Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 42541–42570 of 55581 skills

aas-agent-coordination-review-adjudication-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the multi-reviewer disagreement adjudication workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the reviewer disagreement ledger with evidence, owner, and next action. Success means every exception has a severity rationale, source, owner or explicit unassigned state, and a bounded next step; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-review-adjudication-recovery-readiness-drillManoj-11-Dahal/try-SkillsUse when the multi-reviewer disagreement adjudication workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the reviewer disagreement ledger with starting state, test, and observed outcome. Success means the dry-run or approved non-production drill meets the predeclared recovery target and leaves the baseline intact; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-review-adjudication-scenario-sensitivity-matrixManoj-11-Dahal/try-SkillsUse when the multi-reviewer disagreement adjudication team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the reviewer disagreement ledger with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-review-adjudication-scope-intake-gateManoj-11-Dahal/try-SkillsUse when a new multi-reviewer disagreement adjudication request needs a bounded work scope to produce a scoped intake card for the reviewer disagreement ledger. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-review-adjudication-source-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision about multi-reviewer disagreement adjudication depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the reviewer disagreement ledger. Success means each material claim has a source, version/date, location, and confidence note; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-review-adjudication-threshold-rule-checkManoj-11-Dahal/try-SkillsUse when a multi-reviewer disagreement adjudication decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the reviewer disagreement ledger showing source, units, boundary case, and outcome. Success means the rule source and effective date are verified, units and scope match, and borderline cases are flagged rather than auto-approved; disagreement is resolved by evidence or routed to an owner rather than averaged away. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-approval-evidence-packetManoj-11-Dahal/try-SkillsUse when a parallel worker file leases result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the file-ownership lease map containing options, evidence, risks, and open questions. Success means the decision owner, requested decision, source evidence, alternatives, uncertainty, and consequence of no action are all visible; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-change-impact-traceManoj-11-Dahal/try-SkillsUse when a version, rule, source, or stakeholder change may affect parallel worker file leases to produce a before/after change record and impact map for the file-ownership lease map. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-closeout-handoff-ledgerManoj-11-Dahal/try-SkillsUse when a parallel worker file leases work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the file-ownership lease map with status, evidence, owner, and retention state. Success means all deliverables, unresolved items, approvals, and next owners are recorded, and the stop reason is explicit; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-completeness-reconciliationManoj-11-Dahal/try-SkillsUse when the parallel worker file leases workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the file-ownership lease map with matched, unmatched, and unresolved rows. Success means counts and key fields reconcile or every variance is quantified, sourced, and left unresolved for an owner; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the parallel worker file leases workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the file-ownership lease map with evidence, owner, and next action. Success means every exception has a severity rationale, source, owner or explicit unassigned state, and a bounded next step; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-recovery-readiness-drillManoj-11-Dahal/try-SkillsUse when the parallel worker file leases workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the file-ownership lease map with starting state, test, and observed outcome. Success means the dry-run or approved non-production drill meets the predeclared recovery target and leaves the baseline intact; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-scenario-sensitivity-matrixManoj-11-Dahal/try-SkillsUse when the parallel worker file leases team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the file-ownership lease map with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-scope-intake-gateManoj-11-Dahal/try-SkillsUse when a new parallel worker file leases request needs a bounded work scope to produce a scoped intake card for the file-ownership lease map. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-source-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision about parallel worker file leases depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the file-ownership lease map. Success means each material claim has a source, version/date, location, and confidence note; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
aas-agent-coordination-work-lease-threshold-rule-checkManoj-11-Dahal/try-SkillsUse when a parallel worker file leases decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the file-ownership lease map showing source, units, boundary case, and outcome. Success means the rule source and effective date are verified, units and scope match, and borderline cases are flagged rather than auto-approved; no two workers edit the same protected path concurrently without explicit coordination. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.Stars: 3Updated Claude CodeCodexUnverifiedInstall
agent-architecture-auditManoj-11-Dahal/try-SkillsUse when an agent or LLM application behaves inconsistently, misses tool calls, regresses after wrapper changes, contaminates memory, or fails between model output and UI/API delivery to trace inputs through context, planning, tools, state, recovery, and rendering; isolate the failing stage with evidence. Trigger before broad prompt rewrites or blind retries.Stars: 3Updated Claude CodeCodexUnverifiedInstall
agentic-code-change-workflowManoj-11-Dahal/try-SkillsUse when an agent is asked to modify code, add a feature, fix a bug, or change configuration in a repository to establish scope, inspect project conventions, plan a small change, implement with relevant tests, review the diff, and verify before reporting. Trigger for multi-file edits, behavior changes, or production-impacting fixes; gate commits and deployments separately.Stars: 3Updated Claude CodeCodexUnverifiedInstall
agentic-loop-designManoj-11-Dahal/try-SkillsUse when a request spans multiple actions or tool calls and needs a reliable completion condition to design a bounded agent loop connecting a clear objective to an artifact, feedback signal, allowed actions, durable progress, and stopping rules. Trigger for autonomous, recurring, or multi-turn work; use a simpler single pass for small, reversible tasks.Stars: 3Updated Claude CodeCodexUnverifiedInstall
agentic-workflowsManoj-11-Dahal/try-SkillsUse when a task involves authoring an agent-enabled CI or repository workflow with explicit triggers, safe outputs, and review gates to identify the intended outcome, relevant inputs, platform or version, sensitive data, and permission boundary before acting. Use current primary documentation for version-sensitive behavior, produce a reviewable artifact, and verify it against stated criteria. Trigger for planning, implementation, evaluation, or troubleshooting in this focused domain; do not install or run third-party commands without authorization.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-capability-surface-mapManoj-11-Dahal/try-SkillsUse when the actual capability boundary of CrewAI orchestration needs to be distinguished from assumptions. Produce a capability map for CrewAI orchestration covering the requested behavior, verified support, exclusions, and unknowns. Success means each in-scope capability is tied to local configuration, a version-matched authoritative reference, or an observed non-production result, and all unknowns remain explicit. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-change-impact-assessmentManoj-11-Dahal/try-SkillsUse when a proposed CrewAI orchestration version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for CrewAI orchestration with baseline, affected dependencies, validation needs, and recovery boundary. Success means affected dependencies and compatibility assumptions are evidenced, unknown consumers are named as unknown, and no migration or rollout is implied. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-failure-triage-recordManoj-11-Dahal/try-SkillsUse when a reproducible CrewAI orchestration symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for CrewAI orchestration with symptom, environment, evidence, hypothesis, and next safe check. Success means the diagnosis distinguishes observation from inference, each proposed check is reversible and scoped, and unresolved causes remain open. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-input-output-contractManoj-11-Dahal/try-SkillsUse when the accepted inputs or produced outputs for CrewAI orchestration need a checkable boundary. Produce an input/output contract for CrewAI orchestration with types, required fields, exclusions, and representative approved fixtures. Success means the contract names its source and version, boundary cases are visible, and no private or unapproved payload is needed to explain the result. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-integration-parity-traceManoj-11-Dahal/try-SkillsUse when CrewAI orchestration exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for CrewAI orchestration showing source, transformation, destination, and observed result. Success means each material field or state transition has a traceable mapping and observed mismatches are separated from assumptions. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-performance-envelopeManoj-11-Dahal/try-SkillsUse when CrewAI orchestration must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for CrewAI orchestration with test conditions, baseline, observed range, and limitations. Success means conditions and measurements are reproducible, the comparison uses the stated budget, and limitations or resource costs are visible. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-permission-boundary-reviewManoj-11-Dahal/try-SkillsUse when CrewAI orchestration may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for CrewAI orchestration showing identity, requested capability, data scope, and approval gate. Success means every sensitive capability has a named authorization boundary, unnecessary data and privileges are called out, and no action is treated as approved by implication. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-release-handoff-recordManoj-11-Dahal/try-SkillsUse when a CrewAI orchestration review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for CrewAI orchestration with version, evidence, open issues, approval state, and safe next step. Success means the receiver can distinguish verified facts, proposals, approvals, and unknowns, and no publication, deployment, write, or contact is claimed unless independently confirmed. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-reproducibility-fixture-planManoj-11-Dahal/try-SkillsUse when a CrewAI orchestration result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for CrewAI orchestration defining fixture identity, environment, expected observations, and cleanup boundary. Success means another reviewer can identify the fixture and environment, distinguish expected from observed behavior, and repeat the check without an unapproved external effect. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall
crewai-version-compatibilityManoj-11-Dahal/try-SkillsUse when a CrewAI orchestration integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for CrewAI orchestration with exact versions, supported combinations, and open questions. Success means the tested version tuple is explicit, each compatibility claim has a dated source or local result, and unsupported combinations are not presented as working. The review is bounded to agent role boundaries, task transitions, tool scope, and completion evidence. Use only authorized local evidence, version-matched authoritative references, and synthetic or approved fixtures. Do not install tools, expose credentials, change live systems, publish, contact people, or make irreversible decisions without explicit approval; stop when authority or recovery is unclear.Stars: 3Updated Claude CodeCodexUnverifiedInstall