All authors
Claude Skills by Manoj-11-Dahal
github.com/Manoj-11-Dahal15,860 skills0 installs0 views
- Tavily Web Version CompatibilityUse when a Tavily web retrieval integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for Tavily web retrieval 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 query scope, source identity, extraction bound...Votes: 0GitHub stars: 2
- Tool Argument Schema To Call PreflightUse when an agent is about to call a structured tool or API to create or update a preflight record of schema, target, arguments, and expected effect. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: arguments validate locally and the target and effect match the user’s request. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible wri...Votes: 0GitHub stars: 2
- Tool Execution And ObservationUse when an agent must act through shell, browser, APIs, files, or MCP tools to select least-risk tools, distinguish reads from writes, capture outputs as observations, verify the resulting state, and avoid blind retries. Trigger whenever completion depends on external or local tool effects, especially when commands can change data or cross trust boundaries.Votes: 0GitHub stars: 2
- Tool Response Shape Change Fallback TestUse when a previously stable tool response fails parsing or loses expected values to create or update a response-contract diff and compatibility test result. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the new shape is handled explicitly or the workflow fails closed with a useful report. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or ...Votes: 0GitHub stars: 2
- Tool Timeout Retry Jitter Budget CheckUse when a read-only API or browser call times out under a known transient condition to create or update a retry trace with attempt count, wait schedule, and terminal reason. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the call succeeds or exits within the agreed time and call budget without duplicate side effects. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval b...Votes: 0GitHub stars: 2
- Tool Unavailable Capability Substitution PlanUse when the workflow’s expected search, browser, read, write, or test capability is unavailable to create or update a capability substitution table with permission and evidence impact. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the replacement preserves the required operation or the task stops with a clear limitation. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain appro...Votes: 0GitHub stars: 2
- Transformers Js Capability Surface MapUse when the actual capability boundary of Transformers.js runtime needs to be distinguished from assumptions. Produce a capability map for Transformers.js runtime 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 browser/server runtime, model artifact compat...Votes: 0GitHub stars: 2
- Transformers Js Change Impact AssessmentUse when a proposed Transformers.js runtime version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for Transformers.js runtime 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 browser/server runtime, model artifact comp...Votes: 0GitHub stars: 2
- Transformers Js Failure Triage RecordUse when a reproducible Transformers.js runtime symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for Transformers.js runtime 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 browser/server runtime, model artifact compatibility, preprocessing, and output i...Votes: 0GitHub stars: 2
- Transformers Js Input Output ContractUse when the accepted inputs or produced outputs for Transformers.js runtime need a checkable boundary. Produce an input/output contract for Transformers.js runtime 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 browser/server runtime, model artifact compatibility, preprocessing, and ...Votes: 0GitHub stars: 2
- Transformers Js Integration Parity TraceUse when Transformers.js runtime exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for Transformers.js runtime 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 browser/server runtime, model artifact compatibility, preprocessing, and output integrity....Votes: 0GitHub stars: 2
- Transformers Js Performance EnvelopeUse when Transformers.js runtime must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for Transformers.js runtime 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 browser/server runtime, model artifact compatibility, preproces...Votes: 0GitHub stars: 2
- Transformers Js Permission Boundary ReviewUse when Transformers.js runtime may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for Transformers.js runtime 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 browser/server runtime, model artifact compatibility...Votes: 0GitHub stars: 2
- Transformers Js Release Handoff RecordUse when a Transformers.js runtime review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for Transformers.js runtime 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 browser/server runtime, model artifact compat...Votes: 0GitHub stars: 2
- Transformers Js Reproducibility Fixture PlanUse when a Transformers.js runtime result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for Transformers.js runtime 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 browser/server ru...Votes: 0GitHub stars: 2
- Transformers Js Version CompatibilityUse when a Transformers.js runtime integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for Transformers.js runtime 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 browser/server runtime, model artifact c...Votes: 0GitHub stars: 2
- Vllm Server Capability Surface MapUse when the actual capability boundary of vLLM inference serving needs to be distinguished from assumptions. Produce a capability map for vLLM inference serving 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 model artifact identity, runtime settings, acce...Votes: 0GitHub stars: 2
- Vllm Server Change Impact AssessmentUse when a proposed vLLM inference serving version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for vLLM inference serving 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 model artifact identity, runtime settings, ac...Votes: 0GitHub stars: 2
- Vllm Server Failure Triage RecordUse when a reproducible vLLM inference serving symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for vLLM inference serving 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 model artifact identity, runtime settings, accelerator budget, and request/response...Votes: 0GitHub stars: 2
- Vllm Server Input Output ContractUse when the accepted inputs or produced outputs for vLLM inference serving need a checkable boundary. Produce an input/output contract for vLLM inference serving 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 model artifact identity, runtime settings, accelerator budget, and request/...Votes: 0GitHub stars: 2
- Vllm Server Integration Parity TraceUse when vLLM inference serving exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for vLLM inference serving 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 model artifact identity, runtime settings, accelerator budget, and request/response contract...Votes: 0GitHub stars: 2
- Vllm Server Performance EnvelopeUse when vLLM inference serving must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for vLLM inference serving 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 model artifact identity, runtime settings, accelerator budget, an...Votes: 0GitHub stars: 2
- Vllm Server Permission Boundary ReviewUse when vLLM inference serving may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for vLLM inference serving 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 model artifact identity, runtime settings, accelerator...Votes: 0GitHub stars: 2
- Vllm Server Release Handoff RecordUse when a vLLM inference serving review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for vLLM inference serving 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 model artifact identity, runtime settings, acce...Votes: 0GitHub stars: 2
- Vllm Server Reproducibility Fixture PlanUse when a vLLM inference serving result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for vLLM inference serving 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 model artifact iden...Votes: 0GitHub stars: 2
- Vllm Server Version CompatibilityUse when a vLLM inference serving integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for vLLM inference serving 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 model artifact identity, runtime settings,...Votes: 0GitHub stars: 2
- Web Search Engine DevelopmentUse when building a search engine that discovers and indexes web pages, combines crawl and query workflows, or serves web-scale search results to define the authorized crawl scope, access policy, indexing lifecycle, and ranking evaluation before enabling network collection. Trigger for crawlers, link discovery, web indexes, or public-web query services.Votes: 0GitHub stars: 2
- Backtest Information Leakage AuditUse when a task involves auditing an algorithmic trading backtest for look-ahead, survivorship, and selection leakage 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 producti...Votes: 0GitHub stars: 2
- Finance Ops Close Approval Evidence PacketUse when a period close result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, a...Votes: 0GitHub stars: 2
- Finance Ops Close Change Impact TraceUse when a version, rule, source, or stakeholder change may affect period close to produce a before/after change record and impact map for the close reconciliation packet. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and author...Votes: 0GitHub stars: 2
- Finance Ops Close Closeout Handoff LedgerUse when a period close work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities o...Votes: 0GitHub stars: 2
- Finance Ops Close Completeness ReconciliationUse when the period close workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write ...Votes: 0GitHub stars: 2
- Finance Ops Close Exception Triage QueueUse when the period close workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities ...Votes: 0GitHub stars: 2
- Finance Ops Close Recovery Readiness DrillUse when the period close workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write ca...Votes: 0GitHub stars: 2
- Finance Ops Close Scenario Sensitivity MatrixUse when the period close team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the close reconciliation packet with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities only w...Votes: 0GitHub stars: 2
- Finance Ops Close Scope Intake GateUse when a new period close request needs a bounded work scope to produce a scoped intake card for the close reconciliation packet. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused pass...Votes: 0GitHub stars: 2
- Finance Ops Close Source Provenance LedgerUse when a decision about period close depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the close reconciliation packet. Success means each material claim has a source, version/date, location, and confidence note; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refi...Votes: 0GitHub stars: 2
- Finance Ops Close Threshold Rule CheckUse when a period close decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the close reconciliation packet 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; every reconciliation has a preparer, reviewer, tie-out, and outstanding variance status. Use configured search, fetch, read, browser, test, and ...Votes: 0GitHub stars: 2
- Finance Ops Controls Approval Evidence PacketUse when a financial control and audit administration result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the control evidence ledger 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search,...Votes: 0GitHub stars: 2
- Finance Ops Controls Change Impact TraceUse when a version, rule, source, or stakeholder change may affect financial control and audit administration to produce a before/after change record and impact map for the control evidence ledger. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser, test, and write capabilities...Votes: 0GitHub stars: 2
- Finance Ops Controls Closeout Handoff LedgerUse when a financial control and audit administration work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the control evidence ledger 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser, ...Votes: 0GitHub stars: 2
- Finance Ops Controls Completeness ReconciliationUse when the financial control and audit administration workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the control evidence ledger 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, r...Votes: 0GitHub stars: 2
- Finance Ops Controls Exception Triage QueueUse when the financial control and audit administration workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the control evidence 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser,...Votes: 0GitHub stars: 2
- Finance Ops Controls Recovery Readiness DrillUse when the financial control and audit administration workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the control evidence 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, rea...Votes: 0GitHub stars: 2
- Finance Ops Controls Scenario Sensitivity MatrixUse when the financial control and audit administration team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the control evidence ledger with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser, test,...Votes: 0GitHub stars: 2
- Finance Ops Controls Scope Intake GateUse when a new financial control and audit administration request needs a bounded work scope to produce a scoped intake card for the control evidence ledger. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit re...Votes: 0GitHub stars: 2
- Finance Ops Controls Source Provenance LedgerUse when a decision about financial control and audit administration depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the control evidence ledger. Success means each material claim has a source, version/date, location, and confidence note; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorize...Votes: 0GitHub stars: 2
- Finance Ops Controls Threshold Rule CheckUse when a financial control and audit administration decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the control evidence 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; each tested control has a reproducible sample and exceptions remain visible to the reviewer. Use configured search, fe...Votes: 0GitHub stars: 2
- Finance Ops Expenses Approval Evidence PacketUse when a expense policy administration result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the expense exception queue 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; each exception is classified against the current policy and no reimbursement is approved automatically. Use configured search, f...Votes: 0GitHub stars: 2
- Finance Ops Expenses Change Impact TraceUse when a version, rule, source, or stakeholder change may affect expense policy administration to produce a before/after change record and impact map for the expense exception queue. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; each exception is classified against the current policy and no reimbursement is approved automatically. Use configured search, fetch, read, browser, test, and write capabilities o...Votes: 0GitHub stars: 2