aiskillstore/marketplace / skills/1gy/running-tests
running-tests
VerifiedRuns tests and handles failures. Triggered when: test execution, verification, test failures, CI checks.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.1 KB |
| skill-report.json | config | 18.5 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T15:05:45.104Z",
"slug": "1gy-running-tests",
"source_url": "https://github.com/1gy/jpp/tree/main/.claude/skills/running-tests",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "7e7edd292c653bd52b6d6c259bd8cadcbea0ce22c5c076e69bf81d19dfc993b8",
"tree_hash": "27ea9fcec5af5d968fafd8fa3126f3267761189d2b9c3c89ad1f47ffd5f6aa3d",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "running-tests",
"description": "Detects common project test commands, runs tests, reports failures, and guides fixes before re-running verification.",
"summary": "Run project tests, diagnose failures, and verify fixes with the right test command.",
"icon": "📦",
"version": "1.0.1",
"author": "1gy",
"license": "MIT",
"category": "coding",
"tags": [
"testing",
"test-automation",
"ci",
"debugging",
"verification"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
]
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The external-command findings are confirmed because the skill directs agents to run npm, cargo, just, make, pytest, and go test commands. These commands are appropriate for a testing skill but can execute repository-controlled code or scripts. I also found a workflow risk where the skill instructs agents to commit fixes without an explicit confirmation step.",
"remediation": [
{
"issue": "Project-controlled test command execution",
"suggestion": "Show the detected command and request confirmation before running tests in untrusted repositories or when scripts are project-defined.",
"severity": "medium"
},
{
"issue": "Autonomous commits after fixes",
"suggestion": "Require explicit user approval before creating commits, and separate diagnostic mode from fix-and-commit mode.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 16,
"line_end": 16
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
},
{
"file": "SKILL.md",
"line_start": 21,
"line_end": 21
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:16:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 16,
"line_end": 16,
"snippet": "| `package.json` | `npm test` |"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 17,
"line_end": 17,
"snippet": "| `Cargo.toml` | `cargo test` |"
},
{
"id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 18,
"line_end": 18,
"snippet": "| `justfile` | `just test` |"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 19,
"snippet": "| `Makefile` | `make test` |"
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "| `pyproject.toml` | `pytest` |"
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 21,
"line_end": 21,
"snippet": "| `go.mod` | `go test ./...` |"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:16:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "The skill instructs agents to run npm test when package.json exists. npm scripts are project-controlled and can execute arbitrary shell commands, so this is a real external command risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.84,
"reason": "The skill instructs agents to run cargo test when Cargo.toml exists. Cargo tests and build scripts execute repository-controlled code, which creates a real external command risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "The skill instructs agents to run just test when a justfile exists. just targets are shell command recipes controlled by the repository, so this is a real external command risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "The skill instructs agents to run make test when a Makefile exists. Make targets can execute arbitrary repository-defined shell commands, so this is a real external command risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.85,
"reason": "The skill instructs agents to run pytest when pyproject.toml exists. pytest imports and executes project test code and configuration, so this is a real external command risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"reason": "The skill instructs agents to run go test ./... when go.mod exists. Go tests compile and run repository-controlled test code, so this is a real external command risk.",
"severity": "medium"
}
],
"semantic_findings": [
{
"title": "Autonomous Commit Instruction",
"description": "SKILL.md tells the agent to \"Fix and commit\" for implementation and test bugs. This can modify repository history without an explicit user confirmation step.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 40
}
],
"confidence": 0.78,
"confidence_reasoning": "The instruction is explicit on lines 39-40, and Bash access could allow version-control commands. The file does not define a separate approval requirement before committing."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "| `package.json` | `npm test` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 16,
"line_end": 16
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The skill instructs agents to run npm test when package.json exists. npm scripts are project-controlled and can execute arbitrary shell commands, so this is a real external command risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `Cargo.toml` | `cargo test` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.84,
"confidence_reasoning": "The skill instructs agents to run cargo test when Cargo.toml exists. Cargo tests and build scripts execute repository-controlled code, which creates a real external command risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `justfile` | `just test` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "The skill instructs agents to run just test when a justfile exists. just targets are shell command recipes controlled by the repository, so this is a real external command risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `Makefile` | `make test` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.88,
"confidence_reasoning": "The skill instructs agents to run make test when a Makefile exists. Make targets can execute arbitrary repository-defined shell commands, so this is a real external command risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `pyproject.toml` | `pytest` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.85,
"confidence_reasoning": "The skill instructs agents to run pytest when pyproject.toml exists. pytest imports and executes project test code and configuration, so this is a real external command risk."
},
{
"title": "Ruby/shell backtick execution",
"description": "| `go.mod` | `go test ./...` |",
"locations": [
{
"file": "SKILL.md",
"line_start": 21,
"line_end": 21
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The skill instructs agents to run go test ./... when go.mod exists. Go tests compile and run repository-controlled test code, so this is a real external command risk."
},
{
"title": "Autonomous Commit Instruction",
"description": "SKILL.md tells the agent to \"Fix and commit\" for implementation and test bugs. This can modify repository history without an explicit user confirmation step.",
"locations": [
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 40
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.78,
"confidence_reasoning": "The instruction is explicit on lines 39-40, and Bash access could allow version-control commands. The file does not define a separate approval requirement before committing."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 52,
"audit_model": "codex",
"audited_at": "2026-07-04T15:05:45.104Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Run Project Tests and Diagnose Failures",
"value_statement": "Finding the right test command and interpreting failures slows verification. This skill detects common test setups, runs the test command, reports failures, and guides focused fixes.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"running tests",
"test automation",
"pytest",
"npm test",
"cargo test",
"CI checks",
"debug test failures"
],
"actual_capabilities": [
"Checks CLAUDE.md for a project-specific test command before auto-detection.",
"Detects package.json, Cargo.toml, justfile, Makefile, pyproject.toml, and go.mod test commands.",
"Runs the detected test command and reports pass or fail status.",
"Summarizes failed test names and error messages when available.",
"Analyzes failure causes and re-runs tests after a fix.",
"Produces a completion report with results, test count, fixes, and commits."
],
"limitations": [
"Test commands execute local project code and may need user approval in restricted environments.",
"Auto-detection covers only the file types listed in the skill.",
"It cannot guarantee that all tests are deterministic or available locally.",
"It may need user input when no command is documented or detected."
],
"use_cases": [
{
"title": "Verify Local Changes",
"description": "Run the correct project test command after editing code and get a concise failure summary.",
"target_user": "Software developer"
},
{
"title": "Triage CI Failures",
"description": "Reproduce failing checks locally, identify the likely cause, and confirm fixes before pushing.",
"target_user": "Repository maintainer"
},
{
"title": "Review Test Setup",
"description": "Check whether a project has a documented or detectable test command before assigning verification work.",
"target_user": "Team lead"
}
],
"prompt_templates": [
{
"title": "Run the Tests",
"scenario": "Beginner verification",
"prompt": "Use the running-tests skill to detect the project test command, run it, and report the result."
},
{
"title": "Explain Failures",
"scenario": "Failure triage",
"prompt": "Use the running-tests skill to run the test suite. If tests fail, list failed test names, key errors, and the likely cause."
},
{
"title": "Fix and Verify",
"scenario": "Guided repair",
"prompt": "Use the running-tests skill to run tests, fix failures that are caused by implementation bugs, and re-run tests until they pass."
},
{
"title": "Validate Before CI",
"scenario": "Advanced release check",
"prompt": "Use the running-tests skill to find the documented test command, compare it with auto-detection, run the best command, summarize risks, and confirm readiness for CI."
}
],
"output_examples": [
{
"input": "Run the tests for this repository.",
"output": "Detected a Node project and ran the documented test command. All tests passed. No fixes were applied."
},
{
"input": "The test suite is failing after my parser change.",
"output": [
"Result: failed.",
"Failed tests: parser handles empty input.",
"Likely cause: implementation bug in empty-token handling.",
"Next step: fix parser branch and re-run tests."
]
},
{
"input": "Check whether this change is ready for CI.",
"output": "The skill found a project-specific command, ran it, and confirmed the suite passed. The completion report included test count and no additional commits."
}
],
"best_practices": [
"Review the detected command before running it in an untrusted repository.",
"Prefer the command documented in CLAUDE.md or project docs when available.",
"Re-run the same command after each fix to confirm the result changed."
],
"anti_patterns": [
"Running test commands from unknown repositories without understanding their scripts.",
"Treating flaky failures as fixed without a clean re-run.",
"Committing fixes automatically when the user requested only a diagnostic report."
],
"faq": [
{
"question": "What test commands can it detect?",
"answer": "It detects npm, Cargo, just, Make, pytest, and Go test setups from common project files."
},
{
"question": "Does it run commands automatically?",
"answer": "The skill instructs the agent to run the detected command, so review commands in untrusted repositories."
},
{
"question": "Can it fix failing tests?",
"answer": "It can guide fixes for implementation or test bugs, then re-run tests to confirm the result."
},
{
"question": "What happens if no test command is found?",
"answer": "It asks the user for the correct command instead of guessing beyond its known patterns."
},
{
"question": "Does it work with CI systems?",
"answer": "It helps reproduce CI checks locally when the repository uses one of the detected test setups."
},
{
"question": "Is it safe for untrusted code?",
"answer": "Use caution. Test commands can execute repository scripts, dependencies, and build steps."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 52
}
]
}
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 |