Personal Claude Code workflow skills, commands, and hooks for context continuity and skill evolution
啟動簡短回應模式,所有回答控制在 20 秒內可讀完
Cloud Function 完整測試與驗證:unit → integration → e2e(local) → deploy → trigger → GCP logs
Safely clean up a merged git worktree — sync output/, remove JSON raw files, delete worktree and branch
根據 Heptabase 命名系統 v1.0 生成文件標題
精煉文字,刪除贅詞,保留核心意思,讓文字更精準易讀
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)
Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details!
Session 收尾 agent。當使用者說「收工」「收尾」「session 結束」「wrap up」「session-ender」時使用。依序執行:(1) 從對話中識別 improve signals 並輸出 (2) 提示執行 /work-wrap-up 做 commit+PR+gsheet+slack 收尾。
Fresh-session surrogate verifier for improve skill rewrites. Use when /improve reaches Step 4.5 and needs isolated A/B/C/D eval prototype classification, synthetic test cases, mental simulation, and structured diagnostics.
Mine mechanism-first candidate claims from a bounded source set across thoughts/ and Heptabase MCP. Writes candidate files to thoughts/global/fredrick/candidates/ and stops for human scoring. Trigger: "personal-wiki-mine", "zettel mine", "candidate claims", "卡片盒連結挖掘".
Research the codebase and create a concise implementation plan in one step. Use for small, focused changes where you want to go straight from research to a ready-to-implement plan without back-and-forth. For larger or more complex changes, use /research-codebase followed by /create-plan instead.
Document codebase as-is via parallel sub-agents. Use when researching how code works, mapping architecture, or answering questions about existing systems. Auto-detects thoughts/ directory — if present, integrates historical context and syncs; if absent, skips those steps.
Resume work from a handoff document with context analysis and validation. Use when the user requests to resume from a handoff, continue previous work, or references a handoff path or ticket number (ENG-XXXX). Supports quick mode (default) and full mode (--full flag).
Reflect on /improve Skill Evolution Memory. Use when the user asks to process accumulated improve signals, deduplicate skill gaps, generate or refresh memory/claims/{skill}.md, generate memory/eval-cases/{skill}.json, enrich old memory records, or produce a prioritized /improve worklist from signals.jsonl.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal Claude Code workflow skills, commands, and hooks.
fstack is my personal agent operating system for Claude Code: it preserves
context across sessions, turns repeated workflow failures into skill
improvements, and keeps agent work auditable through plans, handoffs, hooks,
queues, eval cases, and human review gates.
claude plugin install https://github.com/fredrick84823/fstack
research-codebase / create-plan
|
v
implement-plan
|
v
create-handoff
|
v
resume-handoff
|
v
verify current repo state before continuing
See docs/context-continuity.md and examples/handoff.md.
User correction / repeated failure
|
v
<<GAP skill-name: description>>
|
v
Stop hook captures the signal
|
v
signal-queue.md + memory/signals.jsonl
|
v
skill-memory-reflect consolidates claims + eval cases
|
v
/improve proposes a SKILL.md update
|
v
human gate
|
v
skill rule updated + changelog
See docs/skill-evolution-loop.md, examples/improve-signal.md, examples/skill-memory-claim.md, and examples/eval-cases.json.
| Skill | Description |
|---|---|
beautiful-mermaid | Render professionally-styled Mermaid diagrams |
brainstorming | Structured brainstorming coach |
codex-brainstorm | Adversarial brainstorming with Codex |
codex-cli-review | Review uncommitted changes via Codex CLI |
create-handoff | Create handoff docs for session transitions |
create-plan | Create detailed implementation plans |
create-team-plan | Decompose plans for agent teams |
deep-module | Enforce Deep Module principle for interface-first design |
extract-skill | Extract and build skills from candidate queue |
grill-me | Turn vague ideas into concrete PRDs through targeted questioning |
heptabase-task-card | Create Sprint-ready Heptabase task cards |
implement-plan | Execute phased plans with human checkpoints |
implement-team-plan | Execute team-plans with native agent teams |
improve | Skill self-evolution and gap tracking |
personal-wiki-mine | Mine mechanism-first candidate claims from bounded thoughts/ and Heptabase sources |
research-and-plan | Research codebase + plan in one step |
research-codebase | Document codebase architecture via sub-agents |
resume-handoff | Resume work from a handoff document |
skill-memory-reflect | Consolidate improve memory into claims, eval cases, and worklists |
start-day | Build a daily task board from local and external work signals |
work-wrap-up | Commit + PR + progress sync + Slack notification |
| Command | Description |
|---|---|
/brief-mode | Enable terse response mode |
/cf-verify | Cloud Function full test & verification |
/clean-worktree | Safely clean up a merged git worktree |
/heptabase-title | Generate Heptabase document titles |
/refine-text | Tighten text, remove filler |
/safe-pull | Pull from origin with auto stash/rebase |
/start-worktree-task | Create a new git worktree for isolated work |
/work-wrap-up | Shortcut to the work-wrap-up skill |
Sub-agents for the research → plan → implement workflow (from HumanLayer):
npx claudepluginhub fredrick84823/fstack --plugin fstackHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.