Showing 33361–33390 of 60223 skills
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
rootcastleco/rei-skills
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code int...
rootcastleco/rei-skills
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
rootcastleco/rei-skills
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
rootcastleco/rei-skills
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
rootcastleco/rei-skills
张一鸣(字节跳动/TikTok创始人)的思维框架与表达方式。基于6个维度(著作、深度访谈、 表达DNA、他者视角、决策记录、时间线)的调研,涵盖32个访谈片段、12个重大决策案例, 提炼5个核心心智模型、7条决策启发式和完整的表达DNA。 用途:作为思维顾问,用张一鸣的视角分析产品、组织、全球化、人才和个人成长问题。 当用户提到「用张一鸣的视角」「张一鸣会怎么看」「一鸣的思路」「zhang yiming perspective」时使用。 即使用户只是说「帮我用张一鸣的角度想想」「如果是字节会怎么做」「切换到张一鸣」也应触发。 即使用户说「字节怎么看」「头条的逻辑」「一鸣怎么选择」「一鸣」也应触发。
alchaincyf/zhang-yiming-skill
Use when a ChatGPT/Codex Plugin workflow needs to inspect, search, modify, or verify files in the host workspace using the safest native tools available.
imMamdouhaboammar/chatgpt-codex-plugin-autopilot
Use when a user mentions Slidebox, @monabbous/slidebox, monabbous's CSS checkbox or toggle, Mohamed Nabous's elastic switch, or the nabous.dev Slidebox playground. Find the official GitHub repository, choose CSS/SCSS/Less/Tailwind integration, and preserve native checkbox and radio behavior. Also covers optional experimental dragging and range helpers.
monabbous/slidebox
Guidelines for UI text and copy in WooCommerce. Use when writing user-facing text, labels, buttons, messages, or documentation in WooCommerce projects.
secondsky/claude-skills
Independent third-person code review. Use after ALL build phases are complete for a holistic review of the entire feature, or anytime the user wants a quality gate. Reviews as an independent Senior Architect who did NOT write the code and now owns it, so it must meet world-class standards.
nikhilw/structured-agentic-workflow
The Structured Agentic Development Workflow. Orchestrates brainstorm, write-plan, build-phase, 3p-review, triage, test-driven-development, systematic-debugging, and verify-completion skills. Use when starting new work, switching between development phases, or when the user asks about the workflow. A dedicated build model uses the build-model workflow instead of this one.
nikhilw/structured-agentic-workflow
Explore a problem space before planning. Proposes architectural approaches with trade-offs, challenges the obvious solution, estimates impact, and produces a decision document. Code is the LAST thing we touch — this skill never writes code or plans.
nikhilw/structured-agentic-workflow
Execute one phase from a plan file using the TDD → Test → Self-Review loop. Use when a plan has been approved and it's time to build. Accepts a plan file path and phase number. Builds phase by phase and produces a build completion report. Review (/3p-review) and, for a dedicated build model, handoff (/handoff-summary) are driven by the orchestrating workflow (agentic-workflow for the main model, build-model for a dedicated build model), not by this skill.
nikhilw/structured-agentic-workflow
Write a one-line compact command for the user to run, and a resume brief to paste right after it, carrying what the rest of the workflow needs past a context compaction: where the work stands, the owner's rulings, what only ever lived in the conversation, and how the owner wants this model to work. Suggested at the workflow's two compact slots (plan approved, before the build; before verify-completion), and usable any time the user asks for a compact prompt.
nikhilw/structured-agentic-workflow
Summarise what has been decided so far, in plain words, from two angles, what the user will get and how it works. Use when the user asks for a summary, a recap, or "what did we decide", during or after a brainstorm or a plan discussion. It is a capability, not a phase; it changes nothing and the discussion can carry on after it.
nikhilw/structured-agentic-workflow
The eight questions that must be answered about what a codebase already does before anything new is proposed, planned, or built, and the self-duplication inventory that catches a change duplicating its own code. Shared reference loaded by brainstorm, write-plan, build-phase and 3p-review. It is a reference, not a step of its own.
nikhilw/structured-agentic-workflow
Maintain and manage features and bugs on GitHub. Creates, updates, lists, and links GitHub issues and project cards.
nikhilw/structured-agentic-workflow
Emit the Build Handoff Summary artifact in its fixed format. Use at the end of a /build-model session, immediately after /3p-review passes. Produces the fixed handoff template the reviewing model consumes.
nikhilw/structured-agentic-workflow
The perspectives every review in this workflow looks through, one question each (impact, removal, logic, behaviour, business sense, proof, coherence), the checklist each lens walks, the defect kinds that keep coming back, the table of which gate runs which lens at what depth, and the brief for handing a review to an outside model. Shared reference loaded by brainstorm, write-plan and 3p-review. It is a reference, not a step of its own.
nikhilw/structured-agentic-workflow
Recommend what to work on next by reading the backlog (bugs.md, features.md, plans/) and considering what is already loaded in the current conversation context. Minimizes context thrash — prefers tasks aligned with current context. Recommends bugs when context is low, features when resources are plentiful.
