skills/deepsource/SKILL.md
Retrieve code review results from DeepSource — issues, vulnerabilities, report cards, and analysis runs. Use when asked about code quality, security findings, dependency CVEs, coverage metrics, or analysis status.
npx skillsauth add deepsourcecorp/skills deepsourceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
deepsource auth login
deepsource issues --output json
Narrow by severity, category, or path:
deepsource issues --severity critical,major --output json
deepsource issues --category security,bug-risk --output json
deepsource issues --path src/auth --output json
deepsource issues --severity critical --category security --limit 20 --output json
Scope to a PR or branch:
deepsource issues --pr 42 --output json
deepsource issues --default-branch --output json
deepsource report-card --output json
Returns grades (A-F) and scores for security, reliability, complexity, hygiene, coverage, and an aggregate.
Scope to a PR or commit:
deepsource report-card --pr 42 --output json
deepsource report-card --commit abc123 --output json
deepsource vulnerabilities --output json
Filter by severity:
deepsource vulnerabilities --severity critical,high --output json
Scope to a PR or branch:
deepsource vulnerabilities --pr 42 --output json
deepsource vulnerabilities --default-branch --output json
deepsource repo status --output json
deepsource runs --output json
deepsource runs --commit abc123 --output json
repo status shows activation and configured analyzers. runs shows recent analysis run history.
--repo when outside the repo or targeting a different one. Use scope flags (--pr, --commit, --default-branch) to override the auto-detected branch.--output json for machine-readable output.--repo provider/owner/name — providers: gh, gl, bb, ads.--commit, --pr, and --default-branch cannot be combined. Omit all three to use auto-detection.Full CLI docs: https://deepsource.com/docs/developers/cli/installation
Run deepsource <command> --help for detailed flag reference.
development
Scan code for security vulnerabilities, leaked secrets, and dependency issues using the Sentinel API (sentinel.deepsource.com), and auto-fix detected issues. Use this skill when asked to: (1) Scan or analyze a repository or code for security issues, secrets, or vulnerabilities using Sentinel, (2) Upload/sync a local git repository to Sentinel for analysis, (3) Run Sentinel on code changes, pull requests, or patches, (4) Apply auto-fixes from Sentinel analysis results. Requires a Sentinel API key (environment variable SENTINEL_API_KEY).
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.