New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Self Improving Agent

by OpenMinis in OpenMinis/MinisSkills

Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable…

MITAuto-check passed

Install Self Improving Agent

skills CLI
$ npx skills add OpenMinis/MinisSkills --skill self-improving-agent -a claude-code

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

GitHub CLI
$ gh skill install OpenMinis/MinisSkills self-improving-agent --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/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/self-improving-agent .claude/skills/self-improving-agent && 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-improving-agent
GitHub stars
444
Token cost
~3.6k tokens
SKILL.md length
1,354 words
Files
8 (incl. scripts)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable…

  • Works in 5 steps: A command or operation fails and the… → User correction: You point out where my… → Knowledge update or outdated assumption… → …
  • Operation fails
  • SKILL.md covers Minis Directory Conventions, Current Final Rules, Quick Reference and Trigger Logging Rules (Minis…, plus 8 more sections
  • Runs Shell scripts from its folder; calls sh

What it does

Self Improving Agent is an agent skill from OpenMinis/MinisSkills. Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable solution is found. Review historical learnings before important tasks. Avoid triggering during ordinary chat, for temporary mistakes that do not need to be logged, or when the user has explicitly said not to log.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts (for example `data/ERRORS.md`, `data/FEATURE_REQUESTS.md` and `data/LEARNINGS.md`).

The repository describes itself as: Skills collection for Minis. The licence is MIT.

When your agent uses it

  • Operation fails
  • The user corrects you
  • Outdated knowledge is identified
  • An external API fails

Example prompts

  • “/self-improving-agent”

Requirements

  • A Bash shell

Workflow steps

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

  1. A command or operation fails and the cause is not obvious: For example, permissions, paths, dependencies, network issues, or third-party…
  2. User correction: You point out where my understanding is wrong, where my logic does not match the actual behavior of this software, or…
  3. Knowledge update or outdated assumption correction: A previous assumption is found not to apply to Minis, or documentation or…
  4. Reusable better solution: A stable practice, convention, template, or workflow emerges that can significantly reduce rework.
  5. Recurring pattern: Similar issues appear repeatedly within the same task, or across tasks or projects.

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. 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/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • sh

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Self Improving Agent loads about 3.6k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 1,354 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 1,354 words, ~3,593 tokens.

Download SKILL.mdSave it as .claude/skills/self-improving-agent/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
self-improving-agent
description
Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable solution is found. Review historical learnings before important tasks. Avoid triggering during ordinary chat, for temporary mistakes that do not need to be logged, or when the user has explicitly said not to log.
metadata.language
en-US
metadata.scope
minis

Self-Improvement Skill (Minis Edition)

This skill is used in the Minis environment to record errors, corrections, and reusable best practices, creating a traceable learning loop.

Minis Directory Conventions

  • Working directory: /var/minis/workspace/
  • Default learning log directory for this skill: /var/minis/skills/self-improving-agent/data/
  • Public learning log directory within this skill (after promotion): /var/minis/skills/self-improving-agent/data/public/
  • Project-level learning log directory (optional): <project>/.learnings/
  • Learning log files:
    • LEARNINGS.md (corrections, knowledge gaps, best practices)
    • ERRORS.md (command failures, exception output)
    • FEATURE_REQUESTS.md (new capabilities requested by users)

By default, log entries go first to the skill's own data directory. When you explicitly specify a project, write to the project-level log. When an issue has been abstracted into a cross-project rule, promote it to the skill's public area or the Minis memory system.

Current Final Rules

  • Default logging location: /var/minis/skills/self-improving-agent/data/
  • Public area within the skill: /var/minis/skills/self-improving-agent/data/public/
  • Project-level logging: Use <project>/.learnings/ only when --project <path> is passed explicitly
  • Recommended public parameter: --public
  • Compatibility alias: --workspace is still available, but only for compatibility and is no longer recommended
  • Promotion behavior: promote <entryID> copies the entry to the public area within the skill, automatically marks the source entry as promoted, and writes back **Promoted to** and ### Resolution Record
  • Duplicate protection: If the entry already exists in the skill's public area, running promote again will not append a duplicate

Quick Reference

ScenarioAction
Command or operation failsLog to the skill directory by default: data/ERRORS.md
The user corrects youLog to the skill directory by default: data/LEARNINGS.md, category correction
The user needs a missing capabilityLog to the skill directory by default: data/FEATURE_REQUESTS.md
Project context is explicitly specifiedLog to <project>/.learnings/
External API or tool failsLog to ERRORS.md in the current scope, including integration details
Knowledge is outdatedLog to LEARNINGS.md in the current scope, category knowledge_gap
A better solution is foundFirst log it to the current scope, then promote it after confirming it is generally applicable
Similar issues recur across multiple projectsPromote to the public area within the skill: data/public/
Similar to an existing entryLink with **See Also** and consider raising the priority
Widely applicable experiencePromote to the public area within the skill or to Minis memory. See "Promoting to Minis Memory" below

Trigger Logging Rules (Minis Runtime Conventions)

Note: By default, this skill does not automatically listen in the background. When trigger conditions are met, the assistant (or you) should actively call scripts/minis_auto_log.sh to write the log to disk.

If any of the following conditions are met, the event should be logged unless you explicitly say "do not log it":

  1. A command or operation fails and the cause is not obvious: For example, permissions, paths, dependencies, network issues, or third-party API exceptions that require investigation to diagnose.
  2. User correction: You point out where my understanding is wrong, where my logic does not match the actual behavior of this software, or where paths or conventions are incorrect.
  3. Knowledge update or outdated assumption correction: A previous assumption is found not to apply to Minis, or documentation or implementation needs correction.
  4. Reusable better solution: A stable practice, convention, template, or workflow emerges that can significantly reduce rework.
  5. Recurring pattern: Similar issues appear repeatedly within the same task, or across tasks or projects.
Situations That Generally Should Not Be Logged
  • Ordinary chat, one-off small changes, or minor details with no reuse value.
  • You explicitly ask "do not log this."
  • By default, write to the skill area data/ first.
  • After confirming that the entry has reuse value across tasks, use promote to move it to the public area within the skill: data/public/.

Difference from Minis Memory and Promotion Criteria

Difference (Suggested Interpretation)
  • This skill's logs (data/ and data/public/) are an editable work review repository: they record context, troubleshooting processes, and solution evolution, and they allow long text and details.
  • Minis memory (memory_write writing to /var/minis/memory/) is for cross-session long-term rules and preferences: entries should be short, stable, and reusable. Poorly written entries can "pollute" future decisions for a long time.
Where to Write (Log First, Then Refine into Memory)
  • Write to this skill's logs first: When the content needs context, such as error output, troubleshooting paths, or solution comparisons; when it is not yet clear whether it is generally applicable; or when it is still being iterated on.
  • Then promote to memory: When the conclusion is stable, applies across tasks or skills, and can be expressed in one sentence.
When to Promote to Memory (Hard Criteria)

Consider memory_write only if at least one of the following is true:

  1. It can be condensed into a rule of the form "When X happens in the future, do Y" and does not depend on specific project details.
  2. It recurs 3 or more times within 30 days, or appears in at least 2 different tasks or domains.
  3. It clearly belongs to your long-term preferences or conventions, such as tool usage constraints, path conventions, or output format rules, and you explicitly say "remember this" or "do this from now on."
Show full SKILL.md (517 more words)Show less
  • First use promote to promote the entry to the public area within the skill, data/public/, for higher visibility and easier review.
  • Then distill 1 to 3 short rules from the public entry and write them to the day's memory with memory_write.

Usage examples:

bash
# By default, write to the skill's own data directory
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh init

# Log a skill-level learning
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh learning "Fixed the download timeout" "Use chunking and retries"

# If you need to log explicitly at the project level, pass --project
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh --project /var/minis/workspace/my-project error "curl request failed" "HTTP 429"

# If you need to write directly to the public area within the skill, pass --public explicitly
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh --public feature "Support batch export" "Operations needs daily reports"

# Search the skill area + project area + public area within the skill
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh search timeout

# Promote an entry to the public area within the skill
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh promote LRN-20260317-ABC

# View the current scope
sh /var/minis/skills/self-improving-agent/scripts/minis_auto_log.sh status

Logging Format

Learning Record

Append to .learnings/LEARNINGS.md:

markdown
## [LRN-YYYYMMDD-XXX] category

**Record time**: ISO-8601 timestamp
**Priority**: low | medium | high | critical
**Status**: pending
**Domain**: frontend | backend | infra | tests | docs | config

### Summary
One-line description of what was learned

### Details
Full context: what happened, what went wrong, and the correct approach

### Recommended Action
Specific actionable improvement or fix

### Metadata
- Source: conversation | error | user_feedback
- Related file: path/to/file.ext
- Tags: tag1, tag2
- Related entry: LRN-20250110-001 (if applicable)
- Pattern key: simplify.dead_code | harden.input_validation (optional, for recurring pattern tracking)
- Recurrence count: 1 (optional)
- First seen: 2025-01-15 (optional)
- Last seen: 2025-01-15 (optional)

---
Error Record

Append to .learnings/ERRORS.md:

markdown
## [ERR-YYYYMMDD-XXX] skill_or_command_name

**Record time**: ISO-8601 timestamp
**Priority**: high
**Status**: pending
**Domain**: frontend | backend | infra | tests | docs | config