nikhilw/structured-agentic-workflow
The final gate before any claim of "done", "fixed", or "passing", and before the commit or PR that closes the work. Runs three checks that nothing earlier in the workflow guarantees, a fresh full-suite result, a line-by-line tick-off of the plan's requirements, and a plan-drift audit from the decision document through the plan to the code. Evidence before assertions, always.
nikhilw/structured-agentic-workflow
Configure the Structured Agentic Development Workflow — set testing methodology (TDD/BDD), output style (caveman brevity), and persist preferences to agent memory.
nikhilw/structured-agentic-workflow
Write a formal phased implementation plan to docs/plans/new/. Use after brainstorming is complete and a direction has been chosen. Creates a plan file that decouples the planning agent from the building agent.
nikhilw/structured-agentic-workflow
Structured live troubleshooting for deviation problems: something worked (or should work) and now doesn't, and the cause is unknown. Staged method — quick likelihood-weighted tests first, escalating to a comparative IS/IS-NOT specification with distinctions-and-changes analysis when quick tests fail or the search space is large. Influenced by the problem-analysis tradition of Kepner & Tregoe. Works whether the user runs the tests (agent directs, user executes) or the agent can test directly.
air-gapped/skills
Tune and benchmark a healthy Ceph cluster, with Rook-on-Kubernetes specifics: mClock profiles and the NVMe capacity-fallback trap (osd_mclock_max_capacity_iops), osd_memory_target from pod requests, BlueStore allocation and cache defaults, PG autoscaler targets (mon_target_pg_per_osd, bulk, target_size_ratio), public/cluster network and Multus choices, msgr2 modes, Tentacle Fast EC (allow_ec_optimizations, stripe_unit), krbd vs rbd-nbd in ceph-csi, librbd cache, and benchmark method (rados bench, rbd bench, fio). Squid 19.2 and Tentacle 20.2.
air-gapped/skills
Run Ceph RGW as an S3 endpoint under Rook (CephObjectStore, CephObjectStoreUser, ObjectBucketClaim, COSI, CephBucketTopic, multisite realms/zones). Core knowledge: the 19.2.6 / 20.2.4 RGW security fixes and their fallout (SigV4 hardening rejecting presigned PUTs and RGW's own multisite forwarding; rgw_sigv4_insecure + rgw_s3_client_max_sig_ver), AWS SDK default checksums vs RGW (CRC64NVME only in Tentacle), bucket index sharding and large-omap warnings, Tentacle's two-phase reshard, RGW accounts (CephObjectStoreAccount, experimental), and Tentacle S3 behaviour changes (LastModified truncation, tenant IAM deprecation).
air-gapped/skills
Diagnose and recover an unhealthy Ceph cluster, with Rook-on-Kubernetes specifics: slow or stuck recovery/backfill under the mClock scheduler (why osd_max_backfills "does nothing"), nearfull/backfillfull/full, inconsistent/unfound/incomplete/down PGs, BLUESTORE_SLOW_OP_ALERT vs SLOW_OPS, OSD OOM kills from pod memory sizing, mon quorum loss and restore-quorum, OSD removal with the kubectl-rook-ceph plugin, stale RBD watchers after node loss, and field-reported failure modes on Squid 19.2 and Tentacle 20.2.
air-gapped/skills
Author, read, and debug Jinja2 templates across the three places Jinja lives in 2026 — HuggingFace `chat_template.jinja` (rendered by `apply_chat_template` for vLLM / sglang), Ansible playbooks + `.j2` files, and Jinja-adjacent Kubernetes workflows (`values.yaml.j2`, `kubernetes.core.k8s + template`, Helm post-renderers). Companion to the `helm` skill — Helm charts are Go `text/template` + Sprig, not Jinja, and this skill makes that disambiguation explicit.
air-gapped/skills
Plan and run a controlled, COMMUNITY-edition Grafana Mimir upgrade on the `mimir-distributed` Helm chart, air-gap first — the chart↔app co-pinned ladder (5.7→5.8→6.0.6→6.1.0 = app 2.16→2.17→3.0.4→3.1.2), the classic-vs-ingest-storage decision (the chart ships a supported `classic-architecture.yaml`; `kafka.enabled: false` alone is NOT the switch and causes an ingestion outage), the community-specific nginx→gateway rename that silently moves the proxy's DNS name and breaks every remote_write client, the silent-no-op vs crashloop asymmetry between stale chart keys and stale app config, rollout-operator sequencing and the abort levers that deadlock a namespace, per-hop verification, and air-gap image/CRD/egress work. Companion to k8s-components-checker.
air-gapped/skills
NetBox 4.2-4.7 deployment and upgrade knowledge the official netboxlabs/skills marketplace does not cover — deploying or upgrading NetBox on Kubernetes with the netbox-community helm chart (netbox-chart), external PostgreSQL/valkey wiring, API token bootstrap on 4.5+ (nbt_ v2 tokens), plugin installation in the official image, version-migration planning across 4.2-4.7, module type profiles, front/rear port (patch panel) API changes, and OIDC/SSO group-to-role mapping. Gap-filler only: for general NetBox data modeling, IPAM design, Diode, validation, or turning an auth backend on in the first place, prefer the official netbox-administration skill.
air-gapped/skills