linzhe001/deep-check
.agents/skills/deep-check/SKILL.md
Codex wrapper for WF3 deep-check. Use when the user wants a skeptical Go/No-Go review of the technical spec before heavy implementation starts.
$ install --global
skillsauthnpx skillsauth add linzhe001/Harness-Research deep-checkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 17, 2026, 1:58 AM19.4s3 files scanned
SKILL.md
- name:
- deep-check
- description:
- Codex wrapper for WF3 deep-check. Use when the user wants a skeptical Go/No-Go review of the technical spec before heavy implementation starts.
Deep Check
References
Read these first:
../../../.agents/references/workflow-guide.md../../../.agents/references/language-policy.md./references/sanity-check.md../../../PROJECT_STATE.json
When To Use
Use this skill for WF3 when the user wants a skeptical gate review before data engineering or coding.
Required Work
- Read
docs/Technical_Spec.mdand extract assumptions, chosen path, and target outcomes. - Use web research to look for negative evidence, limitations, and failure reports.
- Build the canonical risk matrix with probability, impact, and mitigation.
- Estimate upper, expected, and lower performance bounds.
- Write
docs/Sanity_Check_Log.mdusing the canonical template and one of:GOCONDITIONAL GONO-GO
Output Rules
- Keep the
context_summary. - Include failure-case search results, theoretical analysis, performance estimation, risk matrix, and recommendation.
- Treat template wording as structure-only; localize headings and narrative text according to
../../../.agents/references/language-policy.mdunless a field is explicitly English-only.
Codex Adaptation
- Treat natural-language requests as the canonical
$deep-checkinvocation. - Preserve the critical-gate semantics from the canonical workflow.
- Ask the user directly only if the technical spec path or design target is unclear.
Execution Rule
Follow the local review logic, template, and language policy rather than collapsing this stage into a generic prose review.
Related Skills
linzhe001/validate-run
development
VerifiedTrustedCommunity
WF7.5 training pipeline validation. Before entering WF8 iteration, first use Codex to review code for baseline equivalence, then run a 100-step smoke test to verify end-to-end pipeline functionality.
1SKILL.mdUpdated Apr 17, 2026
linzhe001/survey-idea
business
VerifiedTrustedCommunity
WF1 Inspiration survey and gap analysis. Takes the user's research idea, performs literature search, gap analysis, competitor analysis, and feasibility scoring, then outputs Feasibility_Report.md. Use when the user has a new CV research idea that needs a feasibility assessment.
1SKILL.mdUpdated Apr 17, 2026
linzhe001/release
tools
VerifiedTrustedCommunity
WF10 Submission/Release Tool. Multi-scene training, result packaging, filename validation, dry-run submission checks. Used after ablation experiments are complete and before competition submission.
1SKILL.mdUpdated Apr 17, 2026
linzhe001/refine-arch
development
VerifiedTrustedCommunity
WF2 Architecture refinement and MVP design. Reads the feasibility report, analyzes the base codebase architecture, designs plug-and-play new modules, defines the MVP, provides A/B/C alternative plans, and outputs Technical_Spec.md. Use when a research idea needs to be translated into a concrete technical architecture design.
1SKILL.mdUpdated Apr 17, 2026