envelope

Solid

Classify any incoming directive as Ship / Ask one focused question / Propose first. Forces a sharp decision instead of a multi-option survey to the principal. The default failure mode for agents is treating ship-work as ask-work (over-surveying) or treating propose-work as ship-work (rushing irreversible changes). This skill prevents both.

AI & Automation 18 stars 5 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
43
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Envelope Sort an incoming request into one of three envelopes — **A: Ship**, **B: Ask one focused question**, **C: Propose first** — and act accordingly. ## When to use - The principal gives a directive and you're tempted to respond with multiple clarifying questions - The work involves a fork in the road and you're tempted to present multiple options - Before posting any "should I…?" question - Triggered by Caddy on prompts like: "should I", "before I start", "is this clear", "is this OK", "couple options", "two paths", "ambiguous", "not sure if you want", "want me to", "ship vs ask", "decision tree", "fork in the road" ## The decision tree (run top-to-bottom) ``` 1. Is the request unambiguous? YES → step 2 NO → can I resolve the ambiguity by reading code/data/docs? YES → resolve, then step 2 NO → ENVELOPE B: ask exactly one focused question with options spelled out 2. Is the change reversible? YES → step 3 NO → is the irreversibility expensive? (data loss, schema migration, deploy, broken contract) YES → ENVELOPE C: propose first, wait for sign-off NO → step 3 3. Is the change bounded to a known surface area? YES → step 4 NO → can I re-scope to a bounded version? YES → propose the bounded version + ship that NO → ENVELOPE C: propose first 4. Do I have full context to make the change correctly? YES → ENVELOPE A: SHIP NO → load missing context (search/read/query); re-evaluate 5. Af...

Details

Author
wrg32786
Repository
wrg32786/aigent-os
Created
2 months ago
Last Updated
3 days ago
Language
JavaScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

ship

Implement a clear request or an approved brief/proposal. Work solo, make the smallest sufficient change, verify the changed behavior, and stop. Ask before any delegation.

15 Updated 4 days ago
mirkobozzetto
AI & Automation Listed

deliberate

Use when about to throw a substantive decision back at the user as a multiple-choice question, when the user has explicitly delegated the choice ("you decide", "you pick", "i aint picking", "stop asking me to choose", "just do it"), when a craft / strategy / architecture / design / project decision involves competing pressures requiring synthesis, or any time multiple equally-defensible paths exist and the right answer requires deliberation rather than information retrieval. Three-agent sequential loop (Opinion-Drafter → Goal-Auditor → Impact-Maximizer) iterates until convergence, then issues a single recommendation. Skip for trivial mechanical tasks (file ops, format conversions, single-fact lookups, information requests). Auto-fires before any clarifying question that asks the user to pick between substantive options.

1 Updated 3 weeks ago
LuciferDono
AI & Automation Listed

ask-the-council

Convenes a panel of opinionated advisors (parallel Claude subagents, each with a distinct mandate and a forbidden move so they genuinely diverge), then a Chairman synthesis that COMMITS to one recommendation with explicit tradeoffs. Use proactively for any high-stakes design, architecture, or tradeoff decision where credible options genuinely compete. Also on "ask the council", "the council", "get a panel". Not for fact-finding or decisions with one obvious answer — answer those directly.

13 Updated 1 months ago
alonbaron