All authors
Claude Skills by Manoj-11-Dahal
github.com/Manoj-11-Dahal15,860 skills0 installs0 views
- Aas Agent Quality Retrieval Evidence Completeness ReconciliationUse when the retrieval evidence grounding workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the retrieval-to-claim trace 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 material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and wri...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Exception Triage QueueUse when the retrieval evidence grounding workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the retrieval-to-claim trace 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 material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and write capabiliti...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Recovery Readiness DrillUse when the retrieval evidence grounding workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the retrieval-to-claim trace 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 material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and write...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Scenario Sensitivity MatrixUse when the retrieval evidence grounding team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the retrieval-to-claim trace with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; every material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and write capabilities onl...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Scope Intake GateUse when a new retrieval evidence grounding request needs a bounded work scope to produce a scoped intake card for the retrieval-to-claim trace. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; every material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused p...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Source Provenance LedgerUse when a decision about retrieval evidence grounding depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the retrieval-to-claim trace. Success means each material claim has a source, version/date, location, and confidence note; every material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit r...Votes: 0GitHub stars: 2
- Aas Agent Quality Retrieval Evidence Threshold Rule CheckUse when a retrieval evidence grounding decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the retrieval-to-claim trace 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 material claim maps to the retrieved evidence or is labeled unsupported. Use configured search, fetch, read, browser, test, a...Votes: 0GitHub stars: 2
- Agent Graph Memory DesignUse when a task involves designing a graph-backed memory model for agent sessions, entities, preferences, and provenance 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 ru...Votes: 0GitHub stars: 2
- Agent Memory Claim Confidence CalibrationUse when a task involves calibrating confidence labels for facts stored in an agent memory system 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, devic...Votes: 0GitHub stars: 2
- Agent Memory Contradiction ResolutionUse when a task involves resolving conflicting persistent memories while preserving competing evidence 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, ...Votes: 0GitHub stars: 2
- Agent Memory Correction Propagation ReviewUse when a task involves checking that a corrected fact updates dependent agent memories without erasing provenance 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...Votes: 0GitHub stars: 2
- Agent Memory Cross Tenant Isolation TestUse when a task involves testing that one user's or team's memory cannot leak into another context 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, devi...Votes: 0GitHub stars: 2
- Agent Memory Privacy GovernanceUse when a task involves setting retention, consent, correction, and deletion controls for persistent AI-agent memory to identify the intended outcome, relevant inputs, platform or version, sensitive data, and permission boundary before acting. Use current primary documentation for version-sensitive behavior, produce a reviewable artifact, and verify it against stated criteria. Trigger for planning, implementation, evaluation, or troubleshooting in this focused domain; do not install or run t...Votes: 0GitHub stars: 2
- Agent Memory Recall Precision EvaluationUse when a task involves evaluating whether a persistent memory system retrieves useful and relevant facts 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, financi...Votes: 0GitHub stars: 2
- Agent Memory Session Summary AcceptanceUse when a task involves checking a session summary before it becomes durable long-term memory 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-c...Votes: 0GitHub stars: 2
- Agent Memory Skill Publishing Approval GateUse when a task involves reviewing whether an extracted workflow is ready to become a reusable agent skill 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, financi...Votes: 0GitHub stars: 2
- Agent Memory Source Provenance AuditUse when a task involves auditing source links and lineage for persistent agent memory claims 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-co...Votes: 0GitHub stars: 2
- Agent Memory Staleness Revalidation PolicyUse when a task involves defining when stored facts or preferences need revalidation before reuse 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, devic...Votes: 0GitHub stars: 2
- Agent Memory Temporal Validity ModelUse when a task involves modeling when stored agent facts are true and when they were recorded 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-c...Votes: 0GitHub stars: 2
- Azure Ai Search GroundingUse when a task involves designing a permission-aware Azure AI Search retrieval path that grounds model responses in current indexed content 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; ...Votes: 0GitHub stars: 2
- Codebase Memory McpUse when a task involves designing or evaluating a persistent codebase-memory MCP integration that retrieves useful repository facts 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 i...Votes: 0GitHub stars: 2
- Context EngineeringUse when an agent works in an unfamiliar or information-heavy project, context is limited, or outputs miss local conventions to collect the smallest authoritative set of instructions, code, examples, and history needed for the task; rank freshness and trust; keep untrusted content separate from control instructions. Trigger at session start, task handoff, or when results drift.Votes: 0GitHub stars: 2
- Continuous Learning And Pattern CurationUse when a user asks to preserve a lesson, repeated correction, or successful workflow as reusable guidance for future tasks to turn observed evidence into a small, scoped candidate pattern, distinguish confidence from fact, and obtain approval before persistent or cross-project storage. Trigger for explicit learning, memory curation, or pattern promotion requests.Votes: 0GitHub stars: 2
- Contradictory Web Claim Resolution LedgerUse when two or more sources disagree on a factual statement relevant to a decision to create or update a contradiction table with proposition, source scope, dates, and resolution status. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the disagreement is explained by scope, version, method, or remains explicitly unresolved. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain appr...Votes: 0GitHub stars: 2
- Memory Index Rebuild Consistency CheckUse when a task involves checking that rebuilt search and vector indexes match the authoritative memory store 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, fina...Votes: 0GitHub stars: 2
- Multi Chunk Fetch Completeness LedgerUse when a fetched page reports additional chunks or is truncated before its relevant section to create or update a chunk ledger with expected, fetched, and still-missing ranges. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: all chunks needed for the question are present or the result clearly says review is partial. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval be...Votes: 0GitHub stars: 2
- Rag Retrieval Quality EvaluationUse when a task involves evaluating retrieval quality for a grounded-generation system using representative queries, relevant passages, and permission checks 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...Votes: 0GitHub stars: 2
