Criticism Self Criticism
v1.0.0触发：当一项工作已经完成、进入阶段验收、收到批评反馈，或反复出现同类错误需要系统纠偏时调用；常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoin...
⭐ 0· 46·0 current·0 all-time
by@arg0
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (structured self-review, retrospectives, quality checks) align with the provided SKILL.md and checklist files. Nothing in the skill requests access to unrelated services or capabilities.
Instruction Scope
SKILL.md contains procedural guidance and checklists for self-criticism and review. It does not instruct the agent to read system files, access environment variables, contact external endpoints, or collect credentials. All instructions stay within the stated domain of review and reflection.
Install Mechanism
No install spec and no code files that would be written to disk or executed. Instruction-only skills are lowest technical risk and this one has no install actions.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no surprising secret requests or unrelated credential needs.
Persistence & Privilege
Flags are default (always: false, user-invocable true, model invocation allowed). The skill does not request permanent presence or modify other skills; autonomy is the platform default but not elevated here.
Assessment
Technical risk is low — this skill only provides review/process guidance and requires no installs or credentials. Before installing, consider whether the ideological framing and quoted source material align with your organization's policies and culture. Also: (1) avoid feeding sensitive PII or confidential documents into any automated review without consent and proper safeguards; (2) if you do not want the agent to call this skill autonomously, adjust your agent/skill invocation settings; and (3) review and possibly adapt the guidance so it fits your team norms (to prevent abusive or punitive use of 'criticism' in interpersonal contexts).Like a lobster shell, security has layers — review code before you run it.
latestvk9714vs4xp8nhb45sb5n38mc2h83rj6j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.