BriarDevv
UserPersonal Agent Skills library for Claude Code: eval-first methodology skills, junction-installed globally and built on the Context-Engineering standard.
Categories
Indexed Skills (8)
reviewing-plans
Adversarial review of plans, specs, and proposals before execution — verifies references, extracts and rates assumptions, runs a pre-mortem, hunts what's missing, then pressure-tests its own findings for confidence and real-world severity. Use before executing an implementation plan, when asked to review a spec or proposal, or as the quality gate after writing-plans.
tracing-root-causes
Disciplined causal analysis for explaining observed outcomes — competing hypotheses, evidence ranked by strength, active disconfirmation, and a discriminating next probe. Use when investigating why something happened (intermittent failures, regressions, production incidents, surprising benchmark results) BEFORE proposing fixes, especially when a "obvious culprit" is tempting.
reviewing-plans
Adversarial review of plans, specs, and proposals before execution — verifies references, extracts and rates assumptions, runs a pre-mortem, hunts what's missing, then pressure-tests its own findings for confidence and real-world severity. Use before executing an implementation plan, when asked to review a spec or proposal, or as the quality gate after writing-plans.
tracing-root-causes
Disciplined causal analysis for explaining observed outcomes — competing hypotheses, evidence ranked by strength, active disconfirmation, and a discriminating next probe. Use when investigating why something happened (intermittent failures, regressions, production incidents, surprising benchmark results) BEFORE proposing fixes, especially when a "obvious culprit" is tempting.
designing-consistently
Keeps UI work consistent with an app's DESIGN.md design system and decision log. Use when building or modifying UI in a repo with a DESIGN.md (or one that keeps drifting without it), when new screens must match existing ones, when buttons or patterns come out different every session, or when design decisions get lost between sessions.
extracting-design-md
Reverse-engineers a DESIGN.md (Google Labs format) from an already-built project and measures its design drift. Use whenever an existing codebase should adopt DESIGN.md, when UI values have multiplied (several grays, mixed radii, inconsistent buttons), when the owner says the UI looks inconsistent or "quedó desprolijo", or to re-audit drift after a migration batch — even if nobody says the word DESIGN.md.
context-init
Installs the context-engineering standard in a repository or migrates legacy context architectures (canonical AGENTS.md contracts, per-tool adapters, mandatory read orders) to it. Use when setting up Claude context for a new or existing repo, when a repo lacks CLAUDE.md, or when modernizing an outdated context setup.
context-audit
Audits a repository's Claude context files (CLAUDE.md, AGENTS.md, skills, docs structure) against the context-engineering standard and reports a score with concrete fixes. Use when checking context quality, after running context-init, when a repo's context feels bloated or outdated, or before migrating a repo to the new standard.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.