SkillAgentSearch skills...

async-decision-memo

Run a decision asynchronously — the memo, the silent-read window, the comment protocol, and the deadline that makes it land without a meeting

Install / Use

npx skills add mohitagw15856/pm-claude-skills --skill async-decision-memo

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Supported Platforms

Universal

Tags

Our assessment of async-decision-memo

async-decision-memo scores 82/100 on our quality scale, 841st of 1,144 Content & Media skills we index.

Its SKILL.md is 5.5 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.

With 1,396 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
13/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 8 days ago, so async-decision-memo is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

async-decision-memo compared with similar skills

All 4 of these similar skills score higher than async-decision-memo; compare them before choosing.

SkillScoreStarsUpdatedFormat
async-decision-memo (this skill)by mohitagw15856821.4k8d agoSKILL.md
siyuanby siyuan-note10046.6ktodayMCP Server
algorithmic-artby anthropics100177.9k10d agoSKILL.md
pptxby anthropics100177.9k10d agoSKILL.md
designby nextlevelbuilder100130.2k11d agoSKILL.md

Frequently asked questions

How do I install async-decision-memo?
Run npx skills add mohitagw15856/pm-claude-skills --skill async-decision-memo. The install tabs above show the steps for each supported agent.
Which AI agents does async-decision-memo work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is async-decision-memo safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is async-decision-memo still maintained?
The repository was last updated 8 days ago, so async-decision-memo is actively maintained.

name: async-decision-memo description: "Run a decision asynchronously — the memo, the silent-read window, the comment protocol, and the deadline that makes it land without a meeting. Use when asked to decide something async, replace a decision meeting with a document, run an Amazon-style written decision process, or when a decision keeps stalling in comment threads. Produces the decision memo plus the process wrapper: reader roles, response windows, comment-resolution rules, and the tie-breaker. For the document structure alone use decision-memo; this skill runs the process around it."

Async Decision Memo Skill

Remote teams keep reinventing this badly: someone posts a doc, twelve people leave drive-by comments over two weeks, nothing resolves, and the decision happens in a meeting anyway — now with resentment. The async decision is a process with a deadline, not a document with comments enabled. This skill runs the whole protocol.

What This Skill Produces

  • The decision memo (structured for silent reading, with the recommendation up front)
  • The process wrapper: named roles, response windows, comment-resolution rules, escalation
  • The kickoff message that opens the window and the closing note that records the outcome

Required Inputs

Ask for (if not already provided):

  • The decision — what's being decided, the options, the recommendation and its reasoning (rough notes fine)
  • The people: who decides (one name), who must be consulted (their objection could change the answer), who is merely informed
  • The clock: when is this decision needed, and what does it block
  • The stakes — reversible or one-way-door? (Sets the window length and the bar for escalation)

The Protocol

  1. Write the memo for a silent first read. Structure: the decision needed (one sentence) · the recommendation (up front — burying it invites a treasure hunt) · context in prose (full sentences force complete thinking; bullets hide gaps) · options considered with real trade-offs (a strawman option list discredits the whole memo) · what would change my mind (the single highest-trust section — name the evidence that would flip the recommendation) · cost of deciding slowly (why the deadline is real). Target ≤2 pages; past that, the memo needs editing, not more patience.
  2. Assign the three roles by name. The decider (exactly one; "the group decides" is how nothing does) · consulted (listed individually — their silence is treated as consent and they know it) · informed (get the outcome, not a comment invitation). The role list ships in the kickoff, not in anyone's imagination.
  3. Open a bounded window. Reversible decisions: 2-3 working days. One-way doors: up to a week, never more — an async process longer than a week isn't deliberation, it's drift. The kickoff states the close date/time and timezone, and that silence from consulted = consent.
  4. Enforce the comment protocol. Comments must be one of: objection (with reasoning — and where possible, what evidence would resolve it) · question (answered by the author within a working day) · improvement (accepted/declined by the author, no debate thread). Preference restatements and drive-bys get one reply: "noted — not an objection." Threads longer than 3 exchanges move to a 15-minute call between those two people only, whose outcome is written back into the thread.
  5. Close on time, whatever the state. At the deadline the decider: decides (the default) · extends once with a reason and new date · or escalates (only for an unresolved objection on a one-way door). The closing note records: the decision, the dissent as stated by the dissenter, what would reopen it, and who does what by when. Dissent recorded ≠ decision reopened — disagree-and-commit is the exit, and the note says so.
  6. File it. The memo + closing note land where decisions live (the decision log, the Brain's decisions/ if one exists) — an async decision that lives in a chat scrollback will be relitigated by someone who "never saw it."

Output Format

Async Decision: [title] — window closes [date, tz]

Roles: Decider: [name] · Consulted: [names] (silence = consent) · Informed: [names]

The memo (structured per the protocol above)

Kickoff message (ready to post): [what's being decided, the recommendation exists — read before commenting, the window, the comment protocol in two lines, silence rule]

Closing note template: Decision: […] · Dissent, as stated: […] · Reopens if: […] · Actions: [who/what/when] · Filed: [where]

Quality Checks

  • [ ] Exactly one named decider; consulted people listed individually
  • [ ] The recommendation appears before the context, not after it
  • [ ] "What would change my mind" names specific evidence, not humility theatre
  • [ ] The window has a date, time, and timezone; the silence rule is stated in the kickoff
  • [ ] The closing note records dissent verbatim and the reopen condition

Anti-Patterns

  • [ ] Do not open comments without the protocol — an unbounded comment section is the meeting you were avoiding, slower
  • [ ] Do not run a memo without a decider — consensus-by-exhaustion is not an outcome
  • [ ] Do not let threads run past 3 exchanges — two people arguing in a doc are holding everyone else hostage
  • [ ] Do not extend the window twice — the second extension means the memo was premature; withdraw and rewrite it
  • [ ] Do not soften recorded dissent into "some concerns were raised" — the dissenter's actual words, or the record is fiction

Related Skills

View on GitHub
GitHub Stars1.4k
CategoryContent
Updated8d ago
Forks249

Languages

HTML

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions