๐
Plugins
Loading...
Showing 30 of 14565 results
Changelog & Release Communication Engineer โ Changelog and release communication โ breaking change docs, deprecation notices, migration guides
from ComposioHQ/awesome-claude-skills
Automated changelog generation from git commits
Use this skill when users need to validate their marketing channel strategy, assess channel focus, o
Infrastructure Specialist Team โ Chaos: Chaos engineering โ failure injection design, game days, resilience testing, blast radius control
End-to-end chaos engineering discipline: design experiments with hypothesis + steady-state metric + blast radius + abort criteria, calculate risk score against error budget, and generate blameless postmortems. 3 stdlib Python tools (experiment_designer, blast_radius_calculator, experiment_postmortem), 4 references on chaos principles + experiment design + 7-attack taxonomy + tooling landscape (Chaos Toolkit/Mesh/Litmus/Gremlin/AWS FIS/DIY), templates, and /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (chaos targets).
Chaos engineering orchestration plugin. Manages chaos experiments via Toxiproxy, chaos-monkey scripts, and kubectl. Schedules regular chaos game days, tracks experiment results over time, and verifies steady-state hypotheses automatically. Integrates with Grafana for before/after metric comparison.
Chaos engineering scenarios for resilience testing. Designs fault injection experiments (network partitions, latency injection, dependency failures, disk pressure, memory leaks) and verifies circuit breakers, retries, and fallbacks work correctly. Use when building resilience features, verifying SLO under failure conditions, or preparing for production chaos days.
Unified ChapterWise plugin โ manuscript import, AI analysis, story atlas, static reader, codex utilities, and more
from ansonphong/chapterwise-claude-plugins
from ansonphong/chapterwise-claude-plugins
from ansonphong/chapterwise-claude-plugins
from williavs/charm-dev-skill-marketplace
Know the project + own the owner relationship. At SessionStart, a compact proportional brief that gates substantive work on the project's Claude-facing docs: quality attributes (Lighthouse-aligned for web), a project map (fileโresponsibility index, for blast radius), recorded decisions/ADRs (the alignment anchor โ don't reverse without consulting), a roadmap/backlog, stack notes, and the project's established conventions (reuse before create) โ generating them from code/git when missing and going quiet once they're summarised in CLAUDE.md (claude-companion marker). Surfaces outcome memory โ "scar tissue": files this project has REPEATEDLY had to FIX, derived from git history by the rework ratio (fix/revert commits over total touching a file), not raw churn โ so the review loop treats debt magnets as high-risk (understand why they churn, cover them, prefer the smallest change, or simplify an over-built abstraction) before extending them; surfaced even in quiet mode (it's state, not policy), silent on a clean/new repo. Owns the non-technical owner loop: confirm intent in plain language โ demonstrate the result back โ recap. Adds an alignment floor โ a bounded Stop hook (the outcome-time complement to the review loop's intent-time alignment): when a finished change plausibly bears on a recorded decision (a dependency manifest / config / migration changed, or a backtick-fenced decision token appears in the diff), it blocks once and puts the recorded decisions in front of the model โ honor them, or, if the change reverses/contradicts one, surface that to the owner in plain language and confirm before it lands. Silent on routine edits and on projects with no recorded decisions; bounded (โค CLAUDE_CHARTER_ALIGN_MAX blocks/session, never twice for the same tree) so it can't loop; disable with CLAUDE_CHARTER_ALIGN_GATE=0. /charter:align reconciles open/proposed work against recorded decisions + roadmap on demand (clean โ correct). Action-time consent for consequential/irreversible operations is enforced natively (settings.json auto mode + deny/ask rules), not a charter hook. MCP reachability probe: a second SessionStart hook checks that the MCP servers DECLARED for this project (merged read-only from ~/.claude.json, .mcp.json, and .claude/settings*.json) actually respond โ briefly spawning each stdio server for the MCP initialize handshake and POSTing it to each http/sse endpoint, every probe hard-bounded by a per-server timeout and run in parallel โ so the silent failure mode (a mis-installed/unreachable server whose tools just never appear) is surfaced to a non-technical owner in plain language; an HTTP auth challenge counts as reachable (not down), only a fresh start probes (not compact/resume), self-disables when no servers are declared, never blocks, and disables with CLAUDE_CHARTER_MCP_PROBE=0. Read-only over the project except for cache-only throttle state โ it detects and the model authors the docs.
Prepare scoped ChatGPT Pro review packets and reconcile feedback against local repo evidence.
Apple platform development toolkit โ build, deploy, debug, device management, Apple OAuth setup for Xcode projects
from PsychQuant/psychquant-claude-plugins
from PsychQuant/psychquant-claude-plugins
Axiomatization Systems โ ่ทจ้ ๅๅฝขๅผๅๅ ฌ็้ซ็ณป็ๅปบ็ซใ้ฉ่ญ่ๆฅ่ฉขใๅบๆผ ASBE ๆนๆณ่ซใaxiom-createใaxiom-validateใaxiom-lookup