Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Async Decision Memo

ASecurity

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...

1,330 stars
0 votes
0 copies
1 views
Added 9/3/2026
ai-agentsrustgit

Works with

cli

Security Analysis

A100/100

Scanned 9/3/2026

$npx -y skills add mohitagw15856/pm-claude-skills --skill async-decision-memo --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Async Decision Memo?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Async Decision Memo
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mohitagw15856-async-decision-memo/badge)](https://www.skillsdirectory.com/skills/mohitagw15856-async-decision-memo)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
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."
homepage: https://mohitagw15856.github.io/pm-claude-skills/skill/async-decision-memo.html
metadata:
  {
    "openclaw": { "emoji": "🔩" }
  }
---

# 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](../professional-brain/SKILL.md) `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

Attribution

mohitagw15856mohitagw15856
View sourceSee grades on GitHubMore from mohitagw15856 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →