Criticism Self Criticism
Criticism Self Criticism is an agent skill (a SKILL.md file) from HughYau/qiushi-skill. 批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。 English: Criticism and self-criticism. It works with Claude Code, Codex, Cursor and OpenCode and has 3,830 GitHub stars across a repository of 3 listed skills. Install it by copying the skill folder into your agent's skills directory.
github.com/HughYau/qiushi-skill/skills/criticism-self-criticism (opens in a new tab)
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Plugin marketplace
- Security
- Maintained
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add HughYau/qiushi-skill
/plugin install qiushi-skill@qiushi-skillIn the Claude apps, zip the criticism-self-criticism folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/HughYau/qiushi-skill.git
cp -r qiushi-skill/skills/criticism-self-criticism .agents/skills/criticism-self-criticism # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/HughYau/qiushi-skill.git
cp -r qiushi-skill/skills/criticism-self-criticism .cursor/skills/criticism-self-criticism # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
批评与自我批评:在工作完成、阶段验收、收到批评或同类错误反复出现时,对成果和过程做诚实、具体、基于事实的审视,输出可执行的改进项,并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗";任务刚开始或只是单步查询时不触发。 English: Criticism and self-criticism. After delivery, at a review checkpoint, on receiving criticism, or when the same mistake recurs, examine the result and the process honestly and concretely, produce actionable fixes, and accept valid criticism without defensiveness.
When it triggers
- Triggers include review, retrospective, audit, "check this for problems", "are you sure"; skip at the start of a task or for one-step lookups.
- "帮我看看有没有问题"
- "你确定吗"
- "check this for problems"
- "are you sure"
More skills in HughYau/qiushi-skill
3 skills are listed from this repository.
Similar skills
More security skills
Hunt LLM AI
elementalsouls/Claude-BugHunter
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10).
Active · last commit Oct 25, 2026
SecurityPythonPinme R2
glitternetwork/pinme
Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination.
Maintained · last commit Jul 12, 2026
SecurityTypeScriptLean Ctx Review
yvgude/lean-ctx
Review how the lean-ctx ctx* MCP tools performed in the current session and file upstream issues for confirmed problems.
Active · last commit Oct 26, 2026
SecurityRustAgentwhy Session Audit
davepoon/buildwithclaude
Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open…
Maintained · last commit Oct 26, 2026
SecurityPythonPentest Commands
zebbern/claude-code-guide
This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto"…
Maintained · last commit Oct 24, 2026
SecurityPythonCtf Malware
ljagiello/ctf-skills
Provides malware analysis and network traffic techniques for CTF challenges.
Maintained · last commit Oct 26, 2026
SecurityPython
How do I install the Criticism Self Criticism skill?
In Claude Code, run /plugin marketplace add HughYau/qiushi-skill and then /plugin install qiushi-skill@qiushi-skill. For Codex or Cursor, copy the criticism-self-criticism folder into .agents/skills/ or .cursor/skills/.
Is the Criticism Self Criticism skill free?
Yes. The repository is open source under the MIT license.
Is Criticism Self Criticism maintained?
The repository's most recent commit was on Oct 1, 2026. appsgit only lists skills from repositories with a commit in the last six months.