wagner-skills

Use when building, designing, reviewing, or evaluating command-line tools for AI agent consumption -- structures commands with machine-readable JSON output on stdout, human diagnostics on stderr, adds --json/--fields/--dry-run/--quiet flags, implements semantic exit codes, enforces TTY-aware dual-mode output, hardens input against path traversal and injection, creates CONTEXT.md and AGENTS.md agent knowledge files, adds --help-json schema introspection, and scores CLI agent-friendliness on a 0-21 rubric across 7 axes. Triggers on: 'agent-friendly CLI', 'CLI for agents', 'build a CLI', 'design CLI commands', 'machine-readable output', '--help-json', 'CLI scoring', 'agent DX', 'context window discipline', 'evaluate CLI', 'CLI agent readiness', 'score this CLI'. NOT for TUI/full-screen apps. NOT for GUI apps. NOT for REST/GraphQL API design.

Use when creating, debugging, or configuring Apache Airflow 3 DAGs — builds data pipelines with TaskFlow API or traditional operators, configures scheduling and asset-driven triggers, wires XCom data passing, sets up sensors and deferrable operators, generates dynamic task mappings, and structures multi-layer test suites. Triggers on DAG authoring, TaskFlow API, operators, sensors, scheduling, assets, dynamic tasks, XCom, or pipeline testing.

Use when designing, building, reviewing, or evaluating command-line tools for human users -- structures commands with memorable naming and consistent grammar, adds interactive prompts with flag bypasses, implements color-coded output with spinners and progress bars, designs informative error messages with resolution URLs, enforces XDG config paths, adds shell completions and man pages, optimizes startup to under 500ms, implements TTY-aware dual-mode output, and scores CLI human-friendliness on a 0-21 rubric across 7 axes. Triggers on: 'CLI UX', 'human-friendly CLI', 'CLI design', 'CLI colors', 'CLI prompts', 'progress bar', 'CLI help text', 'error messages', 'CLI usability', 'design a CLI', 'evaluate CLI UX'. NOT for agent/machine CLI consumption (use agent-cli). NOT for TUI/full-screen apps. NOT for GUI apps.

Use when adopting the Open Knowledge Format (OKF v0.2) in a repository, or maintaining a documentation bundle already in it: bootstraps a conformant tree, stamps and repairs YAML frontmatter, regenerates every index.md bottom-up, excludes paths another tool owns via .okfignore, removes log.md and strips changelog/history sections because git already holds history losslessly, and wires CLAUDE.md/AGENTS.md/GEMINI.md to the root index so agents stop grepping for a document's identity. Ships a conformance check that fails closed. Triggers on: 'set up OKF', 'make these docs OKF-conformant', 'regenerate the docs index', 'add frontmatter to the docs', 'keep generated docs out of the index', 'our documentation keeps drifting'. NOT for writing a document's body or deciding its content - repo templates and the adr skill own that. NOT for a repo whose docs/okf.yaml declares a profile, which runs its own toolchain and makes this skill halt. NOT for reverse-engineering a codebase into fresh specs.

SRE-focused Kubernetes specialist for production deployments. Use when deploying to Kubernetes, reviewing manifests, or establishing reliability practices.

Write a production-incident postmortem that reads well for humans and stays parseable by tooling. Produces docs/postmortems/YYYY-MM-DD-<slug>.md with machine-read YAML frontmatter (severity critical|high|medium|low), a stable H1 + filename date that together form a finding-id, and a numbered spine — executive summary, impact/blast radius with per-service evidence, timeline, root cause (mechanism + 5 whys + discarded hypotheses), empirical proof, detection, remediation (palliative vs root fix), action items, lessons learned, read-only appendices. Triggers: 'write a postmortem', 'post-incident review', 'incident record', 'document this outage', 'RCA document', or right after resolving/mitigating any production incident. NOT for reconciling a postmortem with the decision it contradicted. NOT for bug reports. NOT for live incident response.

Use when a requirement or an unproven technique must be made clickable before it is built — produces a single self-contained HTML prototype that doubles as a design spike, whose control panel is the open questions. Rebuilds existing screens at high fidelity from real source (structure, copy strings, icons, tokens, each cited file:line; invents only what the requirement adds, and annotates it), derives one control per acceptance criterion or technical unknown, drives real data through a dev-server proxy that also proposes the route shape (live > recorded capture > labeled stub, never an invented payload), verifies every state in a real browser, and reports what the spike settled. Triggers on 'prototype FR-NNN', 'clickable prototype of FR-NNN', 'make this requirement clickable', 'spike this technique'. NOT for inventing UI from a prompt — use a generative-design skill. NOT for production frontend code. NOT the client-confirmation record — that is a spec-playback step. NOT an ADR writer.

Systematic framework for analyzing product documents (PRDs, feature specs, user stories, roadmaps, one-pagers) to identify gaps, generate clarifying questions for PMs and engineers, and assess technical risks. This skill should be used when engineers or technical leads need to bridge PM documents and implementation by eliciting missing technical details rather than making assumptions. Use when asked to extract technical requirements, review specs, identify what's missing, or prepare clarifying questions from product documents.