- Redirected Source Canonical Url AuditUse when a source URL redirects, canonicalizes, or changes host during retrieval to create or update a redirect record containing requested URL, final URL, and reason for substitution. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the final destination is relevant and its identity is transparent in the record. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before e...Votes: 0GitHub stars: 2
- Shared Agent Memory Acl Boundary ReviewUse when a task involves reviewing access boundaries for memories shared across users, teams, and agents 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...Votes: 0GitHub stars: 2
- Source Grounded ResearchUse when a task depends on facts that must be researched, current, or verifiable from external or internal sources to find authoritative evidence, preserve provenance, distinguish facts from inference, compare disagreements, and cite claims. Trigger for research, documentation, framework decisions, API usage, or any response where unsupported confidence would mislead.Votes: 0GitHub stars: 2
- Web Claim Source Date Freshness AuditUse when a claim concerns current versions, prices, policy, availability, release status, or deadlines to create or update a dated claim-source table with as-of date and update signal. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the source is valid for the requested date or the claim is explicitly time-bounded. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval befor...Votes: 0GitHub stars: 2
- Web Query Evidence Gap RefinerUse when initial search results do not cover one or more explicit research criteria to create or update a query log with the gap, revised query, and newly found source candidates. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: each required criterion is backed by a fetched source or explicitly marked unresolved. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before ...Votes: 0GitHub stars: 2
- Web Quotation Context Boundary AuditUse when a draft paraphrase or quotation may have been shortened or detached from context to create or update a quote-to-claim mapping with the relevant surrounding passage. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: the quotation and paraphrase retain the original limitation and polarity. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible ...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Build Configuration RunbookUse when an authorized implementation needs repeatable steps and a visible change boundary for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means the prepared result is reproducible, review...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Design BlueprintUse when a solution needs a coherent structure before implementation or production for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means interfaces, dependencies, constraints, and review points are testa...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Failure Triage And RecoveryUse when an unexpected result needs diagnosis without widening risk or losing evidence for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means the failure is bounded by observati...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Measured Improvement And HandoffUse when a measured result or recurring failure suggests a change worth testing and handing to an owner for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a versioned improvement proposal and handoff packet with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means the proposed change...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Option Comparison MatrixUse when several tools, designs, methods, or workflows could satisfy the same need for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means options are compared on user-approved criteria w...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Requirements And Decision BriefUse when a request must be converted into testable constraints and an owned decision for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means requirements have priorities, evidence, owner...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Scope And Baseline RecordUse when the work needs a verified goal, authorized boundary, and starting state for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means the owner, constraints, baseline, and acceptance signal are explic...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Security Rights And Safety ReviewUse when the workflow could affect people, systems, confidential data, intellectual property, or physical outcomes for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a scoped risk-and-control review with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means the review names relevant h...Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Source Research And Provenance LedgerUse when a decision depends on current, source-grounded information for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a source-and-claim ledger with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means material claims are linked to current primary sources with dates and limitations....Votes: 0GitHub stars: 2
- Looplab Context Compression Conflicting Evidence Verification And Acceptance Test PlanUse when a result must be checked against explicit behavior, safety, or quality conditions for Agent reasoning, planning, and bounded loops: context compression for conflicting evidence. Produce a risk-weighted verification plan with saved evidence with scope, versions, decisions, and evidence for this task-specific gate: Compare source dates, authority, methods, and scope; preserve unresolved disagreement rather than averaging incompatible claims. Success means each critical requirement maps...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Build Configuration RunbookUse when an authorized implementation needs repeatable steps and a visible change boundary for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a bounded build or configuration runbook with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means the prepared result is reproducible, reviewab...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Design BlueprintUse when a solution needs a coherent structure before implementation or production for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a staged design blueprint with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means interfaces, dependencies, constraints, and review points are testabl...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Failure Triage And RecoveryUse when an unexpected result needs diagnosis without widening risk or losing evidence for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a failure-triage record and reversible recovery plan with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means the failure is bounded by observation...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Measured Improvement And HandoffUse when a measured result or recurring failure suggests a change worth testing and handing to an owner for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a versioned improvement proposal and handoff packet with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means the proposed change i...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Option Comparison MatrixUse when several tools, designs, methods, or workflows could satisfy the same need for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce an evidence-backed option-comparison matrix with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means options are compared on user-approved criteria wit...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Requirements And Decision BriefUse when a request must be converted into testable constraints and an owned decision for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a reviewable requirements and decision brief with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means requirements have priorities, evidence, owners,...Votes: 0GitHub stars: 2
- Looplab Context Compression Long Horizon Tasks Scope And Baseline RecordUse when the work needs a verified goal, authorized boundary, and starting state for Agent reasoning, planning, and bounded loops: context compression for long-horizon tasks. Produce a scope-and-baseline record with scope, versions, decisions, and evidence for this task-specific gate: Track milestone completion and the remaining dependency list; do not claim the whole project is done from one completed subtask. Success means the owner, constraints, baseline, and acceptance signal are explicit...Votes: 0GitHub stars: 2