Explore skills

Analyze Strava-derived fitness notes that already exist in an Obsidian vault, then generate deeper dashboards, proxy training-load metrics, trend reports, and visual summaries. Use when the user wants post-sync analysis of existing workout notes rather than fetching new data from Strava.

Create forward-looking training plans from Strava-derived fitness notes already stored in an Obsidian vault. Use when the user wants a realistic next-week or next-two-week plan generated from recent load, consistency, sport mix, and recovery signals in their existing notes.

Use when at or near the 80% mark of a deliverable and the temptation is to keep polishing past good-enough. The 80/20 rule encapsulated — the last 20% of polish often consumes 80% of remaining time and rarely changes the operator's decision. Distinguished from chengyu-retreat-is-best (abandon FAILED approach) and from chengyu-great-wisdom-looks-foolish / chengyu-words-concise-meaning-complete (res

Use when about to commit, create a PR, or declare work complete — after verification-before-completion confirms tests pass but before code ships. Catches security vulnerabilities, logic errors, and business rule bugs that slip through despite passing tests.

Deep fluency in modern Python (3.14+) for production systems. Use when writing Python code, designing APIs, building data pipelines, creating async services, or optimizing performance. Covers typing, tooling (uv/pyright/ruff), FastAPI, Polars, observability, and engineering judgment.

Lightweight web search via DuckDuckGo with BM25 relevance ranking. Use when asked to search the web, look something up, find recent information, research a topic, or browse the internet. Trigger phrases: search the web, look up, find information about, google, browse the web, web search, find recent, what is the latest on.

Use when facing a task too large to hold in one piece — decompose into atomic subtasks. Divide-and-conquer in chengyu form. Pairs naturally with subagent dispatch (each part becomes one subagent's job) and with the dispatching-parallel-agents superpower. The decomposition itself is the skill — the parts should each have one clear purpose and a well-defined interface to the others.

Use when planning any non-trivial change — refactor, bug fix, migration, optimisation, communication — and the agent should find the natural seams / high-leverage points of the target system rather than brute-forcing through. Cut at joints (low resistance, clean result), not at bone (high resistance, blade dulls, messy result). The patron-saint chengyu of working WITH the grain of the system.

Use when a symptom has an OBVIOUS causal root and the temptation is to patch the symptom — when a bug fix is masking the real issue, when retries are hiding a contract violation, when a workaround is becoming permanent. The default debugging frame; reach for chengyu-besiege-wei-save-zhao only after exhausting this.

Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Analyze session history to identify inefficiency patterns and workflow gaps. Two modes: lightweight end-of-session reflection from conversation context, or comprehensive periodic analysis across multiple sessions via jq-extracted JSONL summaries. Produces structured reports with copy-paste-ready improvement proposals for CLAUDE.md, skills, commands, and automation.

Validates Containerfile COPY commands and Kubernetes manifest paths for consistency. Automatically runs when working with Containerfiles or K8s manifests to ensure source paths exist and destinations match between files.