All authors
Claude Skills by Manoj-11-Dahal
github.com/Manoj-11-Dahal15,860 skills0 installs0 views
- Agent Telemetry Tool Event Schema Recovery Readiness DrillUse when the agent tool-event schemas workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the tool-event contract 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; events distinguish requested, attempted, completed, failed, and unverified actions. Use configured search, fetch, read, browser, test, and write cap...Votes: 0GitHub stars: 2
- Agent Telemetry Tool Event Schema Scenario Sensitivity MatrixUse when the agent tool-event schemas team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the tool-event contract with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; events distinguish requested, attempted, completed, failed, and unverified actions. Use configured search, fetch, read, browser, test, and write capabilities only wh...Votes: 0GitHub stars: 2
- Agent Telemetry Tool Event Schema Scope Intake GateUse when a new agent tool-event schemas request needs a bounded work scope to produce a scoped intake card for the tool-event contract. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; events distinguish requested, attempted, completed, failed, and unverified actions. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passe...Votes: 0GitHub stars: 2
- Agent Telemetry Tool Event Schema Source Provenance LedgerUse when a decision about agent tool-event schemas depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the tool-event contract. Success means each material claim has a source, version/date, location, and confidence note; events distinguish requested, attempted, completed, failed, and unverified actions. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refin...Votes: 0GitHub stars: 2
- Agent Telemetry Tool Event Schema Threshold Rule CheckUse when a agent tool-event schemas decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the tool-event contract 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; events distinguish requested, attempted, completed, failed, and unverified actions. Use configured search, fetch, read, browser, test, and w...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Approval Evidence PacketUse when a agent trace redaction and retention result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, rea...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Change Impact TraceUse when a version, rule, source, or stakeholder change may affect agent trace redaction and retention to produce a before/after change record and impact map for the trace data-minimization review. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and write capabilities only when ...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Closeout Handoff LedgerUse when a agent trace redaction and retention work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and w...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Completeness ReconciliationUse when the agent trace redaction and retention workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browse...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Exception Triage QueueUse when the agent trace redaction and retention workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and ...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Recovery Readiness DrillUse when the agent trace redaction and retention workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser,...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Scenario Sensitivity MatrixUse when the agent trace redaction and retention team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the trace data-minimization review with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and write ...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Scope Intake GateUse when a new agent trace redaction and retention request needs a bounded work scope to produce a scoped intake card for the trace data-minimization review. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Source Provenance LedgerUse when a decision about agent trace redaction and retention depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the trace data-minimization review. Success means each material claim has a source, version/date, location, and confidence note; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record e...Votes: 0GitHub stars: 2
- Agent Telemetry Trace Redaction Threshold Rule CheckUse when a agent trace redaction and retention decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the trace data-minimization review 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; unnecessary payload fields are removed or justified and retention matches policy. Use configured search, fetch, read, ...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Approval Evidence PacketUse when a agent usage and cost attribution result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured se...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Change Impact TraceUse when a version, rule, source, or stakeholder change may affect agent usage and cost attribution to produce a before/after change record and impact map for the usage reconciliation sheet. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, browser, test, and write capabil...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Closeout Handoff LedgerUse when a agent usage and cost attribution work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, brow...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Completeness ReconciliationUse when the agent usage and cost attribution workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fet...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Exception Triage QueueUse when the agent usage and cost attribution workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, bro...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Recovery Readiness DrillUse when the agent usage and cost attribution workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Scenario Sensitivity MatrixUse when the agent usage and cost attribution team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the usage reconciliation sheet with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, browser, ...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Scope Intake GateUse when a new agent usage and cost attribution request needs a bounded work scope to produce a scoped intake card for the usage reconciliation sheet. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, lim...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Source Provenance LedgerUse when a decision about agent usage and cost attribution depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the usage reconciliation sheet. Success means each material claim has a source, version/date, location, and confidence note; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and auth...Votes: 0GitHub stars: 2
- Agent Telemetry Usage Metering Threshold Rule CheckUse when a agent usage and cost attribution decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the usage reconciliation sheet 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; totals reconcile within documented precision and sensitive payloads are not needed for cost attribution. Use configured searc...Votes: 0GitHub stars: 2
- Attempt Diff Information Gain ReviewUse when an agent has produced several similar attempts without progress to create or update an attempt comparison with changed premise, tool, input, and observed evidence. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: at least one justified change increases information or resolves an uncertainty. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally vis...Votes: 0GitHub stars: 2
- Edge Inference Latency BudgetUse when a task involves allocating end-to-end latency for an edge AI inference workflow to define the target, lifecycle stage, controlling artifact, authoritative evidence, version or operating conditions, sensitivity, and approval boundary before applying the method. Separate observed facts from assumptions and model output. Verify the result with appropriate independent checks, preserve provenance, and report uncertainty and limitations. Do not perform production, financial, device-control...Votes: 0GitHub stars: 2
- Evaluation Harness DesignUse when measuring whether an agent, prompt, tool pipeline, or skill is reliable across repeated cases to define representative tasks, reference outcomes, metrics, graders, calibration checks, regression thresholds, and a reproducible report before tuning. Trigger before release, after model or prompt changes, or when subjective impressions are driving quality decisions.Votes: 0GitHub stars: 2
