Showing 38401–38430 of 44682 skills
Protect AI-agent tasks from indirect prompt injection and untrusted tool output by tracing instruction provenance, separating data from authority, constraining source-to-sink flows, and confirming sensitive disclosure or action. Use when reading webpages, issues, emails, documents, logs, MCP results, or third-party skills while tools can access private data or mutate state; do not use for ordinary trusted inputs with no external-content boundary.
CHENG-LIANG1/badass-skills
Use when a parallel artifact integration result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the integration staging plan 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 output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when a parallel artifact integration work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the integration staging plan 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 output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when the parallel artifact integration workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the integration staging plan 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 output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when the parallel artifact integration workflow has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the integration staging plan 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 output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when the parallel artifact integration workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the integration staging plan 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 output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when the parallel artifact integration team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the integration staging plan with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; each output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when a decision about parallel artifact integration depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the integration staging plan. Success means each material claim has a source, version/date, location, and confidence note; each output is reviewed against the same baseline and conflicts remain visible. 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.
Manoj-11-Dahal/try-Skills
Use when a delegated task cancellation propagation result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the cancellation propagation check 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; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when a delegated task cancellation propagation work item is nearing completion, pause, or transfer to another owner to produce a closeout ledger for the cancellation propagation check 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; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when the delegated task cancellation propagation workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the cancellation propagation check 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; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when the delegated task cancellation propagation workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the cancellation propagation check 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; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when the delegated task cancellation propagation team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the cancellation propagation check with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when a decision about delegated task cancellation propagation depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the cancellation propagation check. Success means each material claim has a source, version/date, location, and confidence note; all cancellable work reaches a known terminal state and pending side effects are surfaced. 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.
Manoj-11-Dahal/try-Skills
Use when a multi-agent checkpoint and resume result is ready for a human owner to approve, reject, or redirect to produce a decision packet for the resume checkpoint manifest 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; resumption does not repeat completed side effects or lose unresolved decisions. 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.
Manoj-11-Dahal/try-Skills
Use when the multi-agent checkpoint and resume workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the resume checkpoint manifest 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; resumption does not repeat completed side effects or lose unresolved decisions. 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.
Manoj-11-Dahal/try-Skills
Use when the multi-agent checkpoint and resume workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the resume checkpoint manifest 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; resumption does not repeat completed side effects or lose unresolved decisions. 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.
Manoj-11-Dahal/try-Skills
Use when the multi-agent checkpoint and resume team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the resume checkpoint manifest with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; resumption does not repeat completed side effects or lose unresolved decisions. 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.
Manoj-11-Dahal/try-Skills
Use when a decision about multi-agent checkpoint and resume depends on facts from several records or public sources to produce a source-to-claim provenance ledger for the resume checkpoint manifest. Success means each material claim has a source, version/date, location, and confidence note; resumption does not repeat completed side effects or lose unresolved decisions. 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.
Manoj-11-Dahal/try-Skills
Use when the delegated context handoff workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the minimal context handoff 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; the receiver can continue without hidden assumptions or unnecessary private data. 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.
Manoj-11-Dahal/try-Skills
Use when the delegated context handoff team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the minimal context handoff packet with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; the receiver can continue without hidden assumptions or unnecessary private data. 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.
Manoj-11-Dahal/try-Skills
Use when the agent task dependency graphs workflow receives records that must agree across sources, periods, or statuses to produce a reconciliation worksheet for the task dependency graph 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; no task starts before its prerequisites and every output has a receiving owner. 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.
Manoj-11-Dahal/try-Skills
Use when the agent task dependency graphs team needs to compare options under changing assumptions to produce a baseline-plus-scenarios matrix for the task dependency graph with assumptions and ranges. Success means the baseline is reproducible, scenario inputs are explicit, comparable units are used, and conclusions state uncertainty; no task starts before its prerequisites and every output has a receiving owner. 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.
Manoj-11-Dahal/try-Skills
Use when the user asks for formal verification or formal methods: writing or checking a design model (TLA+, Alloy, P, Quint), proving code against contracts (Dafny, Verus, SPARK, Frama-C, Lean, Rocq), model checking, invariants, liveness, vacuous passes, or counterexamples; deciding whether a design or requirement warrants formal verification; or keeping existing formal specs and proofs current. Not for prose requirements or "spec this out" (use sdd).
ahgraber/skills
Use when authoring or reviewing a hands-on demo, tour, or walkthrough notebook (`#%%` percent-format or Jupyter) that demonstrates a feature, library, or API and doubles as semi-interactive documentation. Triggers: "write a demo notebook", "build a feature demo", "demo this library/API", "a notebook to walk through X", "interactive docs for this feature". Not for production/analysis notebooks or pure asyncio event-loop mechanics (see python-notebooks-async).
ahgraber/skills
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
ahgraber/skills
Use when the user supplies existing security findings or vulnerability reports — SARIF results, CVE/GHSA or advisory text, scanner tickets, bug bounty reports, or finding artifacts — and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.
ahgraber/skills
Use to cut slop out of working code: duplication, dead code, needless indirection, comment noise, defensive padding. Point it at the current changes, a file, a directory, or the whole repo. Triggers: 'simplify this', 'clean this up', 'de-slop this code', 'strip the cruft', 'tighten this diff', 'this code is bloated', 'audit this for slop'. Not for judging correctness or merge readiness (use code-review), and not for structural change that needs a plan and approval (use refactor).
ahgraber/skills
Review what a code change could break beyond the diff and prove the main fact that makes it safe. Use only when the user explicitly asks for a blast-radius review, asks what a change could break, or requests extra scrutiny of a suspicious diff.
ykorovko/dotagents
Create a concise handoff document so a fresh agent or new session can continue the current work. Use only when the user explicitly asks for a handoff, continuation brief, or context transfer.
ykorovko/dotagents