aiskillstore/marketplace / skills/89jobrien/meta-cognitive-reasoning
meta-cognitive-reasoning
VerifiedMeta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention. Use when conducting reviews, making assessments, debugging complex issues, or any task requiring rigorous analytical reasoning. Prevents premature conclusions, assumption-based errors, and pattern matching without verification.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.3 KB |
| references/detailed-frameworks.md | markdown | 10.9 KB |
| references/domain-examples.md | markdown | 8.0 KB |
| skill-report.json | config | 42.3 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T12:59:30.078Z",
"slug": "89jobrien-meta-cognitive-reasoning",
"source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/meta-cognitive-reasoning",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "d920180d3f1fc356351bd184a2c439a204222f7a99ac2c243f9737ed10e6a3e6",
"tree_hash": "5faee4871ecc5829f8380667f97b1e6d11a02876c7dfc09b19375347d8c90c6b",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "meta-cognitive-reasoning",
"description": "Provides evidence-based reasoning workflows for reviews, debugging, assessments, and decisions. It helps users verify claims, test hypotheses, and prevent premature conclusions.",
"summary": "Guides evidence-based analysis with hypothesis testing, verification steps, and self-correction.",
"icon": "📦",
"version": "1.0.2",
"author": "Joseph OBrien",
"license": "MIT",
"tags": [
"reasoning",
"evidence-based analysis",
"hypothesis testing",
"code review",
"debugging"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"network",
"external_commands"
],
"category": "productivity"
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All static findings were adjudicated as false positives. The command alerts are Markdown examples, the URLs are PyPI registry examples, and the reconnaissance alerts are ordinary reasoning prose. No prompt injection, exfiltration intent, or executable payload was found.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "network",
"evidence": [
{
"file": "references/domain-examples.md",
"line_start": 139,
"line_end": 139
},
{
"file": "references/domain-examples.md",
"line_start": 349,
"line_end": 349
},
{
"file": "SKILL.md",
"line_start": 361,
"line_end": 361
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 60
},
{
"file": "SKILL.md",
"line_start": 60,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 89
},
{
"file": "SKILL.md",
"line_start": 89,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 122
},
{
"file": "SKILL.md",
"line_start": 122,
"line_end": 142
},
{
"file": "SKILL.md",
"line_start": 142,
"line_end": 158
},
{
"file": "SKILL.md",
"line_start": 158,
"line_end": 246
},
{
"file": "SKILL.md",
"line_start": 246,
"line_end": 248
},
{
"file": "SKILL.md",
"line_start": 248,
"line_end": 250
},
{
"file": "SKILL.md",
"line_start": 250,
"line_end": 252
},
{
"file": "SKILL.md",
"line_start": 252,
"line_end": 256
},
{
"file": "SKILL.md",
"line_start": 256,
"line_end": 258
},
{
"file": "SKILL.md",
"line_start": 258,
"line_end": 260
},
{
"file": "SKILL.md",
"line_start": 260,
"line_end": 262
},
{
"file": "SKILL.md",
"line_start": 262,
"line_end": 266
},
{
"file": "SKILL.md",
"line_start": 266,
"line_end": 268
},
{
"file": "SKILL.md",
"line_start": 268,
"line_end": 328
},
{
"file": "SKILL.md",
"line_start": 328,
"line_end": 338
},
{
"file": "SKILL.md",
"line_start": 338,
"line_end": 344
},
{
"file": "SKILL.md",
"line_start": 344,
"line_end": 348
},
{
"file": "SKILL.md",
"line_start": 348,
"line_end": 351
},
{
"file": "SKILL.md",
"line_start": 351,
"line_end": 355
},
{
"file": "SKILL.md",
"line_start": 355,
"line_end": 365
},
{
"file": "SKILL.md",
"line_start": 365,
"line_end": 377
},
{
"file": "SKILL.md",
"line_start": 377,
"line_end": 379
},
{
"file": "SKILL.md",
"line_start": 379,
"line_end": 383
},
{
"file": "SKILL.md",
"line_start": 383,
"line_end": 396
},
{
"file": "SKILL.md",
"line_start": 396,
"line_end": 419
},
{
"file": "SKILL.md",
"line_start": 419,
"line_end": 439
},
{
"file": "SKILL.md",
"line_start": 439,
"line_end": 488
},
{
"file": "SKILL.md",
"line_start": 488,
"line_end": 491
}
]
}
],
"static_findings": [
{
"id": "blocker:references/detailed-frameworks.md:60:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/detailed-frameworks.md",
"line_start": 60,
"line_end": 60,
"snippet": "2. **Consider Prevention**: Can we avoid creating the problem?"