- Evidence Certainty GradingUse when a task involves summarizing certainty across a body of evidence with explicit attention to design, bias, consistency, and applicability to identify the research or operational question, target population or system, relevant version, sensitive data, and approval boundary before acting. Use current primary sources, produce a traceable artifact, and verify it against explicit criteria. Trigger for planning, analysis, review, or troubleshooting in this focused domain; do not execute exte...Votes: 0GitHub stars: 2
- Evidence Coverage Matrix Gap ClosureUse when a research brief has multiple criteria but only an unstructured source pile to create or update a criterion-to-source matrix with pass, partial, missing, or contradicted states. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every material criterion has evidence or a clear unresolved status. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally v...Votes: 0GitHub stars: 2
- Gpu Model Serving Cost ReviewUse when a task involves reviewing GPU model-serving capacity, latency, utilization, and cost tradeoffs for a defined workload to identify the research or operational question, target population or system, relevant version, sensitive data, and approval boundary before acting. Use current primary sources, produce a traceable artifact, and verify it against explicit criteria. Trigger for planning, analysis, review, or troubleshooting in this focused domain; do not execute external writes or cli...Votes: 0GitHub stars: 2
- Microsoft Foundry Agent ObservabilityUse when a task involves instrumenting and evaluating hosted agents on Microsoft Foundry with trace, quality, safety, and cost visibility 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 ...Votes: 0GitHub stars: 2
- Per Iteration Tool Budget Before DispatchUse when an agent is about to dispatch another tool call in a repeated workflow to create or update a budget record with projected call, time, and external cost. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the next action fits within the remaining approved budget or stops cleanly. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irrever...Votes: 0GitHub stars: 2
- Progress Ledger Acceptance Claim Closure CheckUse when a long task has multiple completed, partial, or blocked steps to create or update a ledger joining acceptance IDs, evidence paths, status, and owner. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: no item is called complete without a current artifact or reproducible observation. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irr...Votes: 0GitHub stars: 2
- Same Error Fingerprint Stop Rule EnforcerUse when two or more loop iterations fail with apparently unchanged feedback to create or update an attempt ledger with normalized failure fingerprints and stop reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: a changed hypothesis produces new evidence or repeated failure triggers escalation. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally vis...Votes: 0GitHub stars: 2
- Scheduled Agent Noop Threshold ReviewUse when a recurring workflow runs even when no actionable change may exist to create or update a decision record with trigger evidence, confidence, and no-op reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the workflow acts only when the agreed evidence threshold is met. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible...Votes: 0GitHub stars: 2
- Skill Change To Evaluation Impact MapUse when a skill update changes a workflow step, guardrail, example, or routing description to create or update a changed-instruction-to-eval-case map. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every changed obligation has at least one affected scenario and unchanged obligations retain coverage. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally v...Votes: 0GitHub stars: 2
- Skill Trigger Confusable Pair TestUse when a trigger description may be too broad or collide with another skill to create or update a positive, negative, and boundary-case activation test set. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: positive cases route to the skill and confusable negatives do not. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible writes.Votes: 0GitHub stars: 2
- Skill Workflow Exit Evidence Contract TestUse when a procedure ends with “done” but lacks a checkable exit condition to create or update an exit-contract table mapping each outcome to evidence and stop reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every success state has a concrete observation and every failure state has a bounded route. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externa...Votes: 0GitHub stars: 2
- Success Signal Repeatability Cross Run CheckUse when a task completion depends on a nondeterministic metric or one-off visual check to create or update a repeated-result table with environment and variance. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the signal is reproducible within an agreed tolerance or marked unstable. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irrevers...Votes: 0GitHub stars: 2
- Verification And StoppingUse when an agent must prove that a deliverable meets an objective before claiming completion to turn goals into observable checks, choose independent evidence, define pass and fail thresholds, and state explicit stop conditions. Trigger for code, research, data, documents, and long-running agent work where plausible output is not sufficient evidence.Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Build Configuration RunbookUse when an authorized implementation needs repeatable steps and a visible change boundary for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means the prepared result is reproducible, reviewable, an...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Design BlueprintUse when a solution needs a coherent structure before implementation or production for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means interfaces, dependencies, constraints, and review points are testable befo...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Failure Triage And RecoveryUse when an unexpected result needs diagnosis without widening risk or losing evidence for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means the failure is bounded by observations, one...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Option Comparison MatrixUse when several tools, designs, methods, or workflows could satisfy the same need for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means options are compared on user-approved criteria with unce...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Requirements And Decision BriefUse when a request must be converted into testable constraints and an owned decision for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means requirements have priorities, evidence, owners, and m...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Scope And Baseline RecordUse when the work needs a verified goal, authorized boundary, and starting state for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means the owner, constraints, baseline, and acceptance signal are explicit. Use ...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Security Rights And Safety ReviewUse when the workflow could affect people, systems, confidential data, intellectual property, or physical outcomes for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a scoped risk-and-control review with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means the review names relevant hazards, ...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Source Research And Provenance LedgerUse when a decision depends on current, source-grounded information for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means material claims are linked to current primary sources with dates and limitations. Use per...Votes: 0GitHub stars: 2
- Mcplab Authorization Scoping Client Compatibility Verification And Acceptance Test PlanUse when a result must be checked against explicit behavior, safety, or quality conditions for Model Context Protocol servers and integrations: authorization scoping for client compatibility. Produce a risk-weighted verification plan with saved evidence with scope, versions, decisions, and evidence for this task-specific gate: Verify the target host/client protocol version and negotiated capabilities with the actual supported client matrix. Success means each critical requirement maps to a re...Votes: 0GitHub stars: 2