{"slug":"qcr-benchbot","name":"Benchbot","description":"BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","tagline":"BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","category":"robotics-iot","tags":["robotics","automation","robotics-iot","3d-simulation","benchbot","benchmarking","evaluation","nvidia-isaac","real-robots","sim2real"],"author":{"name":"qcr","verified":false,"url":"https://github.com/qcr"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"qcr/benchbot","creatorName":"qcr","creatorUrl":"https://github.com/qcr","sourceUrl":"https://github.com/qcr/benchbot","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/qcr-benchbot#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":113,"forks":12,"downloads":0,"rating":0,"review_count":0,"quality_score":33.1},"quality":{"score":47,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"113","tone":"neutral"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-3-Clause","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"113 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"113 stars, 12 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add qcr/benchbot"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/qcr/benchbot"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"113 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"113 stars, 12 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add qcr/benchbot"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/qcr/benchbot"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"],"evidence":{"stars":"113 GitHub stars","repoActivity":"113 stars, 12 forks","lastPushed":"3y since push","license":"BSD-3-Clause","repository":"https://github.com/qcr/benchbot","install":"npx skills add qcr/benchbot","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add qcr/benchbot","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Shell","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","robotics","automation","3d-simulation","benchbot","benchmarking"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"safety":{"score":33,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","33/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","33/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Shell"],"install":{"ready":true,"command":"npx skills add qcr/benchbot","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":113,"starsLabel":"113","forks":12,"license":"BSD-3-Clause","qualityScore":47,"trustScore":69,"auditScore":61},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1055,"lastPushedAt":"2023-08-13T20:20:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"coverageTags":["Coding","Coding agents","robotics-iot","robotics","automation","3d-simulation","benchbot","benchmarking"]},"audit":{"audit_score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"decision":{"readiness_score":37,"readiness_label":"Needs manual review","headline":"Needs validation for Coding agents","role":"Needs validation","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"qcr-benchbot","name":"Benchbot","description":"BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","category":"robotics-iot","url":"https://www.openagentskill.com/skills/qcr-benchbot","repository":"https://github.com/qcr/benchbot","github_repo":"qcr/benchbot"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Shell","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add qcr/benchbot","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add qcr/benchbot"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Benchbot\" agent skill from https://github.com/qcr/benchbot. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Benchbot\" as a Claude Code skill from https://github.com/qcr/benchbot. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Benchbot\" from https://github.com/qcr/benchbot into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"}],"handoff_url":"https://www.openagentskill.com/api/skills/qcr-benchbot/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/qcr-benchbot"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"113 GitHub stars","repoActivity":"113 stars, 12 forks","lastPushed":"3y since push","license":"BSD-3-Clause","repository":"https://github.com/qcr/benchbot","install":"npx skills add qcr/benchbot","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","robotics","automation","3d-simulation","benchbot","benchmarking"],"known_risks":["Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":47,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Repository appears stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Benchbot in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 33/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"qcr-benchbot (Benchbot)","install_command":"npx skills add qcr/benchbot","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"qcr-benchbot","task":"Use Benchbot in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/qcr-benchbot","api":"https://www.openagentskill.com/api/agent/skills/qcr-benchbot","audit":"https://www.openagentskill.com/skills/qcr-benchbot/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=qcr-benchbot&task=Use%20Benchbot%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Benchbot%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Benchbot%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/qcr-benchbot/install","manifest":"https://www.openagentskill.com/api/registry/manifest/qcr-benchbot"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"qcr-benchbot","name":"Benchbot","description":"BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","category":"robotics-iot","url":"https://www.openagentskill.com/skills/qcr-benchbot","repository":"https://github.com/qcr/benchbot","github_repo":"qcr/benchbot"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Shell","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add qcr/benchbot","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add qcr/benchbot"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Benchbot\" agent skill from https://github.com/qcr/benchbot. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Benchbot\" as a Claude Code skill from https://github.com/qcr/benchbot. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Benchbot\" from https://github.com/qcr/benchbot into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots"}],"handoff_url":"https://www.openagentskill.com/api/skills/qcr-benchbot/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/qcr-benchbot"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"113 GitHub stars","repoActivity":"113 stars, 12 forks","lastPushed":"3y since push","license":"BSD-3-Clause","repository":"https://github.com/qcr/benchbot","install":"npx skills add qcr/benchbot","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","robotics","automation","3d-simulation","benchbot","benchmarking"],"known_risks":["Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":47,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Repository appears stale","Quality score needs review","Stars/forks activity: 113 stars, 12 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Benchbot in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 33/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"qcr-benchbot (Benchbot)","install_command":"npx skills add qcr/benchbot","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"qcr-benchbot","task":"Use Benchbot in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/qcr-benchbot","api":"https://www.openagentskill.com/api/agent/skills/qcr-benchbot","audit":"https://www.openagentskill.com/skills/qcr-benchbot/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=qcr-benchbot&task=Use%20Benchbot%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Benchbot%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Benchbot%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/qcr-benchbot/install","manifest":"https://www.openagentskill.com/api/registry/manifest/qcr-benchbot"}},"platforms":["Shell","Robotics","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add qcr/benchbot","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add qcr/benchbot","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Benchbot\" agent skill from https://github.com/qcr/benchbot. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Benchbot\" as a Claude Code skill from https://github.com/qcr/benchbot. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Benchbot\" from https://github.com/qcr/benchbot into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: BenchBot is a tool for seamlessly testing & evaluating semantic scene understanding tools in both realistic 3D simulation & on real robots","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/qcr/benchbot","github_repo":"qcr/benchbot","version":"1.0.0","license":"BSD-3-Clause","updated_at":"2026-06-23T03:01:19.981577+00:00","canonical_key":"qcr/benchbot","recommendation_reasons":["Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/qcr-benchbot","api":"https://www.openagentskill.com/api/agent/skills/qcr-benchbot","install_api":"https://www.openagentskill.com/api/skills/qcr-benchbot/install","audit":"https://www.openagentskill.com/skills/qcr-benchbot/audit","repository":"https://github.com/qcr/benchbot"},"meta":{"endpoint":"/api/registry/manifest/{slug}","canonical_agent_endpoint":"/api/agent/skills/qcr-benchbot","agent_friendly":true,"api_version":"1.0","generated_at":"2026-07-03T21:42:56.820Z"}}