cursor/agent-compatibility/skills/check-agent-compatibility
agent-compatibility/skills/check-agent-compatibility/SKILL.md
--- name: check-agent-compatibility description: Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability. --- # Check agent compatibility ## Trigger Use when the user wants the full compatibility pass for a repo. ## Workflow 1. Launch `compatibility-scan-review` to run the CLI and capture the raw repository score and main issues. 2. Launch `startup-review` to verify whether the repo can actually be booted by an agent. 3. Launch `validat
$ install --global
skillsauthnpx skillsauth add cursor/plugins agent-compatibility/skills/check-agent-compatibilityInstall 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 16, 2026, 8:05 AM4.4s1 file scanned
SKILL.md
- name:
- check-agent-compatibility
- description:
- Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.
Check agent compatibility
Trigger
Use when the user wants the full compatibility pass for a repo.
Workflow
- Launch
compatibility-scan-reviewto run the CLI and capture the raw repository score and main issues. - Launch
startup-reviewto verify whether the repo can actually be booted by an agent. - Launch
validation-reviewto check whether an agent can verify a small change without an unnecessarily heavy loop. - Launch
docs-reliability-reviewto see whether the documented setup and run paths reliably match reality. - Use one subagent per task. Do not collapse these checks into one agent prompt.
- Compute an internal workflow score as the rounded average of:
Startup Compatibility ScoreValidation Loop ScoreDocs Reliability Score
- Compute an
Agent Compatibility Scoreas:round((deterministic_score * 0.7) + (workflow_score * 0.3))
- Synthesize the results into one final response.
When scoring internally, use specific non-round workflow scores for the behavioral checks rather than coarse round buckets. If startup, validation, or docs mostly work, treat them as good-with-friction rather than defaulting to the mid-60s. Do not create a low workflow score just because logs are noisy or the error text is rough.
Output
Respond in markdown, but keep it minimal. Do not use fenced code blocks.
Show only one score, as a level-two heading: ## Agent Compatibility Score: N/100. Do not show how it was computed, including weights, formula, deterministic score, workflow score, per-check scores, or arithmetic, unless the user explicitly asks for a breakdown.
Then a flat, prioritized list labeled Top fixes with one issue per line, each line starting with - .
If the deterministic scanner cannot be run because of tool environment issues, say that separately and do not treat it as a repo defect or penalize the repo. Fold deterministic and behavioral findings into that one list instead of separate sections. Focus on the fixes that would most improve real agent workflows. Do not include a separate summary unless the user asks for more detail.
Example shape:
Agent Compatibility Score: 72/100
Top fixes
- First issue
- Second issue
- Third issue
Related Skills
cursor/principle-encode-lessons-in-structure
development
VerifiedTrustedCommunity
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
1,824SKILL.mdUpdated May 24, 2026
cursor/principle-build-the-lever
tools
VerifiedTrustedCommunity
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
1,309SKILL.mdUpdated May 27, 2026
cursor/why
tools
VerifiedTrustedCommunity
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
1,309SKILL.mdUpdated May 24, 2026
cursor/unslop
data-ai
VerifiedTrustedCommunity
Cut AI tells from any writing. Must always apply.
1,309SKILL.mdUpdated May 24, 2026