本文へ移動
cccskills
無料GitHub で公開

feature-radar-ref

Record external observations, ecosystem trends, and creative inspiration into .feature-radar/references/. MUST use this skill when the user mentions something interesting from outside their project — other tools, articles, approaches, or trends — even casually ("I saw a cool thing in X"). Use when the user shares a URL, article, talk, or research finding, notes an ecosystem trend or a related project's notable feature, or asks to bookmark or track external inspiration. Do NOT use for internal learnings/patterns — that's feature-radar-learn's job. Do NOT use for prioritizing features — that's feature-radar's job.

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。

runkids/feature-radarスター 14(GitHub 14 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.2 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。

Add Reference

Record external observations into .feature-radar/references/.

Deep Read

<HARD-GATE> Read and follow `../feature-radar/references/DEEP-READ.md` — complete all 6 steps before proceeding. </HARD-GATE>

Behavioral Directives

<HARD-GATE> Read and follow `../feature-radar/references/DIRECTIVES.md`. </HARD-GATE>

Workflow

  1. Identify the source — ask the user what they observed:
    • Interesting project, technique, or creative approach?
    • Ecosystem trend or emerging pattern?
    • Notable feature or solution from a related project?
    • User comparison, feedback, or question?
    • Research, article, or talk with relevant insights?
  2. Gather context — URL, date, key details. If the user provides a GitHub URL, fetch the issue/PR for full context.
  3. Classify — determine the right file:
    • Existing reference file → append a new entry
    • New topic → create .feature-radar/references/{topic}.md
  4. Assess impact — before writing to references/, answer each question:
    • New opportunity or feature idea? → state yes/no, suggest file if yes
    • Way to enhance existing features? → state yes/no, suggest update if yes
    • Ecosystem trend? → state yes/no, suggest specs/ecosystem-trends.md update if yes
  5. Checkpoint — State what was written and the impact assessment results. Ask: "I've updated references/{topic}.md. Does this look correct, or should I adjust anything?" Wait for user confirmation before proceeding.
  6. Update base.md — increment the references count in Tracking Summary

File Format

Use the format defined in ../feature-radar/references/SPEC.md § 3.5 (references/{topic}.md).

Naming Convention

Name by the subject being tracked, not the event:

  • Good: vercel-skills-ecosystem.md, agent-path-conventions.md, cli-ux-patterns.md
  • Bad: 2026-02-18-update.md, interesting-finding.md

Guidelines

  • Always cite source URLs and dates for traceability.
  • Append new entries chronologically to existing files — don't create a new file per observation.
  • Be objective. Record what happened, then assess implications separately.
  • If the observation reveals an unmet need or innovation opportunity, proactively suggest creating an opportunity.

Example Output

→ Appended to references/cli-ux-patterns.md
→ Suggested: new opportunity "interactive config wizard"
→ Updated base.md: references 3 → 3 (appended, not new file)

Completion Summary

Follow the template in ../feature-radar/references/DIRECTIVES.md, with skill name "Ref Complete".

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。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Full-cycle feature discovery, evaluation, and prioritization. Builds a persistent knowledge base at .feature-radar/ and runs a 6-phase workflow to recommend what to build next. Modes: full (all phases), quick (scan only), evaluate (prioritize), #N (deep-dive one). MUST use this skill whenever the user asks about feature priorities, roadmaps, what to build, or wants to evaluate/compare feature ideas — even if they don't say "feature radar" explicitly. Use when the user wants to decide what to build next, rank or compare features and backlog items, plan a roadmap or project direction, reassess deferred or open opportunities, or mentions the .feature-radar/ directory.

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。

runkids/feature-radar142026年9月29日 更新

Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A — including casual mentions like "we shipped X". The skill extracts learnings, derives new opportunities, and updates refs. Use when the user reports a feature shipped or finished, decides against building one, defers or postpones one, or asks to close or archive an opportunity. Do NOT use for discovering new features — that's feature-radar-scan's job.

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。

runkids/feature-radar142026年9月29日 更新

Extract reusable patterns, architectural decisions, and pitfalls from completed work into .feature-radar/specs/. Captures the "why" behind choices so future sessions build on past experience. MUST use this skill when the user reflects on what worked or didn't, wants to record a decision or pattern for future use, or hit a dead end worth documenting. Use when the user asks to remember, document, or extract lessons from recent work. Do NOT use for recording external observations — that's feature-radar-ref's job. Do NOT use for archiving completed features — that's feature-radar-archive's job.

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。

runkids/feature-radar142026年9月29日 更新

Discover new feature opportunities from creative brainstorming, user feedback, ecosystem trends, and cross-project research. Writes results to .feature-radar/opportunities/. MUST use this skill when the user wants to GENERATE new ideas — not evaluate existing ones — including casual or half-formed ones ("what if we...", "I have an idea"). Use when the user wants feature ideas or new directions, asks what the project is missing, wants to mine issues, community feedback, or adjacent tools for inspiration, or wants to refresh the opportunity backlog. Do NOT use for evaluating/prioritizing existing features — that's feature-radar's job.

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。

runkids/feature-radar142026年9月29日 更新

Validate SKILL.md frontmatter and .feature-radar/ files against format rules. Runs validate.sh, reports errors/warnings, and auto-fixes issues. MUST use this skill after editing any SKILL.md or .feature-radar/ file, even if the user doesn't ask — catches format bugs like the Agent Skills spec's 1024-char description limit before they break the skill. Use when the user asks to validate, lint, or verify skills or .feature-radar/ files, after editing either, or before committing changes that touch skills/ or .feature-radar/.

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。

runkids/feature-radar142026年9月29日 更新

runkids のスキルをすべて見る

このスキルの問題を報告する