AI & ML

hoangsonww Bundle

Detect quality and efficiency regressions over time using Agent Monitor data — rising error rate (APIError events), falling cache hit rate, growing compaction frequency, and climbing cost-per-session. Splits history into an earlier baseline window and a recent window and reports which metrics are getting worse, by how much, and where. Use when checking whether things are degrading or trending in the wrong direction.

hoangsonww Bundle

Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data. Pairs PreToolUse with PostToolUse to compute tool durations and surfaces gaps, errors, and compaction points. Use when reconstructing what happened in a session step by step.

hoangsonww Bundle

Quick dashboard health and status overview — checks the Agent Monitor API (port 4820), reports session/agent/event counts from /api/stats, confirms WebSocket connectivity, reads the redacted hook status returned by /api/settings/info, and shows data freshness (last event timestamp). Use to verify the monitoring system is operational.

hoangsonww Bundle

Compile a weekly productivity report using Agent Monitor data — daily_sessions and daily_events trends, per-session costs from pricing engine, token volumes (input/output/cache_read/cache_write + baselines), tool usage top 20, session completion rates by status, and workflow intelligence metrics.

hoangsonww Bundle

Audit hook delivery health from Agent Monitor data — balance PreToolUse vs PostToolUse (a gap means tools that started but never reported back), detect missing Stop/SubagentStop terminators (sessions/subagents that never closed), and check for stale ingestion (no recent events). Use when hooks look unreliable or events seem to be dropping.

hoangsonww Bundle

Walk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, turn_count). Use when reviewing what was actually said and done in a conversation.

ils15 Skill

Build MCP servers with Python FastMCP and TypeScript SDK — tools, resources, prompts, and transport configuration.

ils15 Skill

Practical step-by-step walkthrough for orchestrating features end-to-end using the multi-agent system, from planning through deployment

ils15 Skill

Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instructions.

christian289 Skill

Releases a new version of the WpfDevPackMcp NuGet MCP server (the server under mcp/), which is versioned independently of the wpf-dev-pack plugin and of knowledge content. Bumps the four version strings that must stay in lockstep (csproj <Version>, the dnx pin in wpf-dev-pack/.mcp.json, and BOTH version fields in mcp/.mcp/server.json), then builds, packs, pushes to NuGet, re-pins after the package goes live, and optionally re-publishes to the Official MCP Registry. Use when code under mcp/ or its packaging changed and must be republished. Do NOT use for knowledge-topic edits (served live, no version bump) or plugin-only changes (use /wpf-dev-pack-release). Usage: /releasing-wpfdevpackmcp [version e.g. 0.1.4]

vinnie357 Bundle

Guide for building LLM clients in Rust with rig (rig-core) — AgentBuilder, providers, tools, extractors, RAG, and streaming. Use when writing Rust LLM clients with rig or rig-core, building multi-provider or hybrid clients that mix Anthropic, OpenAI, Gemini, or local models, integrating ollama, LM Studio, or an OpenAI-compatible gateway (LiteLLM, Bifrost, Lemonade Server) from Rust, or implementing rig agents, tools, extractors, or RAG pipelines.

vinnie357 Bundle

Generic epic-to-PR agent workflow (codename Forge) with 4-phase execution, a 6-tier hierarchy, and paired-team fan-out. Use when coordinating any feature delivery, working an issue or epic ("work epic <id>", "work issue <id>", "use Forge on the next bees ready item", "forge <id>"), picking up an epic in a fresh session (decomposing path) or with pre-existing issues (dispatching path), implementing a multi-step task that benefits from plan→test→implement→review phases, asking clarifying questions before decomposing, forming a team and assigning models per tier, or orchestrating multi-agent workflows. Loads on casual feature requests too — not only when the word "epic" appears.

bitwarden Bundle

This skill should be used when the user asks to "create a threat model", "define security goals", "generate a data flow diagram", "write security definitions", "perform an initial security assessment", or needs to produce threat model artifacts for new features or architecture changes.

bitwarden Skill

Use this skill when posting the final summary comment, including its No Verdict form when nothing could be reviewed and no inline comments exist. Otherwise apply as the LAST step of code review, after all findings are classified and inline comments are complete. Detects context (caller-declared local-file output, agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.

hoangsonww Bundle

Audit model delegation and subagent effectiveness for a session — which models handled which subagent types, per-type success rates and average durations, and wasted delegations (heavy models on trivial work or types that consistently fail) — using the Agent Monitor workflow intelligence API. Use when reviewing how a session delegated work across models and subagents.

hoangsonww Bundle

Summarize a sprint's worth of Claude Code activity — sessions grouped by project (cwd), per-model cost breakdown, token efficiency (cache hit rate, compaction baselines), subagent effectiveness from workflow API, velocity metrics (turn_count, turn_duration_ms), and tool diversity across the sprint.

hoangsonww Bundle

Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.

hoangsonww Bundle

Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.

hoangsonww Bundle

Run a daily spend check-in against a daily budget on the Agent Monitor dashboard — today's spend vs the daily target, pace through the day, and the projected overage if the current pace holds. Uses /api/pricing/cost and /api/sessions (grouped by started_at = today). Use for a quick daily spend check-in or a morning/evening budget pulse.

hoangsonww Bundle

Analyze workflow patterns using the Agent Monitor's workflow intelligence API — orchestration DAGs, tool flow transitions, subagent effectiveness, model delegation patterns, error propagation by depth, concurrency lanes, compaction impact, and agent co-occurrence. Produces prioritized optimization recommendations with quantified impact.

seflless Bundle

Audit a repo's tooling for coding agent self-verification. Use when the user wants to audit agent tooling, mentions "agent-dx", "agent developer experience", "what testing tools do I need", "set up verification for agents", "how can agents test this", or when onboarding to a new codebase and want to know what verification tools are missing.

seflless Bundle

Syncs coding agent config files so AGENTS.md is source of truth and CLAUDE.md/instructions.md are symlinks. Ensures skills and commands are shared across Claude, Codex, Cursor, and opencode. Use when adding skills, commands, or modifying agent config.

seflless Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

vinnie357 Bundle

Guide for using awman to run AI coding agents in isolated containers with multi-step workflows and a REST API. Use when configuring parallel agent sessions, authoring awman workflows, driving the awman api server, managing worktrees, migrating from amux, or troubleshooting awman container runs.

gmickel Bundle

Synthesize the current conversation context into a flow-next spec at `.flow/specs/<spec-id>.md` via `flowctl spec create + spec set-plan` — agent-native, source-tagged, with mandatory read-back before write. Triggers on /flow-next:capture, "capture spec", "lock down what we discussed", "make a spec from this conversation", "convert conversation to spec". Optional `mode:autofix` token runs without questions and requires `--yes` to commit. Optional `--rewrite <spec-id>` overwrites an existing spec; `--from-compacted-ok` overrides the compaction-detection refusal; `--override-strategy` proceeds despite a contradiction with an active STRATEGY.md track (and prompts to record the override as a decision).

gmickel Bundle

Wrap `clawpatch map` to produce a semantic feature index of the repo (~20 languages, persisted at `.clawpatch/features/*.json`). Detects install, runs `clawpatch init` when `.clawpatch/` absent, invokes provider-free `clawpatch map --source heuristic` by default; `--source auto|agent` flows through as passthrough. Opt-in enrichment — scouts and prime read the resulting index, but flowctl never depends on clawpatch.

seflless Bundle

Expert guidance for creating Claude Code skills and slash commands. Use when working with SKILL.md files, authoring new skills, improving existing skills, creating slash commands, or understanding skill structure and best practices.

vinnie357 Bundle

Allium behavioral specs integrated with /core:agent-loop. Use when attaching a formal spec to an epic, propagating tests from a spec before TDD, or weed-checking spec/code divergence after CI passes.

vinnie357 Bundle

Linear project management via MCP or GraphQL API: issue queries, state transitions, epic authoring for VantageEx agent teams, and epic auditing. Use when interacting with Linear issues, creating or auditing epics, querying workflow states, or managing Linear project data.

gmickel Skill

Prompt-first router that recommends the smallest sufficient flow-next workflow. Use when unsure which command to run next, which pre-build stage applies, or whether to skip chart/interview/plan. Triggers on /flow-next:guide with a free-form situation description.

gmickel Bundle

Comprehensive codebase assessment for agent and production readiness. Classifies the project (lifecycle, topology, size, stack, shape), scans 8 pillars, verifies commands actually run, checks GitHub settings. Leads with a verdict + ranked next-actions; fixes agent readiness only. Triggers on /flow-next:prime.

gmickel Bundle

Optional local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions, plus a commented model-routing example proposed into the project instruction file. Use when user runs /flow-next:setup.

bitwarden Bundle

Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md, agents, prompts, commands, hooks, or settings. Routes each file type to a targeted review skill and returns classified findings. Flags settings.local.json appearing in a changeset, hardcoded secrets, malformed YAML, insecure agent tool access, and unsafe hook commands. Does not review SKILL.md files — plugin-dev:skill-reviewer owns those.

ninehills Bundle

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application code or reviewing PRs.

ninehills Skill

Oracle second-model review: bundle prompts/files, debug, refactor, design-check.

vinnie357 Bundle

Controlled-language rules for technical writing in two registers — strict mode for procedural text and flavored mode for explanatory prose. Strict mode covers skill descriptions, procedure steps, agent definitions, output contracts, error text, and issue acceptance criteria. Flavored mode covers references, READMEs, ADR rationale, and PR bodies. Use when authoring or editing a SKILL.md, a skill description, an agent definition, a bees issue, an ADR, or a README. Use when reviewing prose for passive voice, hedged directives, terms used with two meanings, or overlong sentences.