save-toolkit

Plugin save-toolkit from marketplace otelyssey in using-system/otelyssey. Commands read from the repo's manifest — today.

Skills (25)

• agent-authoring

  Create, repair, or security-review LLM-facing prompts, agents, skills, tool descriptions, graders, bounded Loop Engineering for evaluation/verification, and agent roster/delegation graphs. Triggers: 'write me an agent/skill/prompt', 'my skill fires too often', 'the output is the wrong shape', 'is th

• akamai-edge

  Akamai edge work in three lanes — triage (edge vs origin, Reference # error strings, cache status, WAF denials, DataStream 2), delivery config (Property Manager versions, staging-first activation, fast fallback), and mPulse RUM (network-side vs app-side slowdowns). Triggers: 'is it the CDN or the or

• api-craft

  Design, build or change HTTP APIs, webhook receivers, and HTTP clients. Covers consumer contracts, integrations, failure behavior, and durable work accepted by an API. Triggers: 'add an endpoint', 'build an API', 'wrap X behind an API', 'integrate an upstream API'. Not for standalone workers, schedu

• ci-actions

  Review, design, troubleshoot, and optimize GitHub Actions workflows: fast feedback, caching, test matrices, reusable jobs, reproducible artifacts, and secure delivery. Includes advice-only workflow reviews when the caller asks for findings without edits. Triggers: 'set up CI', 'speed up this pipelin

• database-reliability

  Diagnose and improve data-layer reliability: slow queries, lock contention, replication lag, connection pools, schema migrations, and recovery evidence. Triggers: 'this query is slow', 'plan this schema migration', 'the connection pool is exhausted'. Not for app-side triage (pcf-ops), burn alerts (o

• frontend-craft

  Build or change web applications and SRE interfaces in React or Vue, from one page to a complete app integrated with its backend. Triggers: 'build a UI for', 'add a page/form/table/console', 'make this look less generic', 'wire the UI to the API'. Not for backend implementation (api-craft) or Grafan

• gcp-ops

  Investigate application-side GCP failures during the migration — Cloud Run services and revisions, gcloud logging reads, what-changed correlation against revision deploys, and the project-vs-platform boundary. Triggers: 'the Cloud Run service is 503ing', 'read the GCP logs', 'container failed to lis

• go-craft

  Write, refactor, modernize, or test Go in services, CLIs, libraries, and workers. Load before editing Go, including module upgrades and concurrent code. Triggers: 'build this in Go', 'refactor this Go package', 'modernize this Go module', 'test this Go worker'. Not for runtime-only operations; use i

• grafana

  Design, explain, create, and edit Grafana dashboards; inspect alert state and notification paths; operate Grafana-managed alert rules and temporary silences. Triggers: 'design a dashboard', 'edit this Grafana dashboard', 'create a Grafana alert', 'silence this alert'. Alert/SLO design uses obs-alert

• incident-investigation

  Use before coaching a human through an incident: interpreting evidence, choosing a next check, correcting an assessment, comparing mitigation, checking recovery, or handing over. This includes synthetic incidents and drills in the advisor role, even with supplied evidence or a required response form

• obs-alerting

  Design alerting that pages on symptoms — SLIs/SLOs and multi-window burn rates, Splunk saved-search alerts, Moogsoft correlation, and ThousandEyes synthetics. Triggers: 'define an SLO', 'this alert is too noisy', 'what should page', 'design a synthetic check'. Not for signal queries or interpretatio

• obs-analysis

  Query and interpret logs, metrics, and traces: signal meaning, request correlation, and bounded comparisons. Triggers: 'search the logs', 'write a metric query', 'trace this request', 'explain this telemetry'. Live incident decisions use incident-investigation; alert/SLO design uses obs-alerting, Gr

• obs-pipeline

  What ships telemetry where — instrument a service with OTel and route metrics, traces, and structured logs through Alloy/collectors to Loki, Mimir, and Tempo. Triggers: 'instrument this service', 'add telemetry', 'logs are not reaching Loki', 'configure the Alloy exporter'. Not for reading signals (

• operational-docs

  Apply repository templates and evidence rules to resolved-incident retrospective intake and postmortem drafting, runbook creation or edits, and durable service or alert knowledge. Also covers Confluence runbook imports and ownership or dependency lookup from existing cards. Triggers: 'draft the retr

• operator-cli

  Build or repair an operator-facing CLI that works interactively and in automation, including partial failures, machine output, dry runs, and interruption. Triggers: 'build an operator CLI', 'make this command safe for automation', 'fix this CLI contract'. Not for running an existing operational comm

• pcf-deploy

  Plan human-approved VMware TAS/PCF application deploys, blue-green cutovers, scaling, and rollback verification. Triggers: 'deploy this app to PCF', 'design a blue-green deploy', 'scale this PCF app'. Not for readiness (production-change-gate) or incident mitigation advice (incident-investigation).

• pcf-ops

  Investigate application-side PCF/TAS failures with cf app, events, logs, and routes, and distinguish app faults from platform-wide symptoms. Triggers: 'the app is crashing', 'why is my app 502-ing', 'exit code 137', 'X-Cf-RouterError'. Not for widespread Diego/Gorouter failures, which go to the plat

• production-change-gate

  Gate the path from code to production with one checklist per question: is this change ready to merge, is this build ready to ship, and may this exact action run against production. Records a human decision and never executes. Triggers: 'is this ready to merge', 'is this build ready to ship', 'can I

• python-craft

  Write, refactor, or modernize Python in services, CLIs, scripts, libraries, and tests, routine or difficult: simplify structure, reduce duplicated logic, fix established defects, and replace custom machinery with suitable maintained libraries. Load before editing any Python; also use for explanation

• python-engineering

  Implement, modify, refactor, modernize, and verify Python code, dependencies, packaging, and quality gates. Use when creating Python scripts, CLIs, libraries, or services; restructuring or modernizing legacy Python modules; selecting or replacing packages; or establishing pytest, Ruff, and type-chec

• resilience-analysis

  Analyze failure propagation and design service resilience using source, configuration, operational evidence, and explicit assumptions. Triggers: 'what happens if this dependency slows down', 'find resilience weaknesses', 'design a safer recovery path'. Covers capacity under failure, partial completi

• root-cause

  Use when diagnosing a bug, test failure, or unexpected behavior before permanent remediation, and especially after a fix attempt has already failed, or when guessing has started ("maybe it's X, let me try changing it"). Triggers: 'debug this failure', 'why did this test fail', 'the fix did not work'

• stack-profile

  What this team runs today: the current stack, which stacks it authors versus only supports, the stay-in-lane rule, and the platform boundary. Load before editing code in a support-only stack (Java/JVM), before recommending any runtime, tool, or infrastructure change, and when choosing between observ

• toil-reduction

  Analyze recurring operational work and design measurable elimination, simplification, self-service or automation improvements. Triggers: 'reduce these repeated manual interventions', 'which toil should we automate', 'is this automation worth maintaining'. Uses frequency, effort, interruption, rework

• workflow-graph-engineering

  Design or review a portable executable workflow/state graph: typed state, node and edge classes, fan-out/fan-in, scheduling, retries, idempotent effects, approvals, durability, cancellation, termination, taint, and graph-level evals, without choosing a runtime. Triggers: 'design the workflow graph',

Slash commands (1)

• /save-toolkit:adr

  Scaffold a self-contained Nygard Architecture Decision Record under docs/decisions. Invoke manually with software-engineer or principal-engineer selected. Triggers: 'create an ADR', 'scaffold an architecture decision record'.

Subagents (9)

• observability-engineer

  Create and improve observability: Grafana dashboards, alert rules and silences, SLIs/SLOs, error budgets, and telemetry pipelines across Alloy/Loki/Tempo/Mimir/Prometheus and Splunk/Wavefront/Moogsoft/ThousandEyes. Triggers: \"set up monitoring\", \"create a Grafana alert\", \"silence this alert\",

• principal-engineer

  Design and architecture for team-owned software before it is built: shared API, schema, or event contract changes, cross-service designs, migrations, hard-to-reverse choices, the architecture of a new service or major component, and tool or platform selection. Use for 'design how we change this cont

• reliability-engineer

  Assess service reliability risks, analyze resilience and capacity, design engineering improvements, and reduce recurring operational toil. Use for 'find reliability weaknesses', 'what happens when this dependency slows down', 'design a safer recovery path', or 'reduce these repeated manual intervent

• repository-investigator

  Use this agent when a question must be answered from the current local checkout: find where code or configuration is defined, trace call sites and data flow, explain how this repository works, compare local files, or verify private or uncommitted implementation. It returns cited file:line evidence a

• researcher

  Use this agent for extended public research, version comparisons, conflicting sources, or a bounded external question another agent needs help answering. Covers official documentation, RFCs, vendor APIs, upstream code and tests, packages, vulnerabilities, and changelogs. Returns a concise cited answ

• reviewer

  Independent correctness and security review of a change, diff, commit, branch, or PR, including a design doc or ADR before it merges. Investigates history and affected consumers, verifies behavior with checks in a scratch copy, and reports evidence-backed findings with a merge verdict. Use for 'revi

• scribe

  Create or update evidence-bound operational documentation: runbooks, resolved-incident postmortems, and operations-KB records for approved services, applications, or alerts. Triggers: \"write the runbook\", \"write the postmortem\", \"update the operations KB\", \"document this new service, applicat

• software-engineer

  Delegate implementation here: use this agent to build, fix, refactor, modernize, and test code and operations tooling end to end — backend services, APIs, CLIs, automation, operator web UIs — in the language the repository already uses, shipped with its operational surface (logs, timeouts, dry-run,

• sre-assistant

  Answer bounded read-only operational lookups and investigations for a human SRE or invoking agent/workflow; return evidence, limits, and recommendations to the caller. Use for \"check order-service events and logs\", \"investigate order-entry latency\", or \"compare failing regions and dependencies\

Hooks (3)

• PreToolUse

  IN=$(cat); G="${CLAUDE_PLUGIN_ROOT}/scripts/readonly-guard.py"; TRACE=; for C in python3 python py; do command -v "$C" >/dev/null 2>&1 || { TRACE="${TRACE}${C}=missing;"; continue; }; OUT=$(printf '%s

• PreToolUse

  powershell.exe -NoProfile -ExecutionPolicy Bypass -File "${CLAUDE_PLUGIN_ROOT}/scripts/readonly-guard-hook.ps1"

• SessionStart

  F="${CLAUDE_PLUGIN_ROOT}/scripts/guard-session-preflight.py"; TRACE=; REASON=; for C in python3 python py; do command -v "$C" >/dev/null 2>&1 || { TRACE="${TRACE}${C}=missing;"; continue; }; OUT=$("$C

Similar plugins