Agent skill

Self Retrospective

by kid0317 in kid0317/crewai_mas_demo

Agent 自我复盘:读取 L2/L3/L1 日志,调用 LLM 生成结构化改进提案, 写入 proposals.json 并发通知至 human.json 等待审批。

No licenceAuto-check passedProduct & Project Management

Install Self Retrospective

skills CLI
$ npx skills add kid0317/crewai_mas_demo --skill self-retrospective -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kid0317/crewai_mas_demo self-retrospective --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kid0317/crewai_mas_demo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/self-retrospective .claude/skills/self-retrospective && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
self-retrospective
GitHub stars
165
Token cost
~505 tokens
SKILL.md length
77 words
Files
2 (incl. scripts)
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

Agent 自我复盘:读取 L2/L3/L1 日志,调用 LLM 生成结构化改进提案, 写入 proposals.json 并发通知至 human.json 等待审批。

  • Works in 6 steps: 读取 L2 日志,找出质量最低的任务 → 读取对应 L3 日志,找到具体失败节点 → 读取 L1 中相关的人类纠正记录 → …
  • Tasks that involve Retrospectives
  • SKILL.md covers 功能概述, 调用方式, 输出格式(JSON) and ⚠️ 强制执行要求(CRITICAL), plus 1 more section
  • Runs Python scripts from its folder; calls pip and python3; needs ALIYUN_API_KEY

What it does

Self Retrospective is an agent skill from kid0317/crewai_mas_demo. Agent 自我复盘:读取 L2/L3/L1 日志,调用 LLM 生成结构化改进提案, 写入 proposals.json 并发通知至 human.json 等待审批。 适用场景:Agent 在完成足够多任务后,触发自我评估和改进提案生成。

Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/self_retro.py`).

It sits in Product & Project Management, covering Retrospectives and Proposals and quotes.

When your agent uses it

  • Tasks that involve Retrospectives
  • Tasks that involve Proposals and quotes

Example prompts

  • “/self-retrospective”

Requirements

  • Python 3
  • A credential in ALIYUN_API_KEY

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 读取 L2 日志,找出质量最低的任务
  2. 读取对应 L3 日志,找到具体失败节点
  3. 读取 L1 中相关的人类纠正记录
  4. 调用 LLM 生成结构化改进提案(Pydantic schema 约束)
  5. 写入 /mnt/shared/proposals/proposals.json
  6. 发通知至 /mnt/shared/mailboxes/human.json 等待审批

What it can do on your machine

Read from SKILL.md and the folder at commit d5cfc79. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ALIYUN_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Self Retrospective loads about 505 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 77 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~505

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 77 words (~505 tokens).

name
self-retrospective
type
task

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in skills/self-retrospective of kid0317/crewai_mas_demo.

  • SKILL.md
  • scripts/self_retro.py

Open the folder on GitHubat commit d5cfc79

Compare with similar skills

Self Retrospective next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Self Retrospective compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Self Retrospective this skillkid0317/crewai_mas_demo165—~505Automated safety check: PassNone
TuneNecmttn/ax115—~1.3kAutomated safety check: PassAGPL-3.0
RetroNecmttn/ax115—~3.5kAutomated safety check: PassAGPL-3.0
Harness ReckoningFairladyZ625/harness-anything226—~768Automated safety check: PassAGPL-3.0
Weekly Engineering Retrogarrytan/gstack136k—~2.4kAutomated safety check: PassMIT
Dough Execute Planterryyin/lizard2.5k—~4.3kAutomated safety check: PassCustom licence

Similar skills

  • Tune

    Necmttn/ax

    Retrospective on one coding session that proposes changes to the agent's environment (hooks, checks, steering files, tool access) and files each as an ax proposal.

    115 GitHub stars~1.3k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Retro

    Necmttn/ax

    Guided experiment-loop retrospective over the ax agent-experience graph.

    115 GitHub stars~3.5k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Harness Reckoning

    FairladyZ625/harness-anything

    Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.

