/cs:decide — Log the Decision
/cs:decide <memo> — Log a decision to two-layer memory via decision-logger.
How to use it
Claude Code
- Run the line below. It pulls the whole folder into
~/.claude/skills/decide, including the files SKILL.md points to. - Describe your job in plain words. Claude Code follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit alirezarezvani/claude-skills/c-level-agents/skills/decide#main ~/.claude/skills/decideFor one project only, change the path to .claude/skills/decide. This skill also uses company-context.md — copying SKILL.md alone won't be enough. See the folder on GitHub.
Claude (web or desktop app)
- On this page open ⋯ → Download .md.
- Save it as SKILL.md in a folder, zip the folder, then Customize → Skills → + → Create skill → Upload a skill.
- Pick the file and Save. Claude shows the name and description and runs a security scan.
- Check the skill is switched on.
- Start a new chat and describe your job in plain words. The AI follows the skill from there.
ChatGPT or another app
- ChatGPT: make a Project and paste it into Instructions.
- Neither? Paste it at the top of a new chat — it works for that chat.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Source of /cs:decide — Log the Decision
Show the full text105 lines
| name | description |
|---|---|
| decide | /cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for reference. Use when the founder has approved a boardroom memo and the decision must become durable company memory — e.g. right after /cs:boardroom concludes. |
/cs:decide — Log the Decision
Command: /cs:decide <memo-path>
Logs the founder's decision via the decision-logger skill. This is the gate where in-session deliberation becomes durable company memory.
Pipeline Position
/cs:office-hours → /cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem
↑ you are here
Two-Layer Memory Model
The decision-logger skill maintains two layers:
- Raw transcripts — every boardroom session, every advisor's Phase 2 position, every dissent. Stored under
~/.claude/decisions/raw/. Reference only, never feeds back automatically. - Approved decisions — only the founder-signed memos. Stored under
~/.claude/decisions/approved/. Feeds into future/cs:office-hoursand/cs:founder-modecalls.
This split prevents the system from "remembering" unresolved debates as if they were decisions.
Input
A board memo file (output of /cs:boardroom).
Workflow
- Read the memo path
- Verify it has founder approval (status: APPROVED)
- Extract structured decision record:
- Decision title
- Date decided
- Option chosen
- Success + kill criteria
- Dissent (preserved)
- Review checkpoint date
- Append to
~/.claude/decisions/approved/<YYYY-MM-DD>-<slug>.md - Update the raw transcript pointer
- If llm-wiki bridge configured, write to vault (
~/company-vault/10-decisions/) - Schedule auto-revisit (90 days)
Output Record Format
# Decision: <title>
**Decided:** YYYY-MM-DD
**By:** <founder name>
**Memo:** <link to boardroom memo>
**Brief:** <link to original brief>
**Review checkpoint:** YYYY-MM-DD (90d default)
## Decision
**Chose:** <option>
**Rejected:** <other options + one-line why>
## Success Criteria (binding)
- <metric, threshold, timeframe>
## Kill Criteria (binding)
- <metric, threshold, action>
## Preserved Dissent
- **<dissenter>:** <unresolved concern>
- (preserved verbatim; dissent never erased)
## Next Action
- `/cs:execute` → 90-day plan due <date>
## Status History
- YYYY-MM-DD: APPROVED
Why Preserved Dissent
The biggest risk in approved decisions is forgetting why someone disagreed. When the kill criteria trigger, the dissent often turns out to have been correct. Preserving it verbatim — not summarized — keeps the company honest at post-mortem time.
Routing
/cs:execute <decision>— build the 90-day plan/cs:freeze <decision> <days>— lock if irreversible- (Auto-scheduled)
/cs:post-mortem <decision>— at 90-day checkpoint
Stale-Decision Audit
cs-chief-of-staff runs a weekly stale audit:
- Decisions > 90 days without revisit → flag for
/cs:post-mortem - Decisions with kill criteria triggered → flag immediately
- Decisions whose company-context.md basis has changed → flag for re-examination
Related
- Skill:
decision-logger - Agent:
cs-chief-of-staff - Bridge:
../../references/llm-wiki-bridge.md
Version: 1.0.0
| 1 | |
| 2 | name "decide" |
| 3 | description "/cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for reference. Use when the founder has approved a boardroom memo and the decision must become durable company memory — e.g. right after /cs:boardroom concludes." |
| 4 | |
| 5 | |
| 6 | # /cs:decide — Log the Decision |
| 7 | |
| 8 | **Command:** `/cs:decide <memo-path>` |
| 9 | |
| 10 | Logs the founder's decision via the `decision-logger` skill. This is the gate where in-session deliberation becomes durable company memory. |
| 11 | |
| 12 | ## Pipeline Position |
| 13 | |
| 14 | |
| 15 | /cs:office-hours → /cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem |
| 16 | ↑ you are here |
| 17 | |
| 18 | |
| 19 | ## Two-Layer Memory Model |
| 20 | |
| 21 | The `decision-logger` skill maintains two layers: |
| 22 | |
| 23 | **Raw transcripts** — every boardroom session, every advisor's Phase 2 position, every dissent. Stored under `~/.claude/decisions/raw/`. Reference only, never feeds back automatically. |
| 24 | **Approved decisions** — only the founder-signed memos. Stored under `~/.claude/decisions/approved/`. Feeds into future `/cs:office-hours` and `/cs:founder-mode` calls. |
| 25 | |
| 26 | This split prevents the system from "remembering" unresolved debates as if they were decisions. |
| 27 | |
| 28 | ## Input |
| 29 | |
| 30 | A board memo file (output of `/cs:boardroom`). |
| 31 | |
| 32 | ## Workflow |
| 33 | |
| 34 | Read the memo path |
| 35 | Verify it has founder approval (status: APPROVED) |
| 36 | Extract structured decision record: |
| 37 | Decision title |
| 38 | Date decided |
| 39 | Option chosen |
| 40 | Success + kill criteria |
| 41 | Dissent (preserved) |
| 42 | Review checkpoint date |
| 43 | Append to `~/.claude/decisions/approved/<YYYY-MM-DD>-<slug>.md` |
| 44 | Update the raw transcript pointer |
| 45 | If llm-wiki bridge configured, write to vault (`~/company-vault/10-decisions/`) |
| 46 | Schedule auto-revisit (90 days) |
| 47 | |
| 48 | ## Output Record Format |
| 49 | |
| 50 | |
| 51 | # Decision: <title> |
| 52 | **Decided:** YYYY-MM-DD |
| 53 | **By:** <founder name> |
| 54 | **Memo:** <link to boardroom memo> |
| 55 | **Brief:** <link to original brief> |
| 56 | **Review checkpoint:** YYYY-MM-DD (90d default) |
| 57 | |
| 58 | ## Decision |
| 59 | **Chose:** <option> |
| 60 | **Rejected:** <other options + one-line why> |
| 61 | |
| 62 | ## Success Criteria (binding) |
| 63 | - <metric, threshold, timeframe> |
| 64 | |
| 65 | ## Kill Criteria (binding) |
| 66 | - <metric, threshold, action> |
| 67 | |
| 68 | ## Preserved Dissent |
| 69 | - **<dissenter>:** <unresolved concern> |
| 70 | - (preserved verbatim; dissent never erased) |
| 71 | |
| 72 | ## Next Action |
| 73 | - `/cs:execute` → 90-day plan due <date> |
| 74 | |
| 75 | ## Status History |
| 76 | - YYYY-MM-DD: APPROVED |
| 77 | |
| 78 | |
| 79 | ## Why Preserved Dissent |
| 80 | |
| 81 | The biggest risk in approved decisions is forgetting why someone disagreed. When the kill criteria trigger, the dissent often turns out to have been correct. Preserving it verbatim — not summarized — keeps the company honest at post-mortem time. |
| 82 | |
| 83 | ## Routing |
| 84 | |
| 85 | `/cs:execute <decision>` — build the 90-day plan |
| 86 | `/cs:freeze <decision> <days>` — lock if irreversible |
| 87 | (Auto-scheduled) `/cs:post-mortem <decision>` — at 90-day checkpoint |
| 88 | |
| 89 | ## Stale-Decision Audit |
| 90 | |
| 91 | `cs-chief-of-staff` runs a weekly stale audit: |
| 92 | Decisions > 90 days without revisit → flag for `/cs:post-mortem` |
| 93 | Decisions with kill criteria triggered → flag immediately |
| 94 | Decisions whose company-context.md basis has changed → flag for re-examination |
| 95 | |
| 96 | ## Related |
| 97 | |
| 98 | Skill: [`decision-logger`] |
| 99 | Agent: [`cs-chief-of-staff`] |
| 100 | Bridge: [`../../references/llm-wiki-bridge.md`] |
| 101 | |
| 102 | |
| 103 | |
| 104 | **Version:** 1.0.0 |
| 105 |
Discussion
Poke Holes In My Plan Before I CommitPaste the plan or decision you're about to make and get back its strongest weaknesses, blind spots, and hidden assumptions — plus a tougher version of the plan.Clinical Decision-Support Research and EvaluationPrepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.Tough Decision Advisor: Every Angle ConsideredHand in a decision you're stuck on. Get back a clear breakdown of every angle — the trade-offs, the risks, the blind spot, and a recommended path.What-If Oracle — Possibility Space ExplorerYou describe a decision you're weighing; you get back best-case, likely, and worst-case outcomes with the early warning signs and the safest moves to make now.
Browse more free Claude skills or everything in Product.