Explore skills
Showing 56731–56760 of 71536 skills
Use when several tools, designs, methods, or workflows could satisfy the same need for Human-governed agent improvement: evaluator integrity for parallel-work handoffs. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Provide the reviewer with the exact proposal, rationale, baseline, tests, risk, and rollback instead of delegating silent changes. Success means options are compared on user-approved criteria with uncertainty and trade-offs shown. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for parallel-work handoffs. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Provide the reviewer with the exact proposal, rationale, baseline, tests, risk, and rollback instead of delegating silent changes. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for parallel-work handoffs. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Provide the reviewer with the exact proposal, rationale, baseline, tests, risk, and rollback instead of delegating silent changes. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for parallel-work handoffs. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Provide the reviewer with the exact proposal, rationale, baseline, tests, risk, and rollback instead of delegating silent changes. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a result must be checked against explicit behavior, safety, or quality conditions for Human-governed agent improvement: evaluator integrity for parallel-work handoffs. Produce a risk-weighted verification plan with saved evidence with scope, versions, decisions, and evidence for this task-specific gate: Provide the reviewer with the exact proposal, rationale, baseline, tests, risk, and rollback instead of delegating silent changes. Success means each critical requirement maps to a reproducible check and a truthful pass, fail, or unknown status. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for partial completion. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a solution needs a coherent structure before implementation or production for Human-governed agent improvement: evaluator integrity for partial completion. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means interfaces, dependencies, constraints, and review points are testable before build. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for partial completion. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when several tools, designs, methods, or workflows could satisfy the same need for Human-governed agent improvement: evaluator integrity for partial completion. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means options are compared on user-approved criteria with uncertainty and trade-offs shown. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for partial completion. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for partial completion. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the workflow could affect people, systems, confidential data, intellectual property, or physical outcomes for Human-governed agent improvement: evaluator integrity for partial completion. Produce a scoped risk-and-control review with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means the review names relevant hazards, permissions, controls, evidence gaps, and approval owners. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for partial completion. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a result must be checked against explicit behavior, safety, or quality conditions for Human-governed agent improvement: evaluator integrity for partial completion. Produce a risk-weighted verification plan with saved evidence with scope, versions, decisions, and evidence for this task-specific gate: Mark update steps as proposed, evaluated, approved, or applied; only an authorized human may advance the approval state. Success means each critical requirement maps to a reproducible check and a truthful pass, fail, or unknown status. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a solution needs a coherent structure before implementation or production for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means interfaces, dependencies, constraints, and review points are testable before build. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a measured result or recurring failure suggests a change worth testing and handing to an owner for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a versioned improvement proposal and handoff packet with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the proposed change is compared with a baseline, regression risk is visible, and the owner can decide next steps. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when several tools, designs, methods, or workflows could satisfy the same need for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means options are compared on user-approved criteria with uncertainty and trade-offs shown. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the workflow could affect people, systems, confidential data, intellectual property, or physical outcomes for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a scoped risk-and-control review with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means the review names relevant hazards, permissions, controls, evidence gaps, and approval owners. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodex- selfupdate-evaluator-integrity-strict-tool-call-budgets-source-research-and-provenance-ledgerVerified
Use when a decision depends on current, source-grounded information for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means material claims are linked to current primary sources with dates and limitations. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodex - selfupdate-evaluator-integrity-strict-tool-call-budgets-verification-and-acceptance-test-planVerified
Use when a result must be checked against explicit behavior, safety, or quality conditions for Human-governed agent improvement: evaluator integrity for strict tool-call budgets. Produce a risk-weighted verification plan with saved evidence with scope, versions, decisions, and evidence for this task-specific gate: Limit the experiment to a fixed budget and stop at the predeclared sample or compute ceiling. Success means each critical requirement maps to a reproducible check and a truthful pass, fail, or unknown status. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodex Use when an authorized implementation needs repeatable steps and a visible change boundary for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means the prepared result is reproducible, reviewable, and within the approved scope. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a solution needs a coherent structure before implementation or production for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means interfaces, dependencies, constraints, and review points are testable before build. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when an unexpected result needs diagnosis without widening risk or losing evidence for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means the failure is bounded by observations, one testable hypothesis, and a safe next step. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when several tools, designs, methods, or workflows could satisfy the same need for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means options are compared on user-approved criteria with uncertainty and trade-offs shown. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when a request must be converted into testable constraints and an owned decision for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means requirements have priorities, evidence, owners, and measurable acceptance conditions. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodexUse when the work needs a verified goal, authorized boundary, and starting state for Human-governed agent improvement: evaluator integrity for uncertain user intent. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Flag ambiguous feedback as a hypothesis, not a training label; request owner review before treating it as a durable preference. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use permissioned inputs, preserve a baseline, check current primary guidance, and stop when evidence, authority, rights, or safe recovery is unclear.
Manoj-11-Dahal/try-Skills
Stars: 3Claude CodeCodex