### Summary
Brief description of the failure

### Error
```
Actual error message or output
```

### Context
- Command or operation attempted
- Input or parameters
- Environment details, if relevant

### Recommended Fix
If identifiable, provide possible solutions

### Metadata
- Reproducible: yes | no | unknown
- Related file: path/to/file.ext
- Related entry: ERR-20250110-001 (if recurring)

---
Feature Request Record

Append to .learnings/FEATURE_REQUESTS.md:

markdown
## [FEAT-YYYYMMDD-XXX] capability_name

**Record time**: ISO-8601 timestamp
**Priority**: medium
**Status**: pending
**Domain**: frontend | backend | infra | tests | docs | config

### Requested Capability
The capability the user wants to implement

### User Context
Why it is needed and what problem it solves

### Complexity Assessment
simple | medium | complex

### Recommended Implementation
Possible implementation approaches and extension points

### Metadata
- Frequency: first_time | recurring
- Related feature: existing_feature_name

---

ID Generation Rules

Format: TYPE-YYYYMMDD-XXX

  • TYPE: LRN (learning), ERR (error), FEAT (feature)
  • YYYYMMDD: current date
  • XXX: sequential number or random 3-character value, such as 001 or A7B

Examples: LRN-20250115-001, ERR-20250115-A3F, FEAT-20250115-002

Resolving Entries

After an issue is fixed, update the entry:

  1. Change **Status**: pending to **Status**: resolved
  2. Add a resolution block after the metadata:
markdown
### Resolution Record
- **Resolution time**: 2025-01-16T09:00:00Z
- **Commit/PR**: abc123 or #42
- **Notes**: Brief description of what was done

Other statuses:

  • in_progress - Being worked on
  • wont_fix - Decided not to fix. Write the reason in the resolution record
  • promoted - Promoted to Minis memory

Promoting to Minis Memory

When a learning item is broadly applicable rather than a one-time fix, it should be promoted to the Minis memory system.

When to Promote
  • The learning applies across multiple files or features
  • Any contributor, human or AI, should know it
  • It prevents repeated mistakes
  • It records project conventions
Promotion Targets (Minis)
  • Daily memory: /var/minis/memory/YYYY-MM-DD.md (written through memory_write)
  • Global memory: /var/minis/memory/GLOBAL.md (read-only; the user must maintain it in settings)
  • Project notes: Recommended target: /var/minis/workspace/PROJECT_NOTES.md
How to Promote
  1. Distill: Condense the learning into concise rules or facts
  2. Write: Use memory_write to write to daily memory, and sync to project notes if needed
  3. Write back: Update the original entry:
    • **Status**: pending to **Status**: promoted
    • Add **Promoted**: YYYY-MM-DD.md or PROJECT_NOTES.md

Recurring Pattern Detection

If the content being logged is similar to an existing entry:

  1. Search first: grep -r "keyword" /var/minis/workspace/.learnings/
  2. Create an association: Add **See Also**: ERR-20250110-001 to the metadata
  3. Raise the priority: If the issue recurs
  4. Consider a systematic fix: Recurring issues usually indicate:
    • Missing documentation (write to PROJECT_NOTES.md or daily memory)
    • Missing automation (add scripts or toolchain support)
    • Architectural issues (create a technical debt task)

Simplify & Harden Feed

Used to ingest recurring patterns from the simplify-and-harden skill and convert them into persistent prompt rules.

Ingestion Workflow
  1. Read simplify_and_harden.learning_loop.candidates from the task summary.
  2. For each candidate, use pattern_key as the stable deduplication key.
  3. Search .learnings/LEARNINGS.md to see whether it already exists:
    • grep -n "Pattern-Key: <pattern_key>" /var/minis/workspace/.learnings/LEARNINGS.md
  4. If it already exists:
    • Increment Recurrence-Count
    • Update Last-Seen
    • Add a See Also association
  5. If it does not exist:
    • Create a new LRN-... entry
    • Set Source: simplify-and-harden
    • Set Pattern-Key, Recurrence-Count: 1, and First-Seen/Last-Seen
Promotion Rules (System Prompt Feedback)

When the following conditions are met, promote the recurring pattern to Minis memory:

  • Recurrence-Count >= 3
  • Appears in at least 2 different tasks
  • Occurs within 30 days

The promoted rule should be a short and clear preventive rule that describes what to do before or during work, not a lengthy incident review.

Periodic Review

Review .learnings/ at natural milestones:

When to Review
  • Before starting a new important task
  • After completing a feature
  • When entering a domain that has previous learnings
  • Once a week during active development
Quick Status Check
bash
# Count pending items
grep -h "Status\*\*: pending" /var/minis/workspace/.learnings/*.md | wc -l

# List pending high-priority items
grep -B5 "Priority\*\*: high" /var/minis/workspace/.learnings/*.md | grep "^## \["

# Find learnings for a specific area
grep -l "Domain\*\*: backend" /var/minis/workspace/.learnings/*.md

© OpenMinis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts) in self-improving-agent of OpenMinis/MinisSkills.

