All authors
Claude Skills by Manoj-11-Dahal
github.com/Manoj-11-Dahal15,860 skills0 installs0 views
- Gh Aw Workflow Secrets Context AuditUse when a task involves checking which workflow jobs and agent processes can access named secrets to record the product, runtime and repository version, identity, trust boundary, data sensitivity, controlling artifact, owner, and approval scope before applying the method. Distinguish documented behavior from tested behavior, verify with a bounded reproducible case, preserve provenance, and report compatibility and uncertainty. Do not install, grant access, send external writes, or change pro...Votes: 0GitHub stars: 2
- Gh Aw Workflow Supply Chain Change ReviewUse when a task involves reviewing changes to actions, agents, skills, MCP servers, and model dependencies in a workflow to record the product, runtime and repository version, identity, trust boundary, data sensitivity, controlling artifact, owner, and approval scope before applying the method. Distinguish documented behavior from tested behavior, verify with a bounded reproducible case, preserve provenance, and report compatibility and uncertainty. Do not install, grant access, send external...Votes: 0GitHub stars: 2
- Gh Aw Workflow Upgrade Regression PlanUse when a task involves planning a regression suite for changes to an agent workflow compiler or runtime to record the product, runtime and repository version, identity, trust boundary, data sensitivity, controlling artifact, owner, and approval scope before applying the method. Distinguish documented behavior from tested behavior, verify with a bounded reproducible case, preserve provenance, and report compatibility and uncertainty. Do not install, grant access, send external writes, or cha...Votes: 0GitHub stars: 2
- Hf Cli Capability Surface MapUse when the actual capability boundary of Hugging Face CLI workflows needs to be distinguished from assumptions. Produce a capability map for Hugging Face CLI workflows 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 account identity, repository target, lo...Votes: 0GitHub stars: 2
- Hf Cli Change Impact AssessmentUse when a proposed Hugging Face CLI workflows version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for Hugging Face CLI workflows 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 account identity, repository target, ...Votes: 0GitHub stars: 2
- Hf Cli Failure Triage RecordUse when a reproducible Hugging Face CLI workflows symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for Hugging Face CLI workflows 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 account identity, repository target, local cache state, and file-operation ...Votes: 0GitHub stars: 2
- Hf Cli Input Output ContractUse when the accepted inputs or produced outputs for Hugging Face CLI workflows need a checkable boundary. Produce an input/output contract for Hugging Face CLI workflows 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 account identity, repository target, local cache state, and file-op...Votes: 0GitHub stars: 2
- Hf Cli Integration Parity TraceUse when Hugging Face CLI workflows exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for Hugging Face CLI workflows 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 account identity, repository target, local cache state, and file-operation scope. Us...Votes: 0GitHub stars: 2
- Hf Cli Performance EnvelopeUse when Hugging Face CLI workflows must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for Hugging Face CLI workflows 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 account identity, repository target, local cache state, a...Votes: 0GitHub stars: 2
- Hf Cli Permission Boundary ReviewUse when Hugging Face CLI workflows may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for Hugging Face CLI workflows 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 account identity, repository target, local cac...Votes: 0GitHub stars: 2
- Hf Cli Release Handoff RecordUse when a Hugging Face CLI workflows review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for Hugging Face CLI workflows 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 account identity, repository target, lo...Votes: 0GitHub stars: 2
- Hf Cli Reproducibility Fixture PlanUse when a Hugging Face CLI workflows result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for Hugging Face CLI workflows 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 account ide...Votes: 0GitHub stars: 2
- Hf Cli Version CompatibilityUse when a Hugging Face CLI workflows integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for Hugging Face CLI workflows 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 account identity, repository targe...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Capability Surface MapUse when the actual capability boundary of Hugging Face model evaluation needs to be distinguished from assumptions. Produce a capability map for Hugging Face model evaluation 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 evaluation-set provenance, backen...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Change Impact AssessmentUse when a proposed Hugging Face model evaluation version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for Hugging Face model evaluation 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 evaluation-set provenance, back...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Failure Triage RecordUse when a reproducible Hugging Face model evaluation symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for Hugging Face model evaluation 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 evaluation-set provenance, backend selection, metric definitions, and...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Input Output ContractUse when the accepted inputs or produced outputs for Hugging Face model evaluation need a checkable boundary. Produce an input/output contract for Hugging Face model evaluation 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 evaluation-set provenance, backend selection, metric definiti...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Integration Parity TraceUse when Hugging Face model evaluation exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for Hugging Face model evaluation 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 evaluation-set provenance, backend selection, metric definitions, and result l...