本文へ移動
cccskills
無料GitHub で公開

roadmap

Synthesize project documentation and codebase into comprehensive roadmap status, gaps analysis, and blockers. Use when assessing project health, identifying blockers, tracking progress, comparing plan vs reality, documenting risks, or planning next milestones. Triggers: "roadmap", "project status", "blockers", "risks", "progress", "next milestone", "gaps", "what's done".

インストール方法を見る

含まれるファイル(4)

  • SKILL.md7.6 KB
  • EXAMPLES.md16.7 KB
  • TROUBLESHOOTING.md8.1 KB
  • WORKFLOW.md36.9 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Roadmap Analyst

Synthesize project documentation and codebase state into actionable status reports.

Context Discovery

Run the shared context discovery protocol in CONTEXT_DISCOVERY.md. Use the scan depth appropriate for the mode:

ModeRequired PhasesScan Depth
plan show1 (config)None — reads {plan_file} directly
next (cached)1 (config)None — reads cached file + git drift check
update --dry-run1, 5, 7Medium — config, docs, codebase scan (no write)
status (with or without --focus)1-7Thorough — full protocol
next (recalc)1-7Thorough — full protocol
update, update --incremental1-7Thorough — full protocol
plan scaffold, plan sync1-7Thorough — full protocol

Store results for analysis below.

Arguments

Parse from $ARGUMENTS:

ModeDescription
statusOverall dashboard — modules, phases, completion + drift detection. Renders Gaps, Blockers, Risks, and Specs as inline sections. Add --focus=<gaps|blockers|risks|specs> to render only one section
updateGit-aware status doc update (Phase A: what shipped + Phase B: full scan + auto-chains plan sync). Add --dry-run to preview the diff without writing. Add --incremental for post-sprint targeted edits only
nextPrioritized recommendations with caching and smart merge. Saves to {output_dir}/next-actions.md. Returns cached results if <3 feat/fix commits and status doc unchanged; otherwise merge-based recalculation that preserves uncompleted items and user additions. Add --force to recalculate (still merges; delete file manually for clean slate)
planProject roadmap lifecycle — scaffold (create), show (read), sync (update). Defaults to show if roadmap exists, scaffold if not
(none)Defaults to status. Footer suggests /roadmap next if next-actions.md is stale

Module Maturity Scale

Rate each module using the shared vocabulary in MATURITY_SCALE.md.

Mode Execution

status

Produce a status dashboard with module maturity table, then detail: What's working, What's planned, What's missing.

After producing the dashboard, render four focus sections inline:

  • Gaps — open/closed/in-progress with evidence (cross-references all gap analysis documents)
  • Blockers — blocking chain analysis with critical path; for each blocker: what it blocks, owner, what's needed
  • Risks — risk register with Likelihood (H/M/L) x Impact (H/M/L) scoring and suggested mitigations
  • Specs — spec pipeline verification against codebase evidence (not just what the spec says). If {plan_file} exists, cross-reference to show which phase each spec belongs to and flag unlinked specs

With --focus=<gaps|blockers|risks|specs>, render only that section (skip the dashboard preamble and other sections).

After producing the dashboard, run drift detection: if 3+ feat/fix commits exist since last {status_file} update, append a staleness notice suggesting /roadmap update.

update

Git-aware status document update. See WORKFLOW.md § update for the full Phase A (git history scan) + Phase B (codebase scan + write) protocol.

Key behaviors:

  • Shows "What Shipped" summary before scanning
  • Diff preview with +/-/~ markers, requires confirmation before writing
  • Checks CHANGELOG.md for gaps (offers to add entries)
  • Auto-chains into plan sync when phase/spec status changes detected
  • Next /roadmap next will detect status doc changes and trigger merge-based recalculation (preserves uncompleted items)
  • --dry-run variant: runs Phase A + Phase B but stops at the diff preview without prompting or writing — read-only comparison of status doc vs current codebase
  • --incremental variant: surgical targeted edits only (skips Phase B full scan)

next

Prioritized recommendations with git-aware caching and smart merge. See WORKFLOW.md § next for the full merge protocol.

Key behaviors:

  • Saves recommendations to {output_dir}/next-actions.md
  • Returns cached results if <3 feat/fix commits and status doc unchanged since last calculation
  • On recalculation, merges new recommendations with existing items — preserves uncompleted items, removes items with completion evidence
  • User-added items in ### User-Added section always preserved across recalculations
  • Shows merge diff preview with +/-/~/= markers before writing (confirmation required)
  • Combines: unclosed gaps, unstarted specs, maturity imbalances, plan backlog themes

plan

Consolidated project roadmap lifecycle. Read plan_file from .arkhe.yaml (default: docs/PROJECT-ROADMAP.md).

SubcommandDescription
scaffoldCreate initial PROJECT-ROADMAP.md using hybrid linking algorithm — see WORKFLOW.md § plan scaffold
showRead-only summary with timeline, progress stats, active phases, drift detection
syncGit-aware update with auto-detected links — see WORKFLOW.md § plan sync
(none)Default to show if roadmap exists; scaffold if not

Legacy file fallback: If {plan_file} is unset in .arkhe.yaml and docs/PROJECT-PLAN.md exists while docs/PROJECT-ROADMAP.md does not, treat the legacy path as {plan_file} for this run and emit a one-time migration notice suggesting mv docs/PROJECT-PLAN.md docs/PROJECT-ROADMAP.md (or pinning plan_file in .arkhe.yaml).

Output Rules

  • Evidence-based — every claim backed by a file path, migration, or component
  • Tabular — use tables for at-a-glance status; prose for analysis
  • Actionable — always end with recommended next actions
  • Honest — distinguish between "verified working" and "files exist but untested"
  • update and plan scaffold/plan sync show unified diff preview and require explicit confirmation before writing
  • --deep reports are saved by default to {output_dir}/reports/; user can opt out

Deep Mode (--deep)

When $ARGUMENTS contains --deep, run the full multi-agent pipeline with parallel cross-perspective analysis. Three Sonnet agents analyze the project simultaneously from PM, Architect, and Roadmap perspectives, then a synthesizer merges findings and surfaces contradictions.

See WORKFLOW.md § Deep Pipeline for the 5-phase execution protocol.

Phase 4 produces a Confidence Scoreboard table with independent scores per finding. Findings below 70 are removed; 70-89 are tagged [NEEDS VALIDATION].

Patterns applied: Pipeline, Supervisor-Worker, Parallel Execution, Confession, Confidence-Gated Completion.

Lane Discipline

See the Roadmap Analyst section of LANE_DISCIPLINE.md. Stay in your lane.

References

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

adr

無料

Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

architect

無料

Analyze system architecture, module structure, API contracts, data models, and code patterns. Use when designing systems, reviewing module boundaries, evaluating API designs, analyzing data models, checking pattern conformance, tracing decisions, or reviewing frontend architecture. Triggers: "architecture", "module design", "API design", "data model", "boundaries", "patterns", "decisions", "frontend architecture".

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Interactive Claude Code environment setup wizard. Detects existing configuration, guides through best-practice setup for Global CLAUDE.md, project scaffolding, MCP servers, hooks, custom agents, keybindings, and settings. Use when user runs /devtools:code-env-setup, mentions "setup claude code", "configure claude", "claude code setup", "environment setup", or "initialize claude code".

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

joaquimscosta のスキルをすべて見る

このスキルの問題を報告する