},
{
"id": "blocker:references/detailed-frameworks.md:71:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/detailed-frameworks.md",
"line_start": 71,
"line_end": 71,
"snippet": "RIGHT: \"Smarter construction to avoid post-processing\""
},
{
"id": "blocker:references/detailed-frameworks.md:150:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/detailed-frameworks.md",
"line_start": 150,
"line_end": 150,
"snippet": "**Recognition Pattern:** Multiple valid proposals, no convergence, debate feels unresolvable"
},
{
"id": "blocker:references/detailed-frameworks.md:198:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/detailed-frameworks.md",
"line_start": 198,
"line_end": 198,
"snippet": "KEEP: \"Single-threaded to avoid race conditions\""
},
{
"id": "blocker:references/detailed-frameworks.md:390:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/detailed-frameworks.md",
"line_start": 390,
"line_end": 390,
"snippet": "- Anti-patterns and how to avoid them"
},
{
"id": "network:references/domain-examples.md:139:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/domain-examples.md",
"line_start": 139,
"line_end": 139,
"snippet": "source = { registry = \"https://pypi.org/simple\" }"
},
{
"id": "network:references/domain-examples.md:349:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/domain-examples.md",
"line_start": 349,
"line_end": 349,
"snippet": "source = { registry = \"https://pypi.org/simple\" }"
},
{
"id": "blocker:references/domain-examples.md:124:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/domain-examples.md",
"line_start": 124,
"line_end": 126,
"snippet": "**Situation:** Review flags `certifi==2025.10.5` as invalid"
},
{
"id": "blocker:references/domain-examples.md:151:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/domain-examples.md",
"line_start": 151,
"line_end": 151,
"snippet": "**Evidence:** Version EXISTS on PyPI with valid hash"
},
{
"id": "blocker:references/domain-examples.md:234:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/domain-examples.md",
"line_start": 234,
"line_end": 234,
"snippet": "**Assessment:** Useless - syntax already shows it's a class"
},
{
"id": "blocker:references/domain-examples.md:243:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/domain-examples.md",
"line_start": 243,
"line_end": 243,
"snippet": "**Assessment:** Useless - function name already says this"
},
{
"id": "blocker:references/domain-examples.md:267:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "references/domain-examples.md",
"line_start": 267,
"line_end": 267,
"snippet": "**Assessment:** Useless - path already provides this information"
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 55,
"line_end": 60,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 60,
"line_end": 82,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 82,
"line_end": 89,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 89,
"line_end": 116,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 116,
"line_end": 122,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 122,
"line_end": 142,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 142,
"line_end": 158,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 158,
"line_end": 246,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:246:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 246,
"line_end": 248,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 248,
"line_end": 250,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:250:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 250,
"line_end": 252,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:252:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 252,
"line_end": 256,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:256:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 256,
"line_end": 258,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:258:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 258,
"line_end": 260,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:260:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 260,
"line_end": 262,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:262:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 262,
"line_end": 266,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:266:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 266,
"line_end": 268,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:268:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 268,
"line_end": 328,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:328:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 328,
"line_end": 338,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:338:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 338,
"line_end": 344,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:344:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 344,
"line_end": 348,
"snippet": "**Situation**: Reviewing code that uses `certifi==2025.10.5`"
},
{
"id": "external_commands:SKILL.md:348:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 348,
"line_end": 351,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:351:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 351,
"line_end": 355,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:355:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 355,
"line_end": 365,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:365:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 365,
"line_end": 377,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:377:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 377,
"line_end": 379,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:379:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 379,
"line_end": 383,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:383:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 383,
"line_end": 396,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:396:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 396,
"line_end": 419,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:419:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 419,
"line_end": 439,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:439:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 439,
"line_end": 488,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:488:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 488,
"line_end": 491,
"snippet": "```"
},
{
"id": "network:SKILL.md:361:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 361,
"line_end": 361,
"snippet": "source = { registry = \"https://pypi.org/simple\" }"
}
],
"finding_verdicts": [
{
"id": "blocker:references/detailed-frameworks.md:60:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/detailed-frameworks.md:71:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/detailed-frameworks.md:150:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/detailed-frameworks.md:198:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/detailed-frameworks.md:390:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "network:references/domain-examples.md:139:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is package registry evidence inside a Markdown example, not executable networking code. No request logic, credentials, or data transmission is present."
},
{
"id": "network:references/domain-examples.md:349:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is package registry evidence inside a Markdown example, not executable networking code. No request logic, credentials, or data transmission is present."
},
{
"id": "blocker:references/domain-examples.md:124:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/domain-examples.md:151:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is reasoning guidance or an example about verification, not system reconnaissance. It does not collect host, user, process, or environment details."
},
{
"id": "blocker:references/domain-examples.md:234:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is a documentation-quality example, not network reconnaissance. It does not request host discovery, port scanning, or network enumeration."
},
{
"id": "blocker:references/domain-examples.md:243:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is a documentation-quality example, not network reconnaissance. It does not request host discovery, port scanning, or network enumeration."
