirements in assets/code-review.md.{output_root}/active/{slug}/probes/<probe-name>.json,
format per references/output-schema.md; the human report's facts section is derived from them.Historical records must be explicitly migrated to standalone JSON; do not infer from free text or auto-fill zeros, and do not read old embedded blocks at the same time.
The following items are done conditionally, not as mandatory steps each round:
lessons/ directory exists and something that actually happened this round is worth reusing, record it with the specific problem, cause, and handling:
lessons/pitfalls.mdlessons/bad-cases.mdlessons/arch-decisions.md{output_root}/active/{slug}/ to {output_root}/archive/{YYYY}/.Use when code has been written, before committing, or when merging a PR; also when the user says "review my code", "check before commit", "take a look at this change", "PR review", or asks for a stric
---name: code-reviewdescription: Use when code has been written, before committing, or when merging a PR; also when the user says "review my…---# skills/code-review/SKILL.mdVisão geral
Use when code has been written, before committing, or when merging a PR; also when the user says "review my code", "check before commit", "take a look at this change", "PR review", or asks for a strict review/merge gate.
Perguntas frequentes
Baixe skills/code-review/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/kyy-logs/code-review-skill.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.
paramsThe agent reads the instructions pointed to by the registry entry's file and references/output-schema.md, and executes according to the parameters.
Run in batches when concurrent slots are insufficient; if independent agents are unavailable, run serially and record the limitation.
Shared probe constraints (include in dispatch): an agent checks only its own probe, and does not re-run the whole process or dispatch further agents; the source version follows step 1. A finding must explain how this change introduced or triggered the issue; unrelated pre-existing issues are described separately and are not included in this round's finding list or counts.
Reuse the review scope and material confirmed and handed off by the main executor, together with context already read by this agent.
Read more as needed; merge independent read-only queries where possible, run dependent queries step by step, and preserve accurate line numbers and necessary context on first reads of source.
Limit local searches to the reviewed repository, explicitly provided related directories, and cache paths corresponding to dependency coordinates. Prefer rg, starting with changed files and known relevant directories and narrowing by file type; return only paths when locating files.
Expand the scope only for a specific evidence gap; avoid searching the whole repository with grep -r and then filtering the output. Record missing or unreadable evidence without expanding to the disk root or user directory, or repeating searches without a new lead.
Write only {output_root}/active/{slug}/probes/<probe-name>.json, not shared reports or metrics. Save identified but unresolved specific concerns in unverified_items under the output contract, rather than only in the return message.
Once checks are complete, first wait for any background tasks you started to finish, or stop tasks that are no longer needed and confirm they have exited. Then validate against the output contract, save the final JSON, and immediately return the handoff message. After saving, do not search, gather more evidence, or repeat explanations of findings.
Handoff: every probe must have JSON for this run. Record skip or error reasons according to the output contract; on execution errors, preserve findings already made and let the other probes continue. If an agent fails to start or returns no valid result, the main executor records error and the reason without reusing old results.
The return message only briefly states the JSON path, the actual checked scope, and necessary limitations, including specific evidence gaps; the main executor incorporates the relevant limitations into the final report.
Record duration when reliable timing is available; the sum of per-probe durations does not represent this round's wall-clock time.
test-coverage hands off the report path, target version, numerator/denominator, and percentage for valid coverage via its return message,
and the main executor reports them; --line accepts only diff line coverage:
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" coverage {slug} --line {diff-line-coverage}
Add --branch {branch-coverage} when a branch value exists, or report only that item. Omit unmeasured or inapplicable metrics without filling in 0; do not call it when neither value is valid. A single-item report updates only that item, and the script does not verify the statistical basis.
Aggregation: after all agents finish, the main executor runs the synchronization command. The script reads required from the registry and computes counts at each level from the probe JSON; do not rewrite raw results or hand-fill counts.
Do not deduplicate across probes yet; count by original finding ID, which may include duplicate records of the same root cause:
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" sync {slug} --probes
This step invalidates the previous batch's reconciliation state, and reconciliation is not recorded yet.
Reconciliation completeness check: Derive the final counts automatically from the probe JSON:
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" sync {slug}
required only controls whether that probe's failed/error execution status directly blocks; it does not change the finding closure requirement.
High findings from any probe enter reconciliation and still block merge until closed; medium/low are recorded in the report and excluded from the reconciliation total:
RECONCILE_TOTAL = total number of high findings
RECONCILE_DONE = number of those whose status is reconciled or false-positive
RECONCILE_PENDING = TOTAL - DONE
Run it even when there are no high findings, explicitly recording the zero result; do not substitute old counts or hand-filled numbers.
Fix format errors first; if records are missing, IDs are duplicated, or statuses conflict, synchronization fails, no counts are written, and the old result must not be used to pass.
When there are unresolved issues (RECONCILE_PENDING > 0), still deliver the report this round and list the blocking items; do not proceed toward merge.
After follow-up fix tasks complete, re-review the affected parts; see execution.max_retry in references/probes.yaml for the re-dispatch limit.
Compile the report:
Fill in the review scope, explanation, fix suggestions, and limitations per the template; do not embed raw JSON in the body; when acceptance criteria are provided, complete the item-by-item check-off first.
The script displays unverified_items as "Pending confirmation" in Findings without including them in severity counts; original records retain their IDs, evidence, and counts; when showing the number of distinct issues, group them by the same root cause and consequence and list the corresponding IDs, without raising severity due to duplication or substituting the displayed count for probe or reconciliation counts.
Run the following commands to generate the report's facts section from the JSON, validate the display, and obtain the final answer summary:
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" render-report {slug}
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" verify-report {slug}
bash "$CODE_REVIEW_SKILL_DIR/scripts/collect-metrics" summary {slug}
The scripts update only the code-review:probes / gate marker regions under Findings and Review Conclusion, preserving other body text and raw JSON. Rendering validates before an atomic update and can be repeated; it stops when markers are missing or duplicated. Validation covers IDs, locations, evidence, severity, status, and counts.
summary validates the report first and outputs the machine summary only when it is consistent. The high/medium/low counts, finding IDs, and blocking conclusion in the final answer must follow the summary; do not add unrecorded issues or omit recorded high findings. Deliver the report, blocking items, and unverified content to the user; you may add explanations and suggestions, but must not rewrite the automatic regions or overturn known blocking facts.
"No recorded blocking items" does not mean acceptance, coverage, tests, or CI have passed. Both gate-pass {slug} code-review and archive with review records validate the report first, then synchronize counts, and do not automatically fix a rewritten display.