# Ci | AI 驅動開發 (@ci.fullstack) on threads

- id: koinon:creator:threads_ci.fullstack
- url: https://koinonlink.com/kol/threads/ci.fullstack
- schema_version: 1.4

## Identity
- platform: threads
- handle: ci.fullstack
- platform_url: https://www.threads.net/@ci.fullstack
- website: http://www.portly.ciyang.dev
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 3473
- posts_observed: 1
- verified: false
- size_tier: nano

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.00374
- best_post_interactions: 13
- measurement_source: threads_post_likes
- measurement_formula: likes on one post (Threads exposes no reply or repost count on this path)
- comparable_pool: peak_interactions
- status_note: We have only the single best observed post, so no mean exists. peak_post_engagement_rate is an UPPER BOUND, systematically higher than an average — never compare it against an average rate.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: ai_tools
- category_confidence: 0.94
- category_source: derived_from_recent_content
- topics: AI Agent development, AI-driven software development workflows, AI coding assistants (e.g., Claude Code), AI tool integration (e.g., Skill Recorder), Practical AI implementation in real projects, Developer productivity with AI
- bio: 全端工程師 ｜ AI Agent 實戰
iTHome 鐵人賽佳作｜JSDC・HWDC 講者
AI Agent | SDD | AI Development Workflow
實戰筆記 • AI 流程導入 • 合作邀約 👇
📧 [contact removed]

## Audience (inferred)
- status: present
- description: Full-stack developers and AI engineering practitioners building AI-driven workflows, especially those experimenting with AI agents and automated development pipelines
- roles: dev
- seniority: practitioner
- pain_points: Struggling to debug or monitor long-running AI agent processes due to overwhelming terminal output, Frustrated by AI agents misinterpreting task instructions, leading to incorrect or redundant outputs, Having difficulty integrating AI tools like code assistants and skill recorders into real development workflows, Need clear, actionable guidance on implementing AI agents in practical, production-like scenarios
- posts_analysed: 4
- confidence: 0.4

## Commercial (inferred)
- audience_buyer_fit: 0.9
- promotion_intent: 0.8
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 40
- authenticity_basis: engagement_observed
- credibility_score: 40
- flagged_for_review: false
- koinon_bd_grade: C — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [threads_ci.fullstack#daeebbd0] 每天發 AI 相關內容，追蹤剛破 1,000，好像該自我介紹一下 我是 Ci，寫了十幾年程式，從定義需求到上線都自己跑過，也帶過團隊 從去年開始出現在一些技術研討會，今年會繼續出現 去年鐵人賽連寫了兩個 AI 開發系列，其中一個拿到佛系分享佳作 其中一篇 Claude Code 教學，沒特別推廣，單篇累積近十萬瀏覽 後來投稿上了 Hello World Dev Conference 那時候我才意識到： 大家不是不想用 AI，是不知道怎麼讓它真的動起來 這也是我現在在做的事—— 用 Claude Code、AI Agent 實際導入團隊開發流程，正在往跨部 (https://www.threads.com/@ci.fullstack/post/DaGGGFHFC74)
- [threads_ci.fullstack#a6821c96] 我常常叫 Claude Code 去找檔案 跑測試 查一堆東西 然後畫面開始被 Bash、Read、IN、OUT 塞滿 我知道它很忙 但老實說我只想知道兩件事 還在跑嗎 有沒有出錯 Claude Code 今天加了 Focus view 我拿自己的每日情報管線實際跑一輪 原本塞滿畫面的過程 收起來後只剩一行 「9 tool calls · 1 failed」 它沒有讓 Claude 變快 但監工真的舒服很多 下面放怎麼開 還有哪些場景適合用
- [threads_ci.fullstack#a1dd7453] 我真的把 Microsoft Skill Recorder 裝起來跑了 錄了 31 秒 給它看我怎麼把 GitHub Release 整理成一張研究素材卡 最後它真的吐出一份 2.8 KB 的 SKILL.md 結果第一版就看錯了 它把「建立一張新卡」 看成「閱讀既有卡片」 然後很有自信地往下生了 5 個 看起來合理 但其實走錯方向的步驟 下面放完整實測 也拆一下它到底怎麼把操作變成 Skill
- [threads_ci.fullstack#bd87a8b8] OpenAI 的工程師面試 有人遇到一輪很新的 Agentic Coding beta 不是叫人關掉 AI 而是丟一

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.4, freshness_days=20, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.4, freshness_days=20, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.4, freshness_days=20, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=78, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=78, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=117, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.5, freshness_days=78, method=Profile-shape heuristic from a single snapshot (follower count, following ratio, account age, posting volume, verification), reduced for engagement red flags where post engagement was collected. Where only a follower count is available the score saturates at 58. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=117, method=llm_partner_fit_classifier + fit_score >= 0.6 AND authenticity >= 60 => A; fit_score >= 0.4 AND authenticity >= 45 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=117, method=platform_profile

## Freshness
- profile_checked_days_ago: 117
- content_analysed_days_ago: 78
- audience_updated_days_ago: 20

## AI retrieval
- indexing_requests: 12
- user_triggered_requests: 1
- last_user_triggered_day: 2026-10-10
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=threads_ci.fullstack
- Request removal: https://koinonlink.com/claim?k=threads_ci.fullstack
- Terms: https://koinonlink.com/for-ai