Claude Skills by paruff

Generate and maintain AI_STANCE.md for any uFawkes* repo. Use when onboarding a repo to the uFawkesAI suite, when reviewing AI policy currency, or when a new AI tool is being adopted. Implements DORA AI Capability 1. Handles review triggers, three-bucket update process, socialization checklist, and cross-repo consistency.

Ensure the internal context an agent needs is current, complete, and placeholder-free before each session. Define minimum AI-accessible documentation per repo. Use at session startup to verify internal context is available to AI tools. Implements DORA AI Capability 3.

Set up local development environment. Use when configuring devcontainers, workspace bootstrap, or local simulation.

15-minute JTBD + acceptance criterion exercise. Use before any spec session. Produces a discovery-brief.md that anchors the entire increment to a real user need and a measurable DORA outcome. Implements DORA AI Capability 6. Includes advanced methods for untested assumptions, persona deep-dives, and prior art search.

Enforce minimum documentation standard across uFawkes* repos. Use when auditing a repo before release, onboarding a new repo to the suite, or implementing roadmap item 0.6 (cross-repo README links). Directly supports DORA AI Capability 3 and the 2023 DORA finding that documentation quality amplifies all technical capabilities.

Compute the five DORA software delivery metrics from uFawkesObs. Implements DORA AI Capability 7 (the platform feedback loop).

Validate the entire OBS + PIPE + GitOps + K8s flow end-to-end, and full system behavior from user's perspective. Implements DORA AI Capabilities 4, 5, 6, 7.

Language-specific toolchain conventions for Python and TypeScript. Implements DORA AI Capabilities 3, 4.

Product retrospective. Runs after a release, after a /measure anomaly flag, or at end of sprint. Maps findings to DORA AI capabilities and produces action items for @planner. Distinct from fawkes learn.md which handles platform incident postmortems.

Regression-gate changes to the agent configuration (AGENTS.md, .agents/ rules, skills, agents, workflows, hooks) by replaying recorded tasks and blocking if the pass rate drops below baseline. Use when changing any agent configuration, or when adding an eval task after a real agent mistake. Implements DORA AI Capability 7.

Surface the relevant Fawkes Dojo module for the current task and map it to the DORA capability being worked on. Implements DORA AI Capability 3 and AI Capability 6 by linking internal docs to the learning path.

Use when searching uFawkesAI institutional knowledge via qmd — agent orchestration, AI-SDLC pipeline, skill/registry conventions, DORA measurement — or when an answer should come from this repo's docs rather than its code.