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.
“Use when the user says /learn or asks to save this lesson.”
Install Learn From Session
$ npx skills add tigerless-labs/autoharness --skill learn -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tigerless-labs/autoharness learn --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/tigerless-labs/autoharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learn .claude/skills/learn && 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 "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .claude/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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/tigerless-labs/autoharness/tree/main/skills/learnType 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 tigerless-labs/autoharness --skill learn -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tigerless-labs/autoharness learn --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tigerless-labs/autoharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/learn .agents/skills/learn && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .agents/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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 tigerless-labs/autoharness --skill learn -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tigerless-labs/autoharness learn --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tigerless-labs/autoharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/learn .cursor/skills/learn && 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 "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .cursor/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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/tigerless-labs/autoharness.git --path skills/learn--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 tigerless-labs/autoharness --skill learn -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tigerless-labs/autoharness learn --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tigerless-labs/autoharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/learn .gemini/skills/learn && 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 "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .gemini/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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 tigerless-labs/autoharness learnInstalls 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 tigerless-labs/autoharness --skill learn -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tigerless-labs/autoharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/learn .github/skills/learn && 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 "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .github/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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 tigerless-labs/autoharness --skill learn -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tigerless-labs/autoharness learn --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tigerless-labs/autoharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/learn .opencode/skills/learn && 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 "learn" agent skill from https://github.com/tigerless-labs/autoharness/tree/main/skills/learn into .opencode/skills/learn/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn", 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
learn- GitHub stars
- 9.2k
- Token cost
- ~280 tokens
- SKILL.md length
- 144 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
- Works in 4 steps: Identify class-level, reusable lessons:… → Compare first: read the injected skill… → Reconcile old with new: when a lesson… → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Learn From Session is a skill in tigerless-labs/autoharness (9.2k stars). Its SKILL.md is about 280 tokens. Licence: MIT.
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Identify class-level, reusable lessons: corrected approaches, non-trivial
- Compare first: read the injected skill index; if an existing skill covers
- Reconcile old with new: when a lesson supersedes an earlier rule, search
- Stage every change exclusively via the stage_skill tool, one intent per
What it can do on your machine
Read from SKILL.md and the folder at commit 4b90a3a. 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
Learn From Session loads about 280 tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 144 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
The full file from tigerless-labs/autoharness at commit 4b90a3a, republished under its MIT licence (© tigerless-labs). 144 words, ~280 tokens.
Download SKILL.mdSave it as
.claude/skills/learn/SKILL.md (or your agent's skills folder).- name
- learn
- description
- Use when the user says /learn or asks to save this lesson.
- category
- general
Learn: distill this session into the skill library
Review the conversation so far and distill what is worth keeping — through the standard proposal chain, never by writing files.
- Identify class-level, reusable lessons: corrected approaches, non-trivial techniques, durable user preferences. Skip one-off narratives and environment-specific failures.
- Compare first: read the injected skill index; if an existing skill covers
the topic, prefer a
patch/updateover creating a near-duplicate. - Reconcile old with new: when a lesson supersedes an earlier rule, search the managed skill trees for contradicting statements and stage updates so the new version wins everywhere.
- Stage every change exclusively via the
stage_skilltool, one intent per lesson, withreasonand a verbatimevidencequote from this session. The deterministic promoter validates and lands; rejects are reported at the next session start.
If nothing meets the bar, say so and stage nothing.
© tigerless-labs, MIT. 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 skills/learn of tigerless-labs/autoharness.
Open the folder on GitHubat commit 4b90a3a
Compare with similar skills
Learn From Session 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 |
|---|---|---|---|---|---|---|
| Learn From Session this skilltigerless-labs/autoharness | 9.2k | — | ~280 | Automated safety check: Pass | MIT | |
| 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 | 296 | — | ~1.1k | Automated safety check: Notes | MIT | |
| Watchmen Setupfirstbatchxyz/watchmen | 296 | — | ~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.
Loopany Reflect
superdesigndev/loopany
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.
Related
Categories
Questions about Learn From Session
How do I install Learn From Session in Claude Code?
Run `npx skills add tigerless-labs/autoharness --skill learn -a claude-code`. Or copy the skill folder (skills/learn in tigerless-labs/autoharness) into .claude/skills/learn in your project. Claude Code loads it when a task matches its description.
How do I install Learn From Session in Codex?
Run `npx skills add tigerless-labs/autoharness --skill learn -a codex`. Or copy the skill folder (skills/learn in tigerless-labs/autoharness) into .agents/skills/learn in your project. Codex loads it when a task matches its description.
Can I use Learn From Session 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 tigerless-labs/autoharness --skill learn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn, .gemini/skills/learn, .github/skills/learn and .opencode/skills/learn in your project.
What does Learn From Session need to run?
SKILL.md names no scripts, command-line tools or credentials: Learn From Session is instructions for the agent only.
Does Learn From Session 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 Learn From Session 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 Learn From Session use?
Learn From Session 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 Learn From Session use?
About 280 tokens (SKILL.md is roughly 1.1k 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 Learn From Session?
Skills that share tags, products or a category with Learn From Session: 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, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Learn From Session?
tigerless-labs (a GitHub organization) maintains it in tigerless-labs/autoharness, which has 9,192 GitHub stars. The repository was last updated on October 7, 2026.
Source: tigerless-labs/autoharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.