    226 GitHub stars~768 tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Dough Execute Plan

    terryyin/lizard

    Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…

    2.5k GitHub stars~4.3k tokensUpdated 4 days ago
    Product & Project ManagementAuto-check passed
  • Oral Paper Skill

    Adkid-Zephyr/oral-paper-skill

    Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.

    357 GitHub stars~1.9k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed

More from kid0317/crewai_mas_demo

All 12 skills in this repo
  • Skill Creator

    kid0317/crewai_mas_demo

    Create new skills and save them to the project's shared skills directory.

    165 GitHub stars~1.6k tokensUpdated 4 mo ago
    Auto-check passed
  • Mailbox

    kid0317/crewai_mas_demo

    收发邮件,与团队成员通信。第27课新增:支持向 human.json 发消息(单一接口约束:只有 manager 可以发)。

    165 GitHub stars~726 tokensUpdated 4 mo ago
    Auto-check passed
  • Mailbox Ops

    kid0317/crewai_mas_demo

    数字员工邮箱操作(三态状态机):sendmail / readinbox / markdone / markdoneall / resetstale。

    165 GitHub stars~700 tokensUpdated 4 mo ago
    Auto-check passed
  • Memory Governance

    kid0317/crewai_mas_demo

    A skill your agent uses to audit and clean up workspace memory files and the skills directory.

    165 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check: notes
  • Memory Save

    kid0317/crewai_mas_demo

    A skill your agent uses to persist important information from the conversation to workspace files so it survives across sessions.

    165 GitHub stars~781 tokensUpdated 4 mo ago
    Auto-check passed
  • Software Dev Sop

    kid0317/crewai_mas_demo

    Software development delivery SOP for an Orchestrator agent.

    165 GitHub stars~1.7k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Self Retrospective

What does Self Retrospective do?

Agent 自我复盘:读取 L2/L3/L1 日志,调用 LLM 生成结构化改进提案, 写入 proposals.json 并发通知至 human.json 等待审批。. Self Retrospective is an agent skill from kid0317/crewai_mas_demo.

When should I use Self Retrospective?

Self Retrospective fits situations like: tasks that involve Retrospectives; tasks that involve Proposals and quotes.

How do I install Self Retrospective in Claude Code?

Run `npx skills add kid0317/crewai_mas_demo --skill self-retrospective -a claude-code`. Or copy the skill folder (skills/self-retrospective in kid0317/crewai_mas_demo) into .claude/skills/self-retrospective in your project. Claude Code loads it when a task matches its description.

How do I install Self Retrospective in Codex?

Run `npx skills add kid0317/crewai_mas_demo --skill self-retrospective -a codex`. Or copy the skill folder (skills/self-retrospective in kid0317/crewai_mas_demo) into .agents/skills/self-retrospective in your project. Codex loads it when a task matches its description.

Can I use Self Retrospective in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kid0317/crewai_mas_demo --skill self-retrospective -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-retrospective, .gemini/skills/self-retrospective, .github/skills/self-retrospective and .opencode/skills/self-retrospective in your project.

What does Self Retrospective need to run?

Going by SKILL.md and its folder, Self Retrospective needs Python for the scripts in its folder, the command-line tools its instructions call (pip and python3) and credentials named ALIYUN_API_KEY. Our summary lists: Python 3; A credential in ALIYUN_API_KEY.

Does Self Retrospective access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Self Retrospective safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Self Retrospective use?

No licence was found for Self Retrospective or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Self Retrospective use?

About 505 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Self Retrospective?

Skills that share tags, products or a category with Self Retrospective: Tune (Necmttn/ax, 115 stars), Retro (Necmttn/ax, 115 stars), Harness Reckoning (FairladyZ625/harness-anything, 226 stars) and Weekly Engineering Retro (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Self Retrospective?

kid0317 (a GitHub user) maintains it in kid0317/crewai_mas_demo, which has 165 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on May 25, 2026.

Source: kid0317/crewai_mas_demo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.