  • SKILL.md
  • data/ERRORS.md
  • data/FEATURE_REQUESTS.md
  • data/LEARNINGS.md
  • data/public/ERRORS.md
  • data/public/FEATURE_REQUESTS.md
  • data/public/LEARNINGS.md
  • scripts/minis_auto_log.sh

Open the folder on GitHubat commit ae8c5db

Compare with similar skills

Self Improving Agent 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 Improving Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Self Improving Agent this skillOpenMinis/MinisSkills444—~3.6kAutomated safety check: PassMIT
Feedbackcodewhale-hq/Codewhale41k—~272Automated safety check: PassMIT
Growth Logaffaan-m/ECC275k1 repos~1.7kAutomated safety check: PassMIT
Clickhouse Logs Queriessupabase/supabase111k—~2.4kAutomated safety check: PassApache-2.0
Investigating LogsPostHog/posthog40k—~2.1kAutomated safety check: PassCustom licence
Feedbacknexu-io/nexu3.3k—~660Automated safety check: WarnMIT

Similar skills

  • Feedback

    codewhale-hq/Codewhale

    Report a Codewhale bug or idea as a GitHub issue. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~272 tokensUpdated today
    Auto-check passed

  • Growth Log

    affaan-m/ECC

    Write growth log entries that extract reusable patterns from completed work — root cause, transferable rule, and a recognizable signal — instead of diary-style event narration, with a 4-8 sentence…

    275k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed

  • Clickhouse Logs Queries

    supabase/supabase

    Official

    Write, review, and migrate Supabase logs queries against the ClickHouse-backed logs table (the logs.all.otel analytics endpoint).

    111k GitHub stars~2.4k tokensUpdated today
    DatabasesAuto-check passed

  • Investigating Logs

    PostHog/posthog

    Official

    Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying.

    40k GitHub stars~2.1k tokensUpdated today
    DatabasesAuto-check passed

  • Feedback

    nexu-io/nexu

    Send feedback to the Nexu team. An agent skill from nexu-io/nexu.

    3.3k GitHub stars~660 tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check: warnings

  • Logging and Error Reporting for Warp

    warpdotdev/warp

    Guides log level choices and when to raise a structured Sentry event instead of a plain log line in the Warp Rust codebase, keeping secrets out of logs.

    65k GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed

More from OpenMinis/MinisSkills

All 49 skills in this repo

  • Android UI Automation

    OpenMinis/MinisSkills

    Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service.

    444 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Codex On Ish

    OpenMinis/MinisSkills

    Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken.

    444 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Evidence Chain Builder

    OpenMinis/MinisSkills

    Score a claim against the evidence behind it. An agent skill from OpenMinis/MinisSkills.

    444 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Hyperframes CLI

    OpenMinis/MinisSkills

    HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

    444 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

  • Whenpeak

    OpenMinis/MinisSkills

    Predict when a person's brain works best from their sleep, using the WhenPeak performance-intelligence API, and turn it into concrete scheduling advice.

    444 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Openstreetmap Marker

    OpenMinis/MinisSkills

    Generate a mobile-first, immersive, Amap(Gaode)-style custom landmark marker HTML map for travel itinerary planning, place showcasing, location sharing, etc.

    444 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Self Improving Agent

What does Self Improving Agent do?

Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable…. Self Improving Agent is an agent skill from OpenMinis/MinisSkills. Self-improvement logging and closed-loop feedback: Trigger when a command or operation fails, the user corrects you, outdated knowledge is identified, an external API fails, or a better reusable solution is found.

When should I use Self Improving Agent?

Self Improving Agent fits situations like: operation fails; the user corrects you; outdated knowledge is identified; an external API fails.

How do I install Self Improving Agent in Claude Code?

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

How do I install Self Improving Agent in Codex?

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

Can I use Self Improving Agent 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 OpenMinis/MinisSkills --skill self-improving-agent -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-improving-agent, .gemini/skills/self-improving-agent, .github/skills/self-improving-agent and .opencode/skills/self-improving-agent in your project.

What does Self Improving Agent need to run?

Going by SKILL.md and its folder, Self Improving Agent needs a shell for the scripts in its folder and the command-line tools its instructions call (sh). Our summary lists: A Bash shell.

Does Self Improving Agent access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Self Improving Agent 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 Improving Agent use?

Self Improving Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Self Improving Agent use?

About 3.6k tokens (SKILL.md is roughly 14k 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 Improving Agent?

Skills that share tags, products or a category with Self Improving Agent: Feedback (codewhale-hq/Codewhale, 41k stars), Growth Log (affaan-m/ECC, 275k stars), Clickhouse Logs Queries (supabase/supabase, 111k stars) and Investigating Logs (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Self Improving Agent?

OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 444 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.

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