Trending Skills
The hottest skills gaining momentum in the community right now.
Gameplay Audit (P2/P3 slice, M41–M42)
by matiaszanolli
"Deep audit of the gameplay layer in byroredux/src — inventory/equipment, interaction/locks/loot persistence, consumables, combat + death, NPC spawn → AI packages → locomotion, player feedback, gameplay-state save coverage and stage order"
source-command-audit-runtime-skill
by matiaszanolli
Audit ByroRedux runtime telemetry by driving a headless engine on per-game cells, diffing stats against checked-in baselines, and reporting the state of the smoke / golden-frame gate matrix. Use when the user requests a runtime telemetry, capture, or gate-matrix audit.
source-command-audit-severity
by matiaszanolli
Unified severity scale for ByroRedux audit findings — CRITICAL/HIGH/MEDIUM/LOW definitions, special rules, and the decision tree. Use when assigning or reviewing the severity of an audit finding.
Concurrency and Synchronization Audit
by matiaszanolli
"Audit Vulkan queue/AS sync, ECS lock ordering, scheduler access declarations, RwLock patterns, deadlock potential"
source-command-audit-fnv-skill
by matiaszanolli
Audit Fallout New Vegas compatibility — the reference title covering cell load, ESM/NIF data, ragdoll, ambient AI and dialogue, consumables, and HUD profile. Use when the user requests a Fallout New Vegas or FNV compatibility audit.
source-command-audit-owners
by matiaszanolli
The ByroRedux audit ownership map — path prefix to owning audit(s) and risk floor, used for incremental routing, suite coverage, and validator gap detection. Use when routing a changed file to its audit, checking audit coverage of a path, or editing ownership rows.
Legacy Compatibility Audit
by matiaszanolli
"Audit compatibility gaps between Gamebryo 2.3 and Redux — what's mapped, what's missing"
Audio Subsystem Audit (M44)
by matiaszanolli
"Deep audit of the M44 audio subsystem — kira backend, spatial sub-tracks, listener/unit seam, reverb send, underwater filter, streaming music — plus its engine callers (footsteps, water audio, reverb zones, REGN ambient music)"
source-command-audit-performance-skill
by matiaszanolli
Audit ByroRedux GPU/CPU performance — CPU hot paths, per-frame allocation churn, draw batching and instancing, GPU memory pressure and eviction thrash, SSBO sizing and upload cost, pass cost, streaming stalls, and telemetry. Use when the user requests a performance, frame-time, hot-path, GPU-cost, or bench audit.
source-command-audit-incremental-skill
by matiaszanolli
Audit only recently changed ByroRedux code for new bugs, regressions, contract breaks, unsafe deltas, and missing tests. Use when the user requests an incremental, delta, working-tree, commit-range, or since-date audit.
source-command-audit-gameplay-skill
by matiaszanolli
Audit ByroRedux's gameplay layer in byroredux/src — inventory/equipment, interaction/locks/loot persistence, consumables, combat + death, NPC spawn → AI packages → locomotion, player feedback, gameplay-state save coverage and stage order. Use when the user requests a gameplay, combat, inventory, or AI-package audit.
announcing-behavior-changes
by PostHog
Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later. Use when a change alters what an existing user sees without them doing anything — a metric moves, a chart shifts, a count drops, a date range resolves differently, a matcher matches differently — and when adding, reviewing, or removing such a notice. Trigger terms: behavior change, breaking change, semantics change, "results may differ", change notice, deprecation banner, migration banner. Carries the gate (narrow to the affected users with a tested predicate, or do not ship a notice at all), the pattern from SqlInsightDateFilterNotice, where to anchor the notice, and the flag-based removal path. Not for new features (use the changelog), not for permanent per-object warnings computed by the backend, and not for the wording itself (see /writing-user-facing-copy).
triaging-merge-queue-failures
by PostHog
Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate that failed on a cancelled run, real failure, one-off flake, or repo-wide flaky/infra issue) and take the matching action (wait, hold and fix, requeue once, or escalate instead of spam-retrying). Use when a PR is kicked from the queue, Trunk reports a failed queue attempt on a PR, someone asks "why was my PR removed from the queue" or "should I requeue", or when running as the scheduled merge queue triage sweep. Trigger terms: merge queue kicked, removed from queue, queue failure, requeue, trunk merge failed. Operators setting up the automation itself: see references/routine-setup.md.
api-provider-setup
by aAAaqwq
添加和配置第三方 API 中转站供应商到 OpenClaw。当用户需要添加新的 API 供应商、配置中转站、设置自定义模型端点时使用此技能。支持 Anthropic 兼容和 OpenAI 兼容的 API 格式。
openclaw-update
by openclaw
"Route routine updates of an existing local or remote OpenClaw Gateway to its installation owner, with automatic session recovery. Defer to deployment-specific skills when available."
agent-md-advisor
by chujianyun
AGENTS.md / CLAUDE.md 最佳实践顾问。用于用户询问 agents markdown、AGENTS.md、CLAUDE.md、Claude Code memory、AI coding agent 指令文件的格式、结构、最佳实践；也用于审查、诊断、重写、优化或从零创建 AGENTS.md、CLAUDE.md、CLAUDE.local.md、.claude/rules 等 agent 指令文件。不适用于通用 README 写作，除非目标是给 AI coding agent 提供项目上下文。
claude-code-plugins
by melodic-software
"Report the Claude Code permission state in effect: merges every settings scope into the effective allow/ask/deny set, each rule with its source and precedence, and flags allow rules auto mode drops. Report-only. Use when: 'what permissions are actually in effect', 'show me my effective permissions', 'which of my rules survive auto mode', 'is my managed policy being read', or before changing a rule whose source is unknown. A rule ignored for its shape: audit-permission-grants."
claude-code-plugins
by melodic-software
"Validate the discipline plugin's configuration, the posture-batch overlay and do-your-research-deep's verification depth, and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up discipline', 'configure discipline', 'discipline setup', 'is discipline configured', 'what's in my posture batch', 'what's my deep-research depth', or the user wants to adjust which correctors the batch runs or how deeply the research fan-out verifies. Actions: check (read-only verification, default and only action. This plugin's entire configuration is native userConfig, so there is nothing an apply could write)."
widgets
by SamSaffron
"Build, install, inspect, and debug term-llm Web UI widgets. Use when adding local widget apps, editing widget manifests, checking widget routes, or explaining how /chat/widgets works."
audit-comments
by mycelium-io
Cheap-model audit of comments and inline docs for temporal/historical narration, overly long prose, over-referencing of GitHub issues / PR numbers / plan-step IDs, and design-justification / conversational residue (comments that defend the approach or echo how the code was steered instead of plainly describing it). Defaults to the current PR diff; pass --all to sweep the whole codebase, --fix to apply the rewrites. Use when the user says "audit comments", "comment cleanup", "tidy comments", "check the comments", or "audit-comments".
jobs
by SamSaffron
"Work with scheduled jobs and container services. Use when creating, updating, pausing, debugging, or inspecting jobs; checking runs/events; or changing runit services like webui and jobs."
memory
by SamSaffron
"Read and update persistent memory. Use when: user says 'remember', asks about past context, preferences, or projects. Also use proactively to save anything reusable before a conversation ends."
self
by SamSaffron
"Modify this agent: system prompt, agent.yaml, scripts, or memory structure. Use when asked to update behavior, personality, memory rules, or configuration."
exploring-llm-traces
by PostHog
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against events.properties.$ai_input / $ai_output_choices returns empty — message content lives only on the dedicated posthog.ai_events table.