Showing 35221–35250 of 43485 skills
Commit current changes with conventional commits format, append the /ai-review trigger to the final commit, and push to remote repository. Use when committing and pushing changes so the pushed PR gets a full AI review.
generic-automation-and-it/smooth-ai-stockanalysis
Sync the current working branch with origin/main and optionally resolve merge conflicts. Use when synchronizing local branch with the latest changes from main, with automatic or manual conflict resolution.
generic-automation-and-it/smooth-ai-stockanalysis
Convention for creating, updating, or modifying rule files in .agents/rules/. Use when adding, editing, or restructuring rule files to ensure compatibility across Claude Code, GitHub Copilot, Cursor, and OpenAI Codex.
generic-automation-and-it/smooth-ai-stockanalysis
Investigate a live or recent incident in a Kubernetes cluster. Anchor the window, bisect the change surface (rollouts, ConfigMaps/Secrets, RBAC, HPA/cluster changes, CronJobs), classify against four reference failure paths (OOM, DNS, cascading-failure, deploy-correlator), confirm the hypothesis with three independent signals, quantify blast radius, and propose mitigation before root cause. Use whenever an agent is asked "what is breaking in the cluster right now", "why did this pod/Deployment just page", "did the rollout cause Z", or to triage an active Kubernetes incident. Vendor-neutral by default (works with kubectl, kube-state-metrics, and whatever telemetry you have); an opt-in Anyshift integration is documented separately.
anyshift-io/sre-skills
Shape output for a reader with ADHD, then write each sentence in controlled English: action first, one word one meaning, active voice, simple tenses, state restated every turn. Invoke with /attention-control; stays on until "stop attention control".
aaddrick/attention-control
Build PFC 5.0 asphalt-mixture specimens with explicit aggregate objects, a declared homogenized-mastic or fine-particle abstraction, residual air voids, measured gradation conversion, contact-pair assignment, compaction, equilibrium, and mass-volume closure; use before Marshall, rutting, creep, or strength tests.
Echo-aloha/asphalt-codex-skills-5
Select, probe, calibrate, and audit the Burger viscoelastic contact model for PFC 5.0 asphalt-mixture cases, including Maxwell-Kelvin parameter roles, units, temperature/rate dependence, PFC5 cmat assignment, timestep checks, creep/recovery validation, and PFC5-only syntax boundary checks.
Echo-aloha/asphalt-codex-skills-5
Adapt and audit a PFC 5.0 asphalt Marshall stability/flow simulation using the external fistPkg26 dc.fis two-head controller as a starting skeleton; use for curved-head geometry, PFC5 wall/contact kinematics, load-deformation histories, peak stability, edition-specific flow processing, and validation against laboratory data.
Echo-aloha/asphalt-codex-skills-5
Design, implement, and audit PFC3D 5.0 asphalt wheel-tracking and intersection-rutting simulations using RVE-to-strip-to-full-size scaling, PFC5-compatible vector reaction control, Burger-calibrated contacts, vertical-horizontal coupled loads, rut/shear histories, edition-specific metrics, and explicit surrogate validation.
Echo-aloha/asphalt-codex-skills-5
Govern Asphalt-Codex-Skills-5 as a PFC 5.0-only asphalt-mixture package, enforcing version purity, external fistPkg boundaries, portable assets, validation, and release hygiene.
Echo-aloha/asphalt-codex-skills-5
Post-process exported PFC 5.0 asphalt DEM data with vedo for particle, force-chain, crack, displacement, velocity, slice, figure, and animation workflows.
Echo-aloha/asphalt-codex-skills-5
Instrument and post-process PFC 5.0 asphalt damage studies using bond-break hits, clustered AE events, macro energy density, source fields, stage summaries, and auditable CSV outputs.
Echo-aloha/asphalt-codex-skills-5
Audit, recover, and prepare portable handoffs of existing private PFC2D/PFC3D 5.0 asphalt cases, including integrity manifests, path portability, saved-state claims, cheap restore-first validation, and legacy-state quarantine.
Echo-aloha/asphalt-codex-skills-5
Build and audit PFC2D/PFC3D 5.0 model foundations for asphalt cases, including lifecycle, domain, balls, walls, clumps, groups, ranges, top-level cmat, staged saves, and source-version purity.
Echo-aloha/asphalt-codex-skills-5
Plan and validate PFC 5.0 asphalt fluid, pore-pressure, buoyancy, seepage, and PFC-FLAC coupling contracts while keeping version-specific commands and licensed coupling assets external.
Echo-aloha/asphalt-codex-skills-5
Design and audit PFC 5.0 asphalt dynamic loading and stress-wave studies with damping, timestep, rate, dispersion, source direction, boundary reflection, histories, and wheel-load handoff checks.
Echo-aloha/asphalt-codex-skills-5
Author and audit PFC 5.0 FISH for asphalt cases, including def/end functions, globals and locals, callbacks, numbered histories, object traversal, command blocks, IO, and stop logic.
Echo-aloha/asphalt-codex-skills-5
Prepare and validate portable CAD, polyline, node-element, clump, and boundary geometry contracts for PFC 5.0 asphalt models without bundling opaque legacy executables.
Echo-aloha/asphalt-codex-skills-5
Design and audit PFC 5.0 wall servo, loading-rate control, equilibrium checks, micro-to-macro calibration, two-target local solves, DOE campaigns, and independent confirmation for asphalt models.
Echo-aloha/asphalt-codex-skills-5
Plan, audit, and post-process PFC 5.0 asphalt calibration tests, including compression, diametral loading, direct tension, creep-recovery, test geometry, histories, peak metrics, stiffness, and fistPkg handoff.
Echo-aloha/asphalt-codex-skills-5
Author a work order for a boringoperator lane (terra build or sol review) with proper context loading, per James's professional-process directive
boringmarketer/kimi-first
Productionization loop for any product repo — classify the lane (rail / surface / activation), fix the proof column, ONE review pass, scripted path to production, done = live with a receipt. Use whenever a feature is being built for a real customer; use instead of ad-hoc review rounds.
boringmarketer/kimi-first
Use when a version, rule, source, or stakeholder change may affect parallel artifact integration to produce a before/after change record and impact map for the integration staging plan. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; 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 new parallel artifact integration request needs a bounded work scope to produce a scoped intake card for the integration staging plan. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are 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 a parallel artifact integration decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the integration staging plan 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 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 version, rule, source, or stakeholder change may affect delegated task cancellation propagation to produce a before/after change record and impact map for the cancellation propagation check. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; 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 has exceptions, missing evidence, or competing priorities to produce a prioritized exception queue for the cancellation propagation check 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; 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 new delegated task cancellation propagation request needs a bounded work scope to produce a scoped intake card for the cancellation propagation check. Success means owner, objective, permitted sources, acceptance condition, exclusions, and deadline are 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 a delegated task cancellation propagation decision depends on a limit, eligibility rule, policy, or target to produce a rule-check record for the cancellation propagation check 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; 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 version, rule, source, or stakeholder change may affect multi-agent checkpoint and resume to produce a before/after change record and impact map for the resume checkpoint manifest. Success means each material difference is tied to affected dependencies, consumers, owners, and a test or explicitly unknown impact; 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