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

Scrub Reflection Self Improvement

by marin-community in marin-community/marin

Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.

Apache-2.0Auto-check passed

Install Scrub Reflection Self Improvement

skills CLI
$ npx skills add marin-community/marin --skill scrub-reflection-self-improvement -a claude-code

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

GitHub CLI
$ gh skill install marin-community/marin scrub-reflection-self-improvement --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/marin-community/marin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/scrub-reflection-self-improvement .claude/skills/scrub-reflection-self-improvement && 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
scrub-reflection-self-improvement
GitHub stars
3.9k
Token cost
~889 tokens
SKILL.md length
450 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.

  • Works in 5 steps: Review recent open issues and open PRs… → Explicitly check for already-open… → Review the latest commits on main for… → …
  • SKILL.md covers Focus, Candidate Signals, Triage Checklist and Decision Heuristics, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scrub Reflection Self Improvement is an agent skill from marin-community/marin. Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Open-source framework for the research and development of foundation models. The licence is Apache-2.0.

Example prompts

  • “/scrub-reflection-self-improvement”

Workflow steps

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

  1. Review recent open issues and open PRs for repeated friction clusters.
  2. Explicitly check for already-open scrub-generated issues/PRs touching the same area; prefer advancing or deferring to that existing…
  3. Review the latest commits on main for changes that imply follow-on docs/workflow updates.
  4. Search AGENTS.md, .agents/skills/, and docs for stale workflow guidance related to those clusters.
  5. De-duplicate against existing issues/PRs before creating new artifacts.

What it can do on your machine

Read from SKILL.md and the folder at commit 61bb85c. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Scrub Reflection Self Improvement loads about 889 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 450 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
~889

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from marin-community/marin at commit 61bb85c, republished under its Apache-2.0 licence (© marin-community). 450 words, ~889 tokens.

Download SKILL.mdSave it as .claude/skills/scrub-reflection-self-improvement/SKILL.md (or your agent's skills folder).
name
scrub-reflection-self-improvement
description
Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.
schedule_cron
0 10 2 * * *
schedule_tz
America/New_York

scrub-reflection-self-improvement

Use this skill on scheduled scrub turns to identify and land high-leverage improvements in marin-community/marin.

Focus

  • Look for improvements from recent issues, PR feedback, and recurring operational friction.
  • Prefer one concrete implementation per run when feasible.
  • If implementation is blocked, produce a concrete plan and capture follow-up work in GitHub.

Candidate Signals

  • Repeated confusion in docs, recipes, or contributor workflows.
  • Recurring failures or avoidable manual steps in experiments, scripts, and infra operations.
  • Capability gaps that reduce the value of agent-assisted contributions.

Triage Checklist

Run a lightweight, repeatable scan before choosing work:

  1. Review recent open issues and open PRs for repeated friction clusters.
  2. Explicitly check for already-open scrub-generated issues/PRs touching the same area; prefer advancing or deferring to that existing artifact instead of creating a parallel one.
  3. Review the latest commits on main for changes that imply follow-on docs/workflow updates.
  4. Search AGENTS.md, .agents/skills/, and docs for stale workflow guidance related to those clusters.
  5. De-duplicate against existing issues/PRs before creating new artifacts.

When possible, prefer improvements that remove recurring operator time (for example, turning ad-hoc scrub judgment into explicit repeatable guidance).

Decision Heuristics

  • Pick the highest-leverage change with the lowest coordination overhead.
  • Treat open scrub-generated issues/PRs as first-class prior art during triage; if one already covers the candidate improvement, avoid opening a second artifact unless the new scope is clearly distinct.
  • De-duplicate against existing issues/PRs before opening new work.
  • When an improvement changes recurring workflow guidance, codify it in durable repo instructions: AGENTS.md for cross-cutting agent behavior, or .agents/skills/ for repeatable task workflows.
  • If no justified improvement exists now, choose a no-op outcome.
  • Prefer direct implementation over opening new issues when the change is fully in-repo and low-risk.
Show full SKILL.md (168 more words)Show less

Output

  • Keep rationale explicit: observed gap, change made (or plan), and expected impact.
  • Prefer durable artifacts over transient notes: land guidance updates in AGENTS.md and/or recipe docs when that is the primary improvement.
  • Treat local-only edits as incomplete work. If you modify files, publish the result (commit/push and open or update a PR per .agents/skills/commit/SKILL.md) before finishing this scrub run.
  • If publish is blocked (auth, permissions, CI infra, etc.), report the blocker and set a future needs_followup_at instead of ending the run.
  • If you choose no-op, include explicit inspected signals and why no justified improvement exists now.
  • End the run with exactly one footer line of valid one-line JSON: HARNESS_SCRUB_LOOP {"needs_followup_at":null}. Set needs_followup_at to null when the run is complete, or a future RFC 3339 timestamp when another follow-up turn is needed.

For no-op outcomes, include at minimum:

  • which issue/PR/commit windows were inspected,
  • why each candidate was not suitable for this run,
  • and why deferring to the next scheduled run is preferable to opening a low-signal artifact now.