},
{
"id": "blocker:references/domain-examples.md:267:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The cited text is a documentation-quality example, not network reconnaissance. It does not request host discovery, port scanning, or network enumeration."
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:246:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:248:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:250:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:252:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:256:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:258:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:260:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:262:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:266:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:268:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:328:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:338:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:344:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:348:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:351:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:355:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:365:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:377:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:379:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:383:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:396:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:419:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:439:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "external_commands:SKILL.md:488:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This matches Markdown code fences or inline example text, not Ruby backtick execution. The content is instructional prose and examples with no executable command path."
},
{
"id": "network:SKILL.md:361:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is package registry evidence inside a Markdown example, not executable networking code. No request logic, credentials, or data transmission is present."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 3,
"total_lines": 1260,
"audit_model": "codex",
"audited_at": "2026-07-05T12:59:30.078Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Improve Evidence-Based Reasoning",
"value_statement": "Complex reviews and decisions often fail when claims outrun evidence. This skill provides verification workflows, hypothesis testing, and self-correction prompts.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"meta-cognitive reasoning",
"evidence-based analysis",
"hypothesis testing",
"code review reasoning",
"debugging workflow",
"decision framework",
"verification checklist"
],
"actual_capabilities": [
"Prompts users to show evidence before making claims.",
"Guides multiple hypothesis generation before conclusions.",
"Adds temporal checks for package, API, and tool versions.",
"Structures self-correction when earlier analysis was wrong.",
"Provides review workflows for code, architecture, and documentation."
],
"limitations": [
"It does not verify facts without access to authoritative sources.",
"It cannot replace domain expertise for legal, medical, or financial decisions.",
"It may slow simple tasks that need quick execution.",
"It relies on the agent to follow the reasoning workflow."
],
"use_cases": [
{
"title": "Review Code Changes",
"description": "Engineers can require evidence for every finding before changing code.",
"target_user": "Software engineers"
},
{
"title": "Debug Complex Failures",
"description": "Support teams can compare possible causes before choosing a fix.",
"target_user": "Support engineers"
},
{
"title": "Assess Technical Decisions",
"description": "Technical leads can weigh assumptions, evidence, and tradeoffs before approving plans.",
"target_user": "Technical leads"
}
],
"prompt_templates": [
{
"title": "Verify a Claim",
"scenario": "Beginner",
"prompt": "Use meta-cognitive reasoning to verify this claim before accepting it: [claim]. Show evidence first, then interpret it."
},
{
"title": "Compare Hypotheses",
"scenario": "Intermediate",
"prompt": "Analyze this issue with at least three hypotheses: [issue]. Identify the evidence that would confirm or reject each one."
},
{
"title": "Review With Evidence",
"scenario": "Advanced",
"prompt": "Review this change for correctness and risk. Cite specific evidence for every finding, and separate observation from assessment."
},
{
"title": "Recover From an Error",
"scenario": "Expert",
"prompt": "Reassess my previous conclusion about [topic]. State the claim, check evidence, explain any error, and give the corrected action."
}
],
"output_examples": [
{
"input": "A reviewer says a new package version is invalid.",
"output": "The response verifies the registry or lockfile first, then states whether the version exists and whether action is needed."
},
{
"input": "Several tests fail with similar timeout messages.",
"output": "The response lists competing causes, names the evidence needed, and avoids blaming one dependency before checking timing and scope."
},
{
"input": "Documentation appears repetitive across files.",
"output": "The response checks whether duplication is copies, generated content, or linked files before suggesting consolidation."
}
],
"best_practices": [
"Use the skill before high-impact reviews, not after conclusions are formed.",
"Provide files, logs, or source links so evidence can be checked.",
"Ask for separate observation, mechanism, and assessment sections."
],
"anti_patterns": [
"Asking for a final verdict without providing evidence sources.",
"Using the skill to justify a decision already made.",
"Skipping verification because an issue matches a familiar pattern."
],
"faq": [
{
"question": "Does this skill execute commands automatically?",
"answer": "No. It describes verification workflows. The active agent decides which tools are available and appropriate."
},
{
"question": "Is it only for software tasks?",
"answer": "No. It also supports documentation, research, planning, and decision analysis."
},
{
"question": "Can it verify current package versions?",
"answer": "It can guide verification, but it needs access to current sources or lockfiles."
},
{
"question": "How does it help code reviews?",
"answer": "It asks for file-level evidence, competing explanations, and clear separation between facts and judgments."
},
{
"question": "Will it make simple tasks slower?",
"answer": "Sometimes. Use it when accuracy matters more than speed."
},
{
"question": "Does it replace expert judgment?",
"answer": "No. It structures reasoning, but experts still own domain-specific conclusions."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "detailed-frameworks.md",
"type": "file",
"path": "references/detailed-frameworks.md",
"lines": 399
},
{
"name": "domain-examples.md",
"type": "file",
"path": "references/domain-examples.md",
"lines": 358
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 503
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |