Skill Claude CodeCodex
USE FOR: Non-code working artifacts: local markdown task trackers, plans, research notes, review packets, drafts, scratch outputs, supplied artifact paths, work-start/resume discovery and reuse, canonical-vs-multiple artifact decisions, cwd-independent mkmd invocation, and human-facing Secret-Gist delivery. DO NOT USE…
Skill Claude CodeCodex
USE FOR: Clarify concepts before names harden by fixing concrete referents, roles, sequence, candidate terms, and first-use definitions. Use for terminology-heavy design docs, research synthesis, cause-isolation or mitigation plans, naming decisions, and reasoning-order summaries only when concept/referent ambiguity…
Skill Claude CodeCodex
USE FOR: Read BEFORE any git or GitHub action (issue, branch, commit, push, PR create/review) — sets the issue-first, worktree-based default via issue-worktree-create. GitHub/Jira/Confluence: gh CLI, PR/commit/issue management, review style, public path hygiene; Atlassian Cloud when env vars are confirmed. DO NOT USE…
Skill Claude CodeCodex
USE FOR: $create-review-comment, ai-create-review-comment, or terse PR-review-comment requests. Infers the PR and routes postman substantive review through guardian/critic without exposing mechanics. DO NOT USE FOR: unrelated tasks, broad rewrites, generated outputs, or posting comments without explicit approval.
Skill Claude CodeCodex
USE FOR: Repo-local BigQuery, Databricks, dbt, restricted BigQuery/dbt safety, and cloud auth workflows. DO NOT USE FOR: harness, diagrams, or generic code.
Skill Claude CodeCodex
USE FOR: draw.io and Mermaid diagram authoring, preview, export, layout, color, and asset workflows in this repo. DO NOT USE FOR: data-platform or generic coding tasks.
Skill Claude CodeCodex
USE FOR: This dotfiles environment and agent harness: machine setup, Nix operations/recovery, missing tools, operating concepts, clipboard, Claude/Codex config, hooks, MCP, skills, Postman routing/runbooks, tmux/worktrees/panes, prompt/review/resume-handoff contracts, and Agent Skills authoring/validation/Waza. DO NOT…
Skill Claude CodeCodex
USE FOR: Reference-only external provider packs and dormant source inventory: dbt, azure, databricks-official, obsidian, hashicorp-terraform, google, aws, Databricks, Azure, Microsoft Foundry, Google Cloud, GCP, AWS, Terraform, HashiCorp, Obsidian, provider-pack lookup, and promotion questions. DO NOT USE FOR…
Skill Claude CodeCodex
USE FOR: Implementation plans and durable task tracking: reduce ambiguity, compare options, parallel investigation, multi-source synthesis, review gates, planning evidence, handoff/resume, DONE/BLOCKED verification, and Secret-Gist handoff semantics. DO NOT USE FOR: artifact storage mechanics, machine-only outputs…
Skill Claude CodeCodex
USE FOR: Programming/debugging: Bash, Python/Jupyter quality, Nix package workflow, Terraform with Checkov, Markdown, TDD/Tidy First, and root-cause isolation. DO NOT USE FOR: agent harness, data-platform, diagramming, or GitHub workflow work.
Skill Claude CodeCodex
USE FOR: Guardian/critic native multi-perspective review workflow, peer critic evidence, material-finding convergence, and blocking-finding synthesis. DO NOT USE FOR: implementation, dispatcher fan-out, overrides, or public posting.
Skill Claude CodeCodex
USE FOR: Verifying technical claims, comparing options, and investigating unfamiliar libraries/APIs/tools with cited, confidence-rated evidence. DO NOT USE FOR: implementation, opinion without evidence, or tasks better served by a narrower repo-specific skill (e.g. data-platform, collaboration).
Skill Claude CodeCodex
USE FOR: Prose QA, Vale/Harper, terminology, English/Japanese edits, English-to-Japanese, stable glossaries, rhythm, AI-slop cleanup, publication QA. DO NOT USE FOR: AI detector/humanizer workflows, fresh generation, meaning-changing rewrites, replacing author judgment, publishing, model/cost/privacy, external…