Audit the current project's website for AI-agent readiness using Cloudflare's isitagentready.com scanner (robots.txt, sitemap, llms.txt, Link headers, Content Signals, Markdown-for-Agents, MCP / OAuth / A2A / Agent-Skills discovery, agentic commerce), triage which gaps are actually worth fixing for THIS kind of site…
Analyze prompt cache hit rates, estimate cost savings from cached system prompts and memories, and recommend improvements to caching strategy. Use when checking cache performance, investigating high token costs, optimizing cache hit rates, or diagnosing slow cache warmup.
Preserve the OPERATIONAL THREAD across coding sessions with a repo-local, inspectable .continuity/ surface and a resume -> work -> finalize lifecycle. Not another memory store — a thin lifecycle layer over the memory you already have. Use at the START of substantial work on a repo ("resume", "where were we", "pick…
Initialize Claude Code optimization for a new project — detect stack, create memories, generate constitution, configure settings. Use when starting in a fresh/uninitialized project or the user says "init project"/"set up Claude Code here"; skip on an already-initialized project.
Reduce token usage by selecting a planning strategy, loading Serena memories, enforcing symbol-first exploration, and reporting savings. Use when starting a non-trivial task, asking to reduce token costs, requesting efficient execution, or wanting optimized Claude Code workflows.
Close the loop on a skill/prompt/convention library: mine recurring review feedback into rules, fold them back into the generator, and gate every change through a tiered evaluation (deterministic lint + trigger accuracy + LLM judge, plus a with/without-skill behavioral eval) that converges instead of drifting. Use…
Search the web for latest Claude API changes, compare findings to existing documentation, and apply targeted updates to keep prompts and configs current. Use when docs are outdated, after a Claude API update, to refresh system prompts, or to validate documentation accuracy.
This skill should be used when performing legal and regulatory compliance audits on software projects. It covers GDPR, CCPA/CPRA, ePrivacy Directive, HIPAA, PCI DSS, SOC 2, and WCAG 2.2 accessibility. The skill generates a full compliance package: audit report with severity ratings, automatic code fixes, legal…
Merges finished feature branches into develop, syncs master/main with develop, commits any uncommitted changes, and deletes the merged feature branches plus those triaged as Close (local and remote); unmerged work it did not close is kept and reported. Handles git submodules automatically. Use when you want to clean…
Optimize PNG and JPEG images locally using pngquant and mozjpeg/jpegtran — TinyPNG-level compression without API keys. Use when compressing images before web deploy or asked to optimize/shrink a directory of image assets.
Audit or install maximum-depth 1Password integration in the current project — fetches fresh 1Password developer docs first, detects existing integration, and either reviews/improves it or greenfield-installs (Service Account secret resolution + site-compat autocomplete/well-known). Stack-aware (Laravel, Node/Next…
Manage Serena memories and session context — load, save, refresh, inspect, and clear project knowledge. Use when loading or saving project memories (/ctx load, /ctx save). Not the built-in /context, which shows context-window usage.
Turn a video (YouTube or anything yt-dlp supports, or a local audio/video file such as a lecture recording) into a short digest in the user's language, linked to existing notes and with fact-checked takeaways, then on request save it to a knowledge store (Svod or a markdown folder). Uses existing subtitles first…
Spawn an agent team for parallel work — PR review, competing hypotheses debugging, or independent module implementation. Use only when teammates genuinely need to work simultaneously and communicate with each other.
Deep, grounded codebase research/audit using parallel background agents — on a LOCAL project OR a GIT repo (clone first). Produces a durable, cross-linked knowledge base. Use for "analyze/audit this codebase", "what's built / what's missing / security / gaps / ui-ux", "review every line", researching an unfamiliar…
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
Pre-implementation confidence assessment (≥90% required). Use before starting a non-trivial implementation — a new feature, an unfamiliar area or a bug whose cause is unclear — to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.…
Run a full sprint lifecycle — chain skills into Think → Plan → Build → Review → Test → Ship → Reflect.
★not rated 91 9d agoA28 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: