capability-onboard
Runs a capability's onboarding interview — typed questions, batched, secrets to the harness store — and writes the answers to the user's MOD.md overlay. Use when installing a capability that ships ONBOARDING.md, when the user asks to redo, refresh or revisit their answers, or when bootstrapping the global MOD.md for a new user. Do NOT use to change a behaviour no question covers: an unasked change is a prose statement written by capability-evolve, and a new question is a source change owned by capability-contribute.
- License 许可
- MIT
- 所属仓库
- AlmogBaku/aos
- 最近更新
- 2026-11-15
- Stars
- ★ 5
- Forks
- 2
01 前言 Front Matter
- name
- capability-onboard
- metadata
- { "aos": { "origin": "capability-lifecycle@0.7.0" } }
- description
- Runs a capability's onboarding interview — typed questions, batched, secrets to the harness store — and writes the answers to the user's MOD.md overlay. Use when installing a capability that ships ONBOARDING.md, when the user asks to redo, refresh or revisit their answers, or when bootstrapping the global MOD.md for a new user. Do NOT use to change a behaviour no question covers: an unasked change is a prose statement written by capability-evolve, and a new question is a source change owned by capability-contribute.
02 资源文件 1
- 参考文档reference/answer-validation.md877 B
03 SKILL.md 正文
capability-onboard
You are the only writer of MOD.md files. Typed answers → frontmatter; prose nuance → body; secret values → harness store (references only in MOD.md).
Inputs
- Target capability's
ONBOARDING.md: frontmatter = typed questions (id,prompt,type: string|number|boolean|enum|list|path, optionalrequired/secret/re_askbooleans); body = the conversational script. Follow the script — don't read questions off like a form. - Existing MOD.md for this capability, if any.
- Global root MOD.md — skip questions it already answers; confirm instead of re-asking.
Which questions to ask
| Situation | Ask |
|---|---|
| First run | all; required must get answers, others may be skipped |
| Re-run | unanswered + every re_ask: true |
--refresh |
all, current answer shown as default |
Never delete an answer the user didn't change.
Conduct
Cluster related questions; accept "skip" for non-required. Everything the user says
beyond the typed answer is body-prose nuance ("19:00 — but never over choir practice":
19:00 is the answer, the rest is nuance).
Write
- Validate every answer per reference/answer-validation.md.
secret: trueanswers: value → harness store per the cheat-sheet; MOD.md gets only{store, key}. Never write or repeat the value.- Diff gate: show the diff (or the full draft on first run) and get approval. Empty diff ⇒ no write, no prompt.
Format (normative):
---
capability: <id>
onboarded_version: <CAPABILITY.md version at interview time>
answers:
<question_id>: <typed value>
secrets:
<question_id>: {store: <store>, key: <key>}
---
<prose nuance under headings; omit headings with nothing under them>
Location: <aos_home>/personal/MOD.md for the global bootstrap (this capability's own
interview); <aos_home>/personal/capabilities/<id>/MOD.md otherwise. Never re-serialize unchanged content — edit the
file, don't regenerate it (unchanged answers stay byte-identical).
Report
Answered / skipped / unchanged; secret store+key names only; the applied diff on re-runs. If part of an install, hand back to the installer.
04 同仓库更多 Skills
wt-update
Updates an existing commitment when the user reports progress: completion, a new deadline, a stall, or abandonment. Use when the user says "I did that", "finished X", "still waiting on Y", "push that to next week", "I started it", or "forget it, I'm not doing X". Finds the matching open action, applies the change, and routes any knowledge the report carries to the knowledge base. Do NOT use to file a new commitment (that is wt-capture) or to find time for one (wt-schedule).
wt-steward
Maintains an existing commitments backlog: overdue, about to expire, stalled, and repeatedly-rescheduled commitments, and someday items gone cold. Use when the nightly cron job fires or the user asks to review or tidy their backlog ('review my backlog', 'what's gone stale on my list'). Does not capture or schedule new work — that happens when the user speaks, through wt-capture and wt-schedule.
wt-schedule
Estimates a commitment, links it to its project, and blocks time for it on the user's calendar. Use when the user asks to find time for something — "when can I do this?", "find me two hours for the CFP", "block time for that tomorrow", "I want to work on it today" — and immediately after wt-capture files a commitment that needs real hours. Do NOT use for a commitment that needs only a deadline or a reminder, and do NOT use to change what the user committed to — that is wt-update.
wt-capture
Records something the user has said they must do themselves: classifies the commitment as next, waiting, someday or trivial, writes it as an action page in their commitments base, and hands off to wt-schedule when it needs real hours. Use when the user commits to work of their own — "I need to find time to…", "I have to…", "remind me to…", "help me remember…", "put that on my list", "I should … at some point". Do NOT use when the user asks the assistant to do the work ("write the CFP", "research X", "email Sam") — that is a request to act now, not a commitment to track. Do NOT use for thoughts, facts or notes carrying no commitment; those are knowledge and belong to kb-capture.
work-tracker
Answers questions about the user's own commitments by querying their commitments base, explains the four statuses (next, waiting, someday, done), routes a request to the right work-tracker skill, and states who may change what without asking. Use when the user asks what they should be working on, what is overdue, what they are waiting on, or how their task tracking works, and no narrower work-tracker skill matches. Do NOT use to file a commitment the user just made (that is wt-capture), to find time for one (wt-schedule), or to report progress on one (wt-update).
kb
Explains how the user's knowledge bases are laid out and which kb skill handles a given job — the tree, the one queue, expiry, links, base health, maintenance. Use when the user asks how their knowledge base works, what state a base is in, why something was or was not kept, or wants base maintenance run, and no narrower kb skill matches. Do NOT use to file something the user just said (that is kb-capture), to answer a question from stored knowledge (that is kb-recall), or to pick a destination base for a write already in hand (that is kb-route).