Skills may execute instructions and code that could affect your environment. Marketplace scans reduce risk but do not guarantee safety. Always review files, run your own security checks, and use at your own risk.

I understand these skills can contain unsafe or unintended behavior, and I will review and security-scan before use. No warranty, suitability, or outcome is guaranteed.

C-Level AdvisoryFree Safe

decide

Security Scan Summary

Status: Safe

Source: Syntic Skills registry

Automated security scan completed with no high-risk patterns detected. Manual review is still required.

About This Skill

Use when an approved boardroom memo becomes durable company memory—e.g., right after boardroom conclusion with founder approval.

Downloadable SKILL.md

Download SKILL.md and place it in your Syntic skills folder. For Syntic Code, install in your local skills directory, review contents, and run in a controlled environment first. Acknowledge the risk notice above to enable the download.

SKILL.md

---
name: decide
description: Use when an approved boardroom memo becomes durable company memory—e.g., right after boardroom conclusion with founder approval.
category: C-Level Advisory
version: 1.0.0
tools: []
---

# Log the Decision

Logs the founder's decision via decision memory. This is where in-session deliberation becomes durable company memory.

## Two-Layer Memory Model

**Layer 1 — Raw Transcripts** (~/.claude/decisions/raw/)
- Every boardroom session, each role's Phase 2 position, Phase 3 critique, Phase 4 synthesis, all debates
- Reference only, never auto-loaded

**Layer 2 — Approved Decisions** (~/.claude/decisions/approved/)
- ONLY founder-approved decisions and actions
- Auto-loaded in future deliberations
- Append-only; never deleted, only superseded

This split prevents unresolved debates bleeding into future decisions.

## Input

A board memo with founder approval status.

## Workflow

1. Verify memo has founder approval (status: APPROVED)
2. Extract decision: title, date, option chosen, success criteria, kill criteria, preserved dissent
3. Append to ~/.claude/decisions/approved/<YYYY-MM-DD>-<slug>.md
4. Update raw transcript pointer
5. Schedule auto-revisit (90 days)

## Decision Entry Format

```
## [YYYY-MM-DD] — [TITLE]

**Decision:** [One clear statement.]
**Owner:** [One person—accountable.]
**Deadline:** [YYYY-MM-DD]
**Review:** [YYYY-MM-DD]
**Rationale:** [Why this over alternatives. 1-2 sentences.]

**User Override:** [If founder changed recommendation—what and why.]

**Rejected:**
- [Proposal] — [reason] [DO_NOT_RESURFACE]

**Action Items:**
- [ ] [Action] — Owner: [name] — Due: [YYYY-MM-DD] — Review: [YYYY-MM-DD]

**Supersedes:** [DATE of previous decision on same topic]
```

## Conflict Detection

Before logging, check for:
1. DO_NOT_RESURFACE violations (new decision matches rejected proposal)
2. Topic contradictions (two active decisions on same topic, different conclusions)
3. Owner conflicts (same action assigned to different people)

## Preserved Dissent

Never erase dissent. When kill criteria trigger, dissent often turns out correct. Preserve verbatim—not summarized—to keep the company honest at post-mortem time.

Bundle Download

Includes SKILL.md and bundled support files where provided. Risk acknowledgement is required.

Install Targets

Syntic App

1. Create a dedicated folder for this skill in your local skills library.
2. Place SKILL.md into that folder.
3. Restart Syntic and invoke this skill on matching tasks.

Syntic Code (CLI)

1. Save SKILL.md in your local Syntic Code skills directory.
2. Keep related files in the same skill folder.
3. Run in a safe environment and validate outputs.

Source

https://github.com/alirezarezvani/claude-skills/blob/main/c-level-advisor/c-level-agents/skills/decide/SKILL.md

Open Source Link

C-Level Advisory

Related Skills