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Performance EnvelopeUse when Hugging Face model evaluation must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for Hugging Face model evaluation 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 evaluation-set provenance, backend selection, metri...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Permission Boundary ReviewUse when Hugging Face model evaluation may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for Hugging Face model evaluation 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 evaluation-set provenance, backend selec...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Release Handoff RecordUse when a Hugging Face model evaluation review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for Hugging Face model evaluation 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 evaluation-set provenance, backen...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Reproducibility Fixture PlanUse when a Hugging Face model evaluation result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for Hugging Face model evaluation 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 evalu...Votes: 0GitHub stars: 2
- Hugging Face Community Evals Version CompatibilityUse when a Hugging Face model evaluation integration or upgrade depends on compatible runtime, client, service, or artifact versions. Produce a version-compatibility record for Hugging Face model evaluation 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 evaluation-set provenance, b...Votes: 0GitHub stars: 2
- Infsh CliUse when a task involves using the configured inference.sh CLI or app workflow to prepare an approved AI media or automation task 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 inst...Votes: 0GitHub stars: 2
- Mcp Conformance And Interoperability Test PlanUse when preparing a test plan for an MCP client, server, SDK, or integration across protocol versions, transports, capabilities, or optional extensions to produce a reproducible matrix of discovery, request/response, authorization, errors, cancellation, and extension scenarios. Success means tests cover both expected behavior and meaningful failure paths for each supported peer combination, findings identify exact versions, and no single visual inspection is presented as full protocol confor...Votes: 0GitHub stars: 2
- Mcp Deprecated Feature Migration PlanUse when upgrading an MCP client, server, SDK, or deployment and identifying protocol features that are deprecated in the target revision to produce a versioned inventory, migration plan, compatibility window, owners, and regression tests. Success means each deprecated use is mapped to the current migration path, new code does not adopt deprecated behavior by default, and existing clients remain supported only through an explicit, tested transition plan. Recheck the live deprecation registry ...Votes: 0GitHub stars: 2
- Mcp Http Authorization And Registration AuditUse when auditing OAuth authorization between an MCP client, protected MCP server, and authorization server over an HTTP transport to verify protected-resource discovery, issuer binding, client registration, resource indicators, token audience, scopes, PKCE, and separation from upstream API credentials. Success means a token is accepted only for its intended MCP resource and authorization context, least privilege is demonstrable, and mismatched or overbroad credentials are rejected without le...Votes: 0GitHub stars: 2
- Mcp Multiroundtrip Input Flow ReviewUse when designing or testing an MCP request that may pause to ask the client or user for additional input before completing, such as a tool call that needs approval or a prompt/resource that needs a selection to review InputRequiredResult, input requests/responses, opaque request state, retry IDs, consent, replay handling, and supported request types. Success means the retry is bound to the original request, user decisions remain explicit, and incomplete or repeated input cannot cause an uni...Votes: 0GitHub stars: 2
- Mcp Protocol Version Discovery Compatibility ReviewUse when verifying MCP protocol-version negotiation, server discovery, capability reporting, or modern/legacy interoperability across named client, server, SDK, and transport versions to produce a compatibility matrix and bounded test record. Success means request metadata and supported versions are explicit, extension behavior has a defined fallback or rejection, version errors trigger only valid retries, and unsupported combinations fail clearly. Do not treat self-reported server identity a...Votes: 0GitHub stars: 2
- Mcp Resource Cache Subscription Boundary ReviewUse when designing or auditing MCP resources, paginated discovery, response caching, or change subscriptions, especially when visibility depends on the caller’s authorization to review resource URIs, cache keys, TTL, public/private scope, pagination, invalidation, subscription filters, and reconnect behavior. Success means private data cannot cross authorization contexts, stale results are invalidated or refreshed appropriately, and cursors and subscription IDs are handled as opaque protocol ...Votes: 0GitHub stars: 2
- Mcp Server DevelopmentUse when building or modifying an MCP server that exposes tools, resources, prompts, or transport behavior to an agent host to verify current protocol and SDK documentation, keep capabilities narrow, validate every boundary, and test through a local or staging client before exposing the service. Trigger for MCP server authoring, SDK upgrades, or transport changes.Votes: 0GitHub stars: 2
- Mcp Server Integration SafetyUse when selecting, configuring, building, or reviewing an MCP server or connection to assess publisher and version, tool schemas, authentication, scopes, data access, network egress, sandbox, approval gates, and audit logging before enabling actions. Trigger before connecting new MCP tools, changing permissions, or exposing agent capabilities to a server.Votes: 0GitHub stars: 2
- Mcp Skills Extension Interoperability ReviewUse when exposing, discovering, or loading Agent Skills through the MCP Skills extension `io.modelcontextprotocol/skills` to review capability declaration, skills/list and skills/get, resource manifests, URI identity, digest verification, cache origin, directoryRead support, user approval, and activation behavior. Success means skill content is loaded only from its approved server and verified manifest, and reading a SKILL.md is not mistaken for permission to activate or execute it.Votes: 0GitHub stars: 2
