Reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
Install
/plugin marketplace add sneg55/agent-starterThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add sneg55/agent-starter --skill reflectgit clone --depth 1 https://github.com/sneg55/agent-starter.git /tmp/agent-starter
mkdir -p ~/.claude/skills
cp -r /tmp/agent-starter/skills/reflect ~/.claude/skills/reflectPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Reflect: Per-Project Self-Improvement You are performing a reflection - turning the signal this project has captured into durable improvements. Nothing is applied without the developer's approval. ## Phase 1 - Orient (gather signal) - Run the stats script over the ledger: `~/.claude/hooks/harness-ledger-stats.sh --ledger .harness/ledger.jsonl --min-recurr 3` If that path doesn't exist, the hooks aren't installed at `~/.claude/hooks/` - run the copy from wherever this project keeps them. If the script prints all zeros there is no ledger yet (no signal captured) - stop; there is nothing to reflect on. - Read the current project rules in `CLAUDE.md` so you improve them rather than duplicate. - Read recent `feedback`-type memory files - these are the developer's explicit corrections and are the highest-value signal. Locate the memory directory first (it sits next to `MEMORY.md`; `find . -name MEMORY.md` if unsure), then `grep -l 'type: feedback' <memory-dir>/*.md`. - Read the most recent `.harness/reflections/*.md` report (if any) to recall the last metric snapshot and what was already changed. ## Phase 2 - Cluster From the stats output and feedback memories, identify recurring problems: - Each `recurring <rule> <prefix> <count>` line is a friction cluster - the same check keeps firing in the same area. - Group related feedback corrections by theme. - Ignore one-off events; focus on what repeats. ## Phase 3 - Propose (one candidate per cluster)
Details
- Skill name
reflect- Repository
- sneg55/agent-starter
- Path
skills/reflect/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Reflect skill do?
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
How do I install the Reflect skill?
Claude Code plugin: /plugin marketplace add sneg55/agent-starter. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Reflect popular?
It lives in sneg55/agent-starter, which has 75 GitHub stars and 4 forks, and is included in 1 curated skill list.
Related skills
Adopt Project
75sneg55/agent-starter
Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or wants starter patterns in an existing codebase.
Commit
75sneg55/agent-starter
Create a single well-crafted git commit from current changes. Analyzes diff, follows repo's commit style, and writes a concise "why not what" message.
Commit Push PR
75sneg55/agent-starter
Full git workflow - creates branch, commits, pushes, and creates or updates a PR with summary and test plan.
Commit
44iOfficeAI/AionHub
Generate commit messages following project conventions and commit staged changes. Use when the user explicitly asks to commit, create a commit, or run /commit.
Popup Studio
47daaihq/da-popup-studio
用户给一个主题,一步步做出纸艺立体书短片:三个剧本大纲 → 详细剧情 → 元素图提示词 → 配音脚本 → 用上传的图和配音渲染视频(音效版 + 配音版 + 封面)。视频风格可选立体书或旋转木马立体书。用户说做立体书、旋转木马书、立体书视频或给出立体书主题时使用。
Jianghushuo Perspective
49simonsxxs/jianghushuo-skill
姜胡说(姜志辉)的思维框架与表达方式:7个核心心智模型、10条决策启发式与完整表达DNA。 用途:作为思维顾问,用姜胡说的视角分析问题、审视决策、提供反馈。 当用户提到「用姜胡说的视角」「姜胡说会怎么看」「胡子哥模式」时使用;「帮我用姜胡说的角度想想」「如果姜胡说会怎么做」「切换到胡子哥」也应触发;英文表达如 "jianghushuo perspective"、"what would Jiang Hushuo say/think" 同样触发。 不在一般性问题上自动触发。用户要求评价、比较或分析姜胡说本人及其观点(第三人称讨论)时不进入角色扮演,正常作答即可。
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.