SkillOpt-Sleep Self-Improvement Cycle
microsoft/SkillOpt
Runs a nightly or on-demand sleep cycle for a local Codex agent: review past sessions, replay recurring tasks and stage validated skill and memory edits for adoption.
Runs a self-improvement loop for loopany: reads recent task outcomes and dismissed signals, finds patterns, writes learnings and skill proposals, and applies accepted ones.
Install Loopany Reflect
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install superdesigndev/loopany loopany-reflect --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loopany-reflect .claude/skills/loopany-reflect && rm -rf skills-srcUse ~/.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/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .claude/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflectType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install superdesigndev/loopany loopany-reflect --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/loopany-reflect .agents/skills/loopany-reflect && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .agents/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install superdesigndev/loopany loopany-reflect --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/loopany-reflect .cursor/skills/loopany-reflect && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .cursor/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/superdesigndev/loopany.git --path skills/loopany-reflect--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install superdesigndev/loopany loopany-reflect --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/loopany-reflect .gemini/skills/loopany-reflect && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .gemini/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install superdesigndev/loopany loopany-reflectInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/loopany-reflect .github/skills/loopany-reflect && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .github/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add superdesigndev/loopany --skill loopany-reflect -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install superdesigndev/loopany loopany-reflect --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/superdesigndev/loopany.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/loopany-reflect .opencode/skills/loopany-reflect && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "loopany-reflect" agent skill from https://github.com/superdesigndev/loopany/tree/main/skills/loopany-reflect into .opencode/skills/loopany-reflect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopany-reflect", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
loopany-reflect- GitHub stars
- 140
- Token cost
- ~1.4k tokens
- SKILL.md length
- 496 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- None found
At a glance
Runs a self-improvement loop for loopany: reads recent task outcomes and dismissed signals, finds patterns, writes learnings and skill proposals, and applies accepted ones.
- Works in 5 steps: Gather evidence → Look for patterns → Write a learning → …
- Asking the agent what it has learned from recent tasks
- SKILL.md covers Part 1: Reflect, Part 2: Proposal Apply, Anti-patterns and Quick reference
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill has two modes. Reflect gathers evidence with loopany artifact commands, covering done tasks, signals and dismissed signals from roughly the past week, and subtracts anything already cited by active learnings or non-rejected proposals. It then looks for patterns using thresholds: three tasks with the same kind of outcome, two tasks that refute or add a caveat to a belief, or a signal dismissed at least three times over two weeks. One bad outcome is not a pattern, and rejected proposals are not suggested again.
A learning is written as a declarative belief with at least two evidence IDs and a check date one to three months out. A skill proposal is written only when a learning implies a concrete edit, with sections for motivation, proposed change, expected effect and check-at. Proposal-apply mode accepts or rejects pending proposals. It should run on request, weekly, or after several tasks finish, not after every task. The excerpt ends in the proposal step.
When your agent uses it
- Asking the agent what it has learned from recent tasks
- Turning repeated outcomes into a recorded learning with evidence
- Drafting a proposal to edit a skill based on observed patterns
- Reviewing and accepting or rejecting pending skill proposals
Example prompts
- “Reflect on this week's finished tasks and write up any learnings.”
- “What have we learned from the dismissed signals over the last two weeks?”
- “Review the pending skill proposals and walk me through accepting or rejecting each one.”
- “Write a skill proposal from the learning about tasks that had no baseline metrics.”
Requirements
- The loopany CLI and its artifact store
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Gather evidence
- Look for patterns
- Write a learning
- Write a skill-proposal (if warranted)
- Verify evidence chain
What it can do on your machine
Read from SKILL.md and the folder at commit cdd1d08. 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 (its code samples are bash).
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
Loopany Reflect loads about 1.4k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 496 words of instructions outside code blocks.
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 496 words (~1,426 tokens).
“Two modes: reflect (discover patterns → write learnings + proposals) and proposal-apply (accept or reject a pending proposal).”
- name
- loopany-reflect
Files
Just SKILL.md in skills/loopany-reflect of superdesigndev/loopany.
