AGENT SKILL

where-were-we

Provide the user with a refresher of existing chat turns. Useful when the user wants to understand where we stand in the conversation.

License 许可
MIT
所属仓库
dotlas/skills
最近更新
2026-10-27
Stars
★ 2
Forks
0

01 前言 Front Matter

name
where-were-we
description
Provide the user with a refresher of existing chat turns. Useful when the user wants to understand where we stand in the conversation.

03 SKILL.md 正文

Provide the user with an ELI5, first-principles recap of the recent conversation turns. Assume they are returning after a while to resume work on this task.

Help them clearly understand:

  • Where things currently stand.
  • Which decisions have been locked.
  • Which decisions remain open, along with the available options for each.
  • What remains in the planning stage (if planning is still ongoing).

Go back as many turns as necessary to provide a complete picture of the conversation context. Do not waste time going too far back unnecessarily—use locked decisions and implementation milestones to short-circuit the context and highlight what needs the user’s attention right now.

Assume the user may not remember past decisions made, but will recall checkpoints for implementation work that has already been completed and shipped. Do not make the assumption that even a message that exists in the prior conversational turn was read by the user either.

For completeness, include any deferrals present in the current or previous plans in the brief too.

Prioritize scannability to minimize cognitive load, ensuring the brief is easy to skim without omitting important details in its content.

04 同仓库更多 Skills

dotlas
dotlas/skills

update-global-dotlas-skills

Sync the globally-installed dotlas/skills catalog and prune stale remnants. Runs the documented global install command, then detects skills that were installed from dotlas/skills but no longer exist in the catalog and removes them (with confirmation). Use when the user wants to update, refresh, or clean up their global Dotlas skills, or invokes /update-global-dotlas-skills.

★ 2
dotlas
dotlas/skills

unpack

Explain an unfamiliar thing plainly and from first principles, structured so the reader sees why it is true. Use when someone is trying to understand something — a dense or jargon-heavy passage, a baffling error, an unfamiliar mechanism, a codebase, or a document — asks to break something down ("walk me through this", "what does this actually mean"), or wants their intent turned into a precise instruction for another agent. Trigger on confusion or a request to understand, not on difficulty alone; technical or long content is not itself a signal.

★ 2
dotlas
dotlas/skills

sum

Use when the previous response is too technical, complex, or jargon-heavy and needs a clear, plain-language explanation

★ 2
dotlas
dotlas/skills

slack

Compose a Slack message, or digest a Slack thread into compact context. Use when the user asks to reply to a person or channel, write a Slack post, or catch up on a thread without reading the whole transcript. This skill covers how to write well for Slack — both jobs share the same standard.

★ 2
dotlas
dotlas/skills

plan-with-me

Collaborative, human-in-the-loop planning for something new that spans several parts and needs human judgement at each fork. A brainstorming partner that funnels — each fork opens up the real options, then narrows to a decision, surfacing caveats and breaking points, and co-authoring the plan instead of guessing alone. Fits any domain where you plan something new against existing context. Resolves one decision at a time, each with a recommendation, then emits a lightweight plan to hand off for implementation. Use when planning alone would make wrong assumptions, or the user wants to shape something new together.

★ 2
dotlas
dotlas/skills

multi-agent-chat

Open a chatroom — a plain .txt log on disk — so agents in separate sessions (Claude, Codex, others) whose work has collided or become correlated can talk to each other: resolve the conflict, trade the context each is missing, and settle who owns what. The agent that opens the room moderates it; the operator relays the room path to the other agents. Use when two sessions are stepping on each other or one needs what the other knows, or when handed a room path and asked to join.

★ 2