Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 41101–41130 of 51818 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| agent-commit-message-to-diff-consistency-checkManoj-11-Dahal/try-SkillsUse when a tool-using agent prepares a commit message from a diff to create or update a message-to-file mapping with any unsupported claims removed. Use the configured search, fetch, read, browser, and test capabilities only when available and authorized. Success criterion: every message claim has a corresponding changed path or verified behavior. Preserve evidence and a run record, limit rework to three meaningful passes, and obtain approval before externally visible or irreversible writes. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-loop-budgeting-and-observabilityManoj-11-Dahal/try-SkillsUse when an agent loop can consume variable time, tool calls, money, tokens, or external quota to set explicit limits and progress signals, monitor them per iteration, detect churn or plateau, and stop or ask before crossing budgets. Trigger for unattended, recurring, multi-agent, or open-ended tasks where cost or runaway behavior matters. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-runtime-debuggingManoj-11-Dahal/try-SkillsUse when an agent run stalls, repeats tool calls, misroutes work, loses task context, or produces behavior inconsistent with its intended workflow to reconstruct the run from observable traces, test a specific failure hypothesis, and recommend a bounded recovery. Trigger for agent-runtime incidents and repeated orchestration failures, not ordinary application-code defects. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-approval-evidence-packetManoj-11-Dahal/try-SkillsUse when a agent message-to-tool correlation result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-change-impact-traceManoj-11-Dahal/try-SkillsUse when a version, rule, source, or stakeholder change may affect agent message-to-tool correlation to produce a before/after change record and impact map for the correlation map. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; each cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-closeout-handoff-ledgerManoj-11-Dahal/try-SkillsUse when a agent message-to-tool correlation work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-completeness-reconciliationManoj-11-Dahal/try-SkillsUse when the agent message-to-tool correlation workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the agent message-to-tool correlation workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-recovery-readiness-drillManoj-11-Dahal/try-SkillsUse when the agent message-to-tool correlation workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-scenario-sensitivity-matrixManoj-11-Dahal/try-SkillsUse when the agent message-to-tool correlation team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the correlation map with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; each cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-scope-intake-gateManoj-11-Dahal/try-SkillsUse when a new agent message-to-tool correlation request needs a bounded work scope to produce a scoped intake card for the correlation map. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; each cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-source-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision about agent message-to-tool correlation depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the correlation map. Success means each material claim has a source, version/date, location, and confidence note; each cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-message-correlation-threshold-rule-checkManoj-11-Dahal/try-SkillsUse when a agent message-to-tool correlation decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the correlation map 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 cited action maps to the correct call and no result is attributed to a neighboring turn. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-approval-evidence-packetManoj-11-Dahal/try-SkillsUse when a agent run outcome classification result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-change-impact-traceManoj-11-Dahal/try-SkillsUse when a version, rule, source, or stakeholder change may affect agent run outcome classification to produce a before/after change record and impact map for the outcome taxonomy and sample audit. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-closeout-handoff-ledgerManoj-11-Dahal/try-SkillsUse when a agent run outcome classification work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-completeness-reconciliationManoj-11-Dahal/try-SkillsUse when the agent run outcome classification workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the agent run outcome classification workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-recovery-readiness-drillManoj-11-Dahal/try-SkillsUse when the agent run outcome classification workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-scenario-sensitivity-matrixManoj-11-Dahal/try-SkillsUse when the agent run outcome classification team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the outcome taxonomy and sample audit with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-scope-intake-gateManoj-11-Dahal/try-SkillsUse when a new agent run outcome classification request needs a bounded work scope to produce a scoped intake card for the outcome taxonomy and sample audit. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are explicit; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-source-provenance-ledgerManoj-11-Dahal/try-SkillsUse when a decision about agent run outcome classification depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the outcome taxonomy and sample audit. Success means each material claim has a source, version/date, location, and confidence note; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-outcome-taxonomy-threshold-rule-checkManoj-11-Dahal/try-SkillsUse when a agent run outcome classification decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the outcome taxonomy and sample audit 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; classes are mutually understandable and separate model output from verified task completion. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-replay-fixture-approval-evidence-packetManoj-11-Dahal/try-SkillsUse when a agent trace replay fixtures result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the minimized replay fixture 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; the fixture reproduces the declared failure without replaying external side effects or private content. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-replay-fixture-change-impact-traceManoj-11-Dahal/try-SkillsUse when a version, rule, source, or stakeholder change may affect agent trace replay fixtures to produce a before/after change record and impact map for the minimized replay fixture. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; the fixture reproduces the declared failure without replaying external side effects or private content. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-replay-fixture-closeout-handoff-ledgerManoj-11-Dahal/try-SkillsUse when a agent trace replay fixtures work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the minimized replay fixture 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; the fixture reproduces the declared failure without replaying external side effects or private content. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-replay-fixture-completeness-reconciliationManoj-11-Dahal/try-SkillsUse when the agent trace replay fixtures workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the minimized replay fixture 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; the fixture reproduces the declared failure without replaying external side effects or private content. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| agent-telemetry-replay-fixture-exception-triage-queueManoj-11-Dahal/try-SkillsUse when the agent trace replay fixtures workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the minimized replay fixture 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; the fixture reproduces the declared failure without replaying external side effects or private content. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions. | Stars: 3 | Updated | Claude CodeCodex | Unverified | Install |
| la-le-meBulletsHo/la-le-me以中文、English 或中英双语记录、解释和复盘成人日常排便与肠道健康信息,包括 Bristol 便形文字分类、频次和时段趋势、食物线索、可持续饮食调整、季节菜谱、每日排便提醒,以及危险信号分流和经同意的附近就医机构查找。Use for Chinese, English, or bilingual requests about poop, stool, bowel movements, constipation or diarrhea tendencies, foods associated with a bowel change, gut-friendly meals, recurring bowel-health reminders, or nearby appropriate care after a safety concern. Do not use as a diagnostic or treatment tool. | Stars: 2 | Updated | Claude CodeCodex | Unverified | Install |
| la-le-meBulletsHo/la-le-me以中文、English 或中英双语记录、解释和复盘成人日常排便与肠道健康信息,包括 Bristol 便形文字分类、频次和时段趋势、食物线索、可持续饮食调整、季节菜谱、每日排便提醒,以及危险信号分流和经同意的附近就医机构查找。Use for Chinese, English, or bilingual requests about poop, stool, bowel movements, constipation or diarrhea tendencies, foods associated with a bowel change, gut-friendly meals, recurring bowel-health reminders, or nearby appropriate care after a safety concern. Do not use as a diagnostic or treatment tool. | Stars: 2 | Updated | Claude CodeCodex | Unverified | Install |