Open the folder on GitHubat commit cdd1d08
Compare with similar skills
Loopany Reflect 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Loopany Reflect this skillsuperdesigndev/loopany | 140 | — | ~1.4k | Automated safety check: Pass | None | |
| SkillOpt-Sleep Self-Improvement Cyclemicrosoft/SkillOpt | 18k | — | ~2.3k | Automated safety check: Pass | MIT | |
| SkillOpt-Sleep for Cursormicrosoft/SkillOpt | 18k | — | ~2.4k | Automated safety check: Pass | MIT | |
| SkillOpt Sleep Cyclemicrosoft/SkillOpt | 18k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Watchmen Setupfirstbatchxyz/watchmen | 297 | — | ~1.1k | Automated safety check: Notes | MIT | |
| Watchmen Setupfirstbatchxyz/watchmen | 297 | — | ~1.2k | Automated safety check: Notes | MIT |
Similar skills
- Official
- Official
SkillOpt-Sleep for Cursor
microsoft/SkillOpt
Mines recurring tasks from recent local Cursor sessions, replays them to test bounded skill edits, and stages validated improvements to a project Cursor skill for review.
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs a usage-driven self-improvement cycle for the dsh agent: harvest past sessions, mine recurring tasks, replay them and stage validated skill edits.
Watchmen Setup
firstbatchxyz/watchmen
Walks through installing watchmen, running its init wizard, wiring the plugin into Codex or Claude Code and checking the result with doctor.
Watchmen Setup
firstbatchxyz/watchmen
Sets up watchmen on the current machine: installs the CLI, hands off the init wizard, wires the plugin and statusline into Claude Code and Codex, and verifies with doctor.
OmniRoute Plugins, Skills and Memory CLI
diegosouzapw/OmniRoute
Command reference for the omniroute CLI's memory, plugin, marketplace and skills commands: search and manage stored memory, install and scaffold plugins, and find skill packages.
More from superdesigndev/loopany
loopany Periodic Review
superdesigndev/loopany
Runs a daily, weekly or monthly review of a loopany workspace, sorting items into silent fixes, things that need you and deferrals, and closing every surfaced item.
Loopany Artifact Lifecycle
superdesigndev/loopany
Routes artifact operations in a loopany workspace to the right playbook: tasks, signals, learnings, skill proposals, missions, people, notes, briefs and journals.
Loopany Capture
superdesigndev/loopany
Decides, once a task is finished, whether the outcome deserves a loopany record and routes it to the right artifact kind through a quality gate.
Related
Categories
Questions about Loopany Reflect
What does Loopany Reflect do?
Runs a self-improvement loop for loopany: reads recent task outcomes and dismissed signals, finds patterns, writes learnings and skill proposals, and applies accepted ones. This skill has two modes. Reflect gathers evidence with loopany artifact commands, covering done tasks, signals and dismissed signals from roughly the past week, and subtracts anything already cited by active learnings or non-rejected proposals.
When should I use Loopany Reflect?
Loopany Reflect fits situations like: asking the agent what it has learned from recent tasks; turning repeated outcomes into a recorded learning with evidence; drafting a proposal to edit a skill based on observed patterns; reviewing and accepting or rejecting pending skill proposals.
How do I install Loopany Reflect in Claude Code?
Run `npx skills add superdesigndev/loopany --skill loopany-reflect -a claude-code`. Or copy the skill folder (skills/loopany-reflect in superdesigndev/loopany) into .claude/skills/loopany-reflect in your project. Claude Code loads it when a task matches its description.
How do I install Loopany Reflect in Codex?
Run `npx skills add superdesigndev/loopany --skill loopany-reflect -a codex`. Or copy the skill folder (skills/loopany-reflect in superdesigndev/loopany) into .agents/skills/loopany-reflect in your project. Codex loads it when a task matches its description.
Can I use Loopany Reflect 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 superdesigndev/loopany --skill loopany-reflect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loopany-reflect, .gemini/skills/loopany-reflect, .github/skills/loopany-reflect and .opencode/skills/loopany-reflect in your project.
What does Loopany Reflect need to run?
SKILL.md names no scripts, command-line tools or credentials: Loopany Reflect is instructions for the agent only. Our summary lists: The loopany CLI and its artifact store.
Does Loopany Reflect 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 Loopany Reflect 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 Loopany Reflect use?
No licence was found for Loopany Reflect or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Loopany Reflect use?
About 1.4k tokens (SKILL.md is roughly 5.7k 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 Loopany Reflect?
Skills that share tags, products or a category with Loopany Reflect: SkillOpt-Sleep Self-Improvement Cycle (microsoft/SkillOpt, 18k stars), SkillOpt-Sleep for Cursor (microsoft/SkillOpt, 18k stars), SkillOpt Sleep Cycle (microsoft/SkillOpt, 18k stars) and Watchmen Setup (firstbatchxyz/watchmen, 297 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Loopany Reflect?
superdesigndev (a GitHub organization) maintains it in superdesigndev/loopany, which has 140 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on June 2, 2026.
Source: superdesigndev/loopany on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.