- Mcp Streamable Http Stateless Deployment ReviewUse when deploying, upgrading, or auditing an MCP server over Streamable HTTP, especially when moving from session-based or HTTP+SSE behavior to the 2026-07-28 stateless request model to review the endpoint, POST/SSE flow, request metadata, Origin validation, authentication, subscriptions, cancellation, and legacy compatibility. Success means each request is correctly scoped, network exposure is intentional, and no deprecated stream/session assumption creates a security or interoperability gap.Votes: 0GitHub stars: 2
- Mcp Tasks Extension Lifecycle ReviewUse when deciding whether an MCP operation needs a durable task handle because it may run for a long time, pause for input, survive disconnects, or expose meaningful progress to review Tasks-extension negotiation, task creation, status transitions, polling, input updates, cancellation, retention, and side effects. Success means clients and servers opt in explicitly, task state is recoverable within its declared lifetime, and cancellation is not misrepresented as rollback or guaranteed stop.Votes: 0GitHub stars: 2
- Parallel FindallUse when a task involves using a configured entity-discovery service to find records matching a natural-language description 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 o...Votes: 0GitHub stars: 2
- Parallel Web SearchUse when a task involves using an approved Parallel web-search integration for source discovery, extraction, or targeted research 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 inst...Votes: 0GitHub stars: 2
- Planetscale Schema Recommendations Agent LoopUse when a task involves reviewing PlanetScale query or schema recommendations and packaging safe changes for human review 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 ...Votes: 0GitHub stars: 2
- Skill Discovery And Supply Chain ReviewUse when a user asks to find, compare, or add agent skills from a URL list, registry, or repository to check candidate relevance, source identity, license, entry-point format, dependencies, and side effects before importing; keep provenance and never run setup scripts by default. Trigger for skill discovery, evaluation, or installation.Votes: 0GitHub stars: 2
- Skill Frontmatter Host Parser Compatibility CheckUse when a skill package is intended for more than one agent client to create or update a host-compatibility record for metadata, folder name, and required fields. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: each target host accepts the required metadata or a known limitation is declared. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or...Votes: 0GitHub stars: 2
- Skill Tool Capability Fallback Routing TestUse when a workflow depends on optional search, browser, filesystem, or test capabilities to create or update a capability-to-fallback table with prohibited substitutions. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the agent either uses an authorized equivalent or stops with a precise missing-capability request. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval bef...Votes: 0GitHub stars: 2
- Tavily Web Capability Surface MapUse when the actual capability boundary of Tavily web retrieval needs to be distinguished from assumptions. Produce a capability map for Tavily web retrieval 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 query scope, source identity, extraction boundary, ...Votes: 0GitHub stars: 2
- Tavily Web Change Impact AssessmentUse when a proposed Tavily web retrieval version, setting, schema, model, or integration change may affect existing consumers. Produce a change-impact record for Tavily web retrieval 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 query scope, source identity, extraction boundary...Votes: 0GitHub stars: 2
- Tavily Web Failure Triage RecordUse when a reproducible Tavily web retrieval symptom needs bounded diagnosis before any corrective change. Produce a failure-triage record for Tavily web retrieval 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 query scope, source identity, extraction boundary, freshness, and citation traceability...Votes: 0GitHub stars: 2
- Tavily Web Input Output ContractUse when the accepted inputs or produced outputs for Tavily web retrieval need a checkable boundary. Produce an input/output contract for Tavily web retrieval 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 query scope, source identity, extraction boundary, freshness, and citation trac...Votes: 0GitHub stars: 2
- Tavily Web Integration Parity TraceUse when Tavily web retrieval exchanges state or data with another component and the handoff needs to be verified. Produce an integration-parity trace for Tavily web retrieval 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 query scope, source identity, extraction boundary, freshness, and citation traceability. Use onl...Votes: 0GitHub stars: 2
- Tavily Web Performance EnvelopeUse when Tavily web retrieval must be assessed against a user- or owner-defined latency, memory, throughput, size, or cost budget. Produce a performance-envelope note for Tavily web retrieval 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 query scope, source identity, extraction boundary, freshness, and cit...Votes: 0GitHub stars: 2
- Tavily Web Permission Boundary ReviewUse when Tavily web retrieval may read, write, transmit, publish, spend, or administer data or resources. Produce a permission-boundary map for Tavily web retrieval 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 query scope, source identity, extraction boundary, freshne...Votes: 0GitHub stars: 2
- Tavily Web Release Handoff RecordUse when a Tavily web retrieval review is ready to be handed to a maintainer or accountable operator. Produce a release-handoff record for Tavily web retrieval 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 query scope, source identity, extraction boundary, ...Votes: 0GitHub stars: 2
- Tavily Web Reproducibility Fixture PlanUse when a Tavily web retrieval result must be independently repeated or compared without relying on an uncontrolled live action. Produce a reproducibility plan for Tavily web retrieval 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 query scope, source ide...Votes: 0GitHub stars: 2