© marin-community, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/scrub-reflection-self-improvement of marin-community/marin.

Open the folder on GitHubat commit 61bb85c

Compare with similar skills

Scrub Reflection Self Improvement 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.

Scrub Reflection Self Improvement compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scrub Reflection Self Improvement this skillmarin-community/marin3.9k—~889Automated safety check: PassApache-2.0
Reflectalirezarezvani/claude-skills28k1 repos~2.4kAutomated safety check: PassMIT
ReflectNeoLabHQ/context-engineering-kit1.7k—~5.6kAutomated safety check: PassGPL-3.0
Reflection Coachpaperclipai/paperclip99k—~3kAutomated safety check: PassMIT
Skill Improversickn33/agentic-awesome-skills47k2 repos~1.5kAutomated safety check: PassMIT
Reflectagenticnotetaking/arscontexta3.5k—~7.2kAutomated safety check: NotesMIT

Similar skills

  • Reflect

    alirezarezvani/claude-skills

    Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias.

    28k GitHub starsUsed in 1 repo~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Reflect

    NeoLabHQ/context-engineering-kit

    Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

    1.7k GitHub stars~5.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Reflection Coach

    paperclipai/paperclip

    Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change.

    99k GitHub stars~3k tokensUpdated today
    Sales & SupportAuto-check passed

  • Skill Improver

    sickn33/agentic-awesome-skills

    Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.

    47k GitHub starsUsed in 2 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Reflect

    agenticnotetaking/arscontexta

    Find connections between notes and update MOCs. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub stars~7.2k tokensUpdated 7 mo ago
    Auto-check: notes

  • Improve Oas

    elastic/kibana

    Official

    Add or improve OpenAPI descriptions, examples, and code samples for a Kibana API area.

    21k GitHub stars~4.8k tokensUpdated today
    Backend & APIsAuto-check passed

More from marin-community/marin

All 41 skills in this repo

  • Noslop

    marin-community/marin

    Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Use Iris

    marin-community/marin

    Use Iris to submit, inspect, debug, monitor, or recover jobs and tasks; diagnose scheduling and federation; deploy controllers; or reserve dev GPUs and TPUs.

    3.9k GitHub stars~745 tokensUpdated today
    Auto-check passed

  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Auto-check passed

  • Marina Applet

    marin-community/marin

    Build, validate, publish, update, inspect, query, roll back, or archive a dynamic Marina applet.

    3.9k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Query Finelog

    marin-community/marin

    Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

    3.9k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Trace Pulumi Diff

    marin-community/marin

    Run a read-only preview for a specified Marin infra/pulumi stack and trace each pending resource change to merged pull requests since its latest successful update when that update records a clean…

    3.9k GitHub stars~663 tokensUpdated today
    Auto-check passed

Questions about Scrub Reflection Self Improvement

What does Scrub Reflection Self Improvement do?

Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub. Scrub Reflection Self Improvement is an agent skill from marin-community/marin. Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.

How do I install Scrub Reflection Self Improvement in Claude Code?

Run `npx skills add marin-community/marin --skill scrub-reflection-self-improvement -a claude-code`. Or copy the skill folder (.agents/skills/scrub-reflection-self-improvement in marin-community/marin) into .claude/skills/scrub-reflection-self-improvement in your project. Claude Code loads it when a task matches its description.

How do I install Scrub Reflection Self Improvement in Codex?

Run `npx skills add marin-community/marin --skill scrub-reflection-self-improvement -a codex`. Or copy the skill folder (.agents/skills/scrub-reflection-self-improvement in marin-community/marin) into .agents/skills/scrub-reflection-self-improvement in your project. Codex loads it when a task matches its description.

Can I use Scrub Reflection Self Improvement 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 marin-community/marin --skill scrub-reflection-self-improvement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scrub-reflection-self-improvement, .gemini/skills/scrub-reflection-self-improvement, .github/skills/scrub-reflection-self-improvement and .opencode/skills/scrub-reflection-self-improvement in your project.

What does Scrub Reflection Self Improvement need to run?

SKILL.md names no scripts, command-line tools or credentials: Scrub Reflection Self Improvement is instructions for the agent only.

Does Scrub Reflection Self Improvement 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 Scrub Reflection Self Improvement 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. Review the folder before installing.

What licence does Scrub Reflection Self Improvement use?

Scrub Reflection Self Improvement is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scrub Reflection Self Improvement use?

About 889 tokens (SKILL.md is roughly 3.6k 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 Scrub Reflection Self Improvement?

Skills that share tags, products or a category with Scrub Reflection Self Improvement: Reflect (alirezarezvani/claude-skills, 28k stars), Reflect (NeoLabHQ/context-engineering-kit, 1.7k stars), Reflection Coach (paperclipai/paperclip, 99k stars) and Skill Improver (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scrub Reflection Self Improvement?

marin-community (a GitHub organization) maintains it in marin-community/marin, which has 3,920 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 9, 2026.

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