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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is compact, well-structured, and provides a copy-paste-ready output template plus concrete workflow steps. Its main weakness is workflow_clarity: the durable-write operation has a single thin validation checkpoint and no explicit failure/recovery branch, which the rubric caps at 3.

Suggestions

Add an explicit failure branch after the 'Verify APPROVED status' step (e.g., if not approved, halt and route back to /cs:boardroom) so the durable write has a real validation feedback loop.

Tighten the 'Why Preserved Dissent' section to one line or fold it into the Preserved Dissent field of the record template to reclaim a few tokens.

Consider noting what to do if the llm-wiki bridge is absent or the write fails, so the batch-write path is robust rather than implicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding about concepts Claude already knows; the 'Why Preserved Dissent' rationale is domain-specific and earns its place, though it is a touch of explanation that could be trimmed.	4 / 5
Actionability	Highly actionable for an instruction-only skill: exact output paths, a copy-paste-ready decision record template, concrete routing commands, and explicit audit rules cover the common cases fully.	5 / 5
Workflow Clarity	The 7-step sequence is clear and includes an approval-validation checkpoint, but for a durable/batch write operation there is no error-recovery feedback loop or branch for when validation fails, which per the rubric cap holds this at 3.	3 / 5
Progressive Disclosure	A compact (~100 line), well-sectioned skill with clearly signaled, one-level-deep cross-skill references and no nested bundle references; per the simple-skill note this organization merits 5.	5 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both the capability and its trigger conditions in third-person voice. It is well-distinguished from sibling skills by its narrow, pipeline-bound niche.

Dimension	Reasoning	Score
Specificity	Names several concrete actions tied to a specific mechanism — 'Log a decision to two-layer memory via decision-logger', 'Approved memo becomes durable', 'raw transcripts kept for reference' — with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('Log a decision to two-layer memory... raw transcripts kept for reference') and when ('Use when the founder has approved a boardroom memo... right after /cs:boardroom concludes') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrasings are present ('Use when the founder has approved a boardroom memo', 'right after /cs:boardroom concludes') but domain vocabulary is somewhat narrow, missing a few synonyms.	4 / 5
Distinctiveness Conflict Risk	A clear niche — founder-approved boardroom memo becoming durable company memory — with distinct triggers tied to a specific pipeline, minimizing conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: c-level-agents/skills/decide/SKILL.md
Commit: 19392f7

Reviewed: ~7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.