メニュー
Prioritization framework, sprint sequencing, and success criteria for uFawkes.dev work. Used by Planning agent to sequence issues across PRs and agents.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Code quality standards for uFawkes.dev — Jekyll/Liquid linting rules, CSS validation, HTML structure checks, and review thresholds. Used by Review and Build agents.
Full lifecycle for uFawkes components — anatomy definition, implementation spec, styling rules, and Jekyll/Liquid integration patterns. For UI and Build agents.
Handoff protocol, dependency sequencing, and parallel task rules for the uFawkes agent team. Ensures agents don't conflict, block each other, or duplicate work.
Three-phase accessibility workflow for uFawkes.dev — audit (find issues), remediate (fix specifications), verify (confirm compliance). Covers WCAG AA, Jekyll/HTML patterns, and vanilla CSS focus states.
Content strategy for uFawkes.dev — narrative structure, page-level content hierarchy, tone guidelines, CTA copy patterns, and trust signal rules.
Process for evolving the Fawkes Design System (FDS) — token definition, pattern library maintenance, compliance checking, and documentation. Currently in bootstrap phase.
| name | planning-workflow |
| description | Prioritization framework, sprint sequencing, and success criteria for uFawkes.dev work. Used by Planning agent to sequence issues across PRs and agents. |
| license | MIT |
| compatibility | opencode |
Trust-damaging content that is live on the site right now. Examples: zero-star badges, "Screenshot placeholder" text, raw Liquid rendering as text.
Blocks the primary visitor action. A Builder or Operator cannot complete their journey. Examples: no CTA above fold, buried quick start, broken cross-links.
Weakens credibility or comprehension. Visitor can still act but leaves with less confidence. Examples: generic meta descriptions, stub content, repeated "coming soon" notices.
Minor improvements. No visitor impact, just cleaner. Examples: section label tweaks, formatting consistency.
Sprint 1 — PR 1 (all P0 and P1 issues in index.md) Sequence: #1 → #3 → #4 → #9 → #2 → #10 → #5 → #11 → #12
Rationale: fix trust-damaging first (#1 double H1, #3 fake badges, #4 bad alt text), then consolidate notices (#9), then conversion (#2 CTA reorder, #10 hero CTA), then polish (#5 Dojo callout, #11 label, #12 DORA descriptions).
Sprint 2 — PR 2 (stack pages and learn guides) Sequence: #6 (all 5 stack pages) → #8 (all 5 meta descriptions) → #7 (learn guides + guide-meta include)
Sprint 3 — PR 3 (design system — deferred) Do not start until PR 1 and PR 2 are merged and live.
Sprint 4 — PR 4 (agent/skill infrastructure) Can run in parallel with Sprint 2. No site file conflicts.
An issue is ✅ Done when:
make build exits 0)main (merged)After each issue completes:
⬜ Not started → ✅ Done in Section 8docs(agents): mark issue #N completeAfter each PR merges: