cklxx

@cklxx source repo

21 skills
0 followers
6 hours ago last updated

▌
Writing Plans · cklxx
Use BEFORE starting non-trivial work. Creates a structured plan with task breakdown, technical design, and risks. A task is non-trivial if it touches 3+ files, involves a design choice, or will take more than 30 minutes.

0
installs
▌
Running Retros · cklxx
Use when enough raw experience has accumulated to compress — 10+ unreviewed entries, milestone completed, or 7+ days since last retro. Reads entries, finds patterns, distills executable rules, and feeds them back into memory. This is the compression step that turns raw logs into curated knowledge.

0
installs
▌
Managing Memory · cklxx
Use when a VERIFIED, DURABLE insight emerges — not raw events (that's recording-practices), not pattern analysis (that's running-retros). Persists one-line knowledge items to docs/memory/long-term.md, which is loaded on every session start.

0
installs
▌
Recording Practices · cklxx
Use DURING work when a notable event occurs — bug fixed, non-obvious root cause found, effective technique discovered, pitfall hit. Logs raw experience entries. Does NOT distill rules (that's running-retros) or persist knowledge (that's managing-memory).

0
installs
▌
Using Compound Engineering · cklxx
Bootstraps compound-engineering on every session. Loads project memory, scans recent experience, and activates the plan→record→remember→review loop.

0
installs
▌
Anygen · cklxx bundle
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.

1
install
▌
Openmax · cklxx bundle
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.

1
install
▌
Openseed · cklxx bundle
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.

1
install
▌
Openbench · cklxx bundle
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.

1
install
▌
Feishu CLI · cklxx bundle
When the agent needs to call 飞书/Lark APIs locally → unified CLI (auth/tool/api/help) with progressive disclosure.

1
install
▌
Feishu Doc · cklxx
When 飞书云文档 needs creating, reading, or updating → CRUD docs with Lark-flavored Markdown syntax.

1
install
▌
Browser Use · cklxx bundle
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.

1
install
▌
Feishu Task · cklxx
When 飞书任务 (tasks/todos) need managing → CRUD tasks, subtasks, and task lists.

1
install
▌
Feishu Bitable · cklxx bundle
When 飞书多维表格 (Bitable) needs CRUD or management → create/query/edit apps, records, fields, views with advanced filtering and batch ops.

1
install
▌
Feishu Im Read · cklxx
When 飞书 chat history needs reading → fetch group/DM messages, thread replies, and download attached files/images.

1
install
▌
Image Creation · cklxx bundle
When the user wants to create or edit images → generate with Seedream (text-to-image + image-to-image).

1
install
▌
Notebooklm CLI · cklxx bundle
When the user needs NotebookLM operations → unified CLI (command/op) returning structured results.

1
install
▌
Feishu Calendar · cklxx
When 飞书日历 events or meetings need managing → CRUD calendar events, manage attendees, query free/busy status.

1
install
▌
Video Production · cklxx bundle
When the user wants to create a short video → generate with Seedance, validate and save output files.

1
install
▌
Reminder Scheduler · cklxx bundle
When the user wants to set reminders → create, query, cancel one-time or recurring reminders with expiry scanning.

1
install
▌
Feishu Troubleshoot · cklxx
When 飞书 plugin errors or auth failures occur → troubleshoot with FAQ and authorization diagnostics.

1
install

21 published skills