reflect-and-improve
Skill1 starsChanged 9 months agoMITView on GitHub
Use after completing significant work, recovering from errors, or at session breakpoints to review actions, synthesize learnings, and write persistent improvements to memory files. Reduces repeated mistakes and user friction over time.
- Reads credentials
- Installs packages
- Commits and pushes
2 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- ShaishavMaisuria/research-paper-lifecycle-skillstheir own version, first seen Nov 1, 2026
- aroyburman-codes/claude-skillsedited, first seen Feb 18, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- aroyburman-codes/claude-skills★ 035% same
Wrote their own version · 1
- ShaishavMaisuria/research-paper-lifecycle-skills★ 59same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- prompt-coachSkill
- zero-slopSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 22 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈22
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
After completing multi-file edits, project setup, or debugging sessions
- Distinctive: line 13
After making an error and recovering from it
- Distinctive: line 15
After a tool call is denied and you adjusted approach
- Distinctive: line 20
Run these 6 steps in order.
- Distinctive: line 42
If 0 signals found, skip to step 6.
- Distinctive: line 68
Only record permissions observed 2+ times OR explicitly stated
- Distinctive: line 69
Never persist tokens, passwords, or secrets
- Distinctive: line 70
Update existing entries, don't append duplicates
- Distinctive: line 100
Only log errors likely to recur
- Distinctive: line 102
After 30 days with no recurrence, consider archiving
- Distinctive: line 117
Only record preferences confirmed by 2+ instances or explicit statement
- Distinctive: line 118
Don't duplicate what's already in CLAUDE.md or project config
- Distinctive: line 123
Write confirmed learnings to persistent memory files.
- Distinctive: line 138
Check if a relevant topic file exists (permissions.md, errors.md, preferences.md)
- Distinctive: line 139
If yes: update existing entries, add new ones, remove outdated ones
- Distinctive: line 140
If no: create the topic file
- Distinctive: line 141
Update MEMORY.md if it needs a link to a new topic file (keep under 200 lines)
- Distinctive: line 164
Every entry gets a "last updated" date
- Distinctive: line 166
If a preference contradicts recent behavior, update or remove it
- Distinctive: line 174
Edit, don't append: Keep files clean by updating existing entries.
- Distinctive: line 176
Privacy first: Never persist secrets, tokens, or personal data.
- Distinctive: line 177
Respect existing docs: Don't duplicate CLAUDE.md or project config.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Reflect and Improve
A self-improvement loop for Claude Code. After significant work, this skill reviews what happened — errors made, corrections received, implicit preferences — and writes confirmed learnings to persistent memory files. Future sessions start smarter.
When to Invoke
- After completing multi-file edits, project setup, or debugging sessions
- After making an error and recovering from it
- At natural session breakpoints (switching tasks, wrapping up)
- After a tool call is denied and you adjusted approach
- When explicitly requested
The Reflection Framework
Run these 6 steps in order. Skip any step with no findings.
1. Review Checkpoint
Scan recent actions for signals worth learning from.
Look for:
- Tool calls that failed or were retried
- User corrections ("no, I meant...", "not that file", "use X instead")
- Permission denials
- Approaches abandoned mid-way
- Tasks that required multiple attempts
Output format:
## Review Checkpoint — [date]
- [RETRY] Ran tests 3 times before realizing venv wasn't activated
- [CORRECTION] User said "use pnpm, not npm" — package manager preference
- [DENIED] User denied `git push` — wants to review before pushing
- [ABANDONED] Started editing wrong file, had to switchIf 0 signals found, skip to step 6.
2. Permission Patterns
Track which operations the user approved or denied.
Write to: permissions.md in the project memory directory
Format:
# Permission Patterns
Last updated: YYYY-MM-DD
## Approved
- git commit — always approved
- npm install — approved for this project
## Denied
- git push — user wants to review first
- modifying .env — never touch without asking
## Implicit
- if user asks to "set up tests", creating test files is implicitly approvedRules:
- Only record permissions observed 2+ times OR explicitly stated
- Never persist tokens, passwords, or secrets
- Update existing entries, don't append duplicates
3. Error Catalog
Classify errors and record the fix.
Error categories:
| Category | Example |
| Wrong assumption | Assumed Python 3.10 but project uses 3.8 |
| Missing context | Didn't read package.json before running npm commands |
| Tool misuse | Used cat instead of Read tool |
| Wrong file | Edited the test file instead of the source file |
| Stale knowledge | Used deprecated API method |
| Ordering error | Ran tests before installing dependencies |
Write to: errors.md in the project memory directory
Format:
# Error Catalog
Last updated: YYYY-MM-DD
## [date] Wrong assumption — Python version
- What happened: Used match/case syntax, but project requires Python 3.8
- Root cause: Didn't check pyproject.toml before writing code
- Prevention: Before writing Python code, check version requirementsRules:
- Only log errors likely to recur
- Include the prevention step — that's the value
- After 30 days with no recurrence, consider archiving
4. User Preference Signals
Capture implicit preferences revealed through behavior and corrections.
Signal types:
- Coding style: tabs vs spaces, quotes, naming conventions
- Communication style: prefers short answers, likes/dislikes emojis
- Tool choices: package manager, test framework, linter
- Workflow patterns: commits frequently vs batches, reviews diffs vs trusts agent
Write to: preferences.md in the project memory directory
Rules:
- Only record preferences confirmed by 2+ instances or explicit statement
- Don't duplicate what's already in CLAUDE.md or project config
- Project config wins over inferred preferences
5. Memory Synthesis
Write confirmed learnings to persistent memory files.
What qualifies:
- Pattern observed 2+ times this session
- Explicit user instruction ("always do X", "never do Y")
- Error with a clear prevention rule
- Stable permission pattern
What doesn't qualify:
- Speculation or single observations
- Anything already in project docs
- Session-specific context
- Sensitive data
Process:
- Check if a relevant topic file exists (permissions.md, errors.md, preferences.md)
- If yes: update existing entries, add new ones, remove outdated ones
- If no: create the topic file
- Update MEMORY.md if it needs a link to a new topic file (keep under 200 lines)
6. Friction Audit
Identify moments where the experience could be smoother.
Look for:
- User had to repeat themselves
- User had to correct a misunderstanding
- User provided context that should have been known
- A task took multiple rounds when one would suffice
Output format:
## Friction Audit — [date]
- User corrected package manager twice -> saved to preferences.md
- Had to re-read config file I should have cached -> read it first next timeFor each friction point, identify if there's a systemic fix and apply it.
Memory File Hygiene
- Every entry gets a "last updated" date
- During reflection, flag entries older than 90 days for review
- If a preference contradicts recent behavior, update or remove it
- Each topic file: aim for under 100 lines
- MEMORY.md: must stay under 200 lines
- Archive old entries when files grow too large
Key Principles
- Less is more. A few high-quality entries beat a bloated log.
- Edit, don't append. Keep files clean by updating existing entries.
- Confirm before persisting. Save observed facts, not assumptions.
- Privacy first. Never persist secrets, tokens, or personal data.
- Respect existing docs. Don't duplicate CLAUDE.md or project config.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

