#97 by GitHub stars
microsoft/SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/claude-code/skills/skillopt-sleep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
e2edfa9721ce → 01e41dbcdf9e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → e2edfa9721ce
No earlier version was observed for comparison.
plugins/codex/skills/skillopt-sleep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
e2edfa9721ce → 01e41dbcdf9e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e2edfa9721ce
No earlier version was observed for comparison.
plugins/cursor/skills/skillopt-sleep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
e2edfa9721ce → 01e41dbcdf9e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e2edfa9721ce
No earlier version was observed for comparison.
plugins/dsh/skills/skillopt-sleep/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
e2edfa9721ce → 01e41dbcdf9e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → e2edfa9721ce
No earlier version was observed for comparison.
plugins/openclaw/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
e2edfa9721ce → 01e41dbcdf9e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e2edfa9721ce
No earlier version was observed for comparison.
Verified commit 01e41dbcdf9ea6e20d6428c152c14178bd1c80f3
git clone --filter=blob:none --no-checkout https://github.com/microsoft/SkillOpt.git .hotskills/microsoft-skillopt && git -C .hotskills/microsoft-skillopt checkout --detach 01e41dbcdf9ea6e20d6428c152c14178bd1c80f3
# Copy each selected skill directory from .hotskills/microsoft-skillopt into .claude/skills/<skill-name>/Heat
6.9- Star growth, last 7 daysAhead of 80% of tracked repositories
- Star growth, last 24 hoursAhead of 70% of tracked repositories
- Rank movement, last 7 daysAhead of 81% of tracked repositories
- Commits, last 30 daysAhead of 86% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- skillopt-sleep
plugins/claude-code/skills/skillopt-sleep - skillopt-sleep
plugins/codex/skills/skillopt-sleep - skillopt-sleep
plugins/cursor/skills/skillopt-sleep - skillopt-sleep
plugins/dsh/skills/skillopt-sleep - skillopt-sleep
plugins/openclaw
How it works
skillopt-sleep
When your agent uses it
Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated CLAUDE.md/SKILL.md behind a held-out gate.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
2,209 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- The cycle (six stages)
- How to drive it
- Common CLI flags
- Config keys (`~/.skillopt-sleep/config.json`)
- Memory consolidation
- Hard rules
- Validate / demo
Scripts executed separately
../../scripts/sleep.sh../../scripts/sleep.sh../../scripts/sleep.sh../../../run-sleep.sh
Files
../../.claude-plugin/marketplace.jsonasset1,157 bytes../../.claude-plugin/plugin.jsonasset877 bytes../../hooks/hooks.jsonasset273 bytes../../scripts/sleep.shruns1,369 bytes../../scripts/sleep.shruns1,369 bytes../../scripts/sleep.shruns1,369 bytesSKILL.mdcore9,054 bytesSKILL.mdcore9,054 bytesSKILL.mdcore9,054 bytes../../../run-sleep.shruns3,602 bytes
Read SKILL.md
# SkillOpt-Sleep: usage-driven self-evolution for a local Claude agent
SkillOpt-Sleep gives the user's agent a **sleep cycle**. On demand or on a
nightly schedule, it reviews real past Claude Code sessions, re-runs recurring
tasks through the selected backend, and consolidates what it
learns into **memory** (`CLAUDE.md`) and **skills** (`SKILL.md`). With the
default validation gate enabled, it keeps only changes that improve a held-out
score. Live files change only through explicit adoption or a user-requested
`--auto-adopt`. It aims to improve this user's recurring work, while making
each accepted proposal measurable on the run's held-out tasks,
with no model-weight training. It is the deployment-time analogue of training:
short-term experience → long-term competence.
It synthesizes three ideas:View the complete source on GitHubskillopt-sleep
When your agent uses it
Use when the user wants Codex to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, wants Codex to review past sessions, learn preferences, consolidate memory/skills, run dry-run/run/adopt/status for SkillOpt-Sleep, or schedule background self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay through a selected backend -> consolidate validated memory + skills behind a held-out gate.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
2,359 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- The cycle
- How to drive it
- Steps
- Hard rules
- Validate
Files
SKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytesSKILL.mdcore9,402 bytes
Read SKILL.md
# SkillOpt-Sleep: usage-driven self-evolution for a local Codex agent
SkillOpt-Sleep gives the user's Codex agent a sleep cycle. On demand or on a
nightly schedule, it reviews past local sessions, re-runs recurring tasks
through the selected backend, and proposes changes to a configured skill and to
the project's `CLAUDE.md`. With the default validation gate enabled, it keeps
only changes that improve a held-out score. Live files change only through
explicit adoption or a user-requested `--auto-adopt`. There is no model-weight
training.
The current shared engine does **not** write `AGENTS.md`. For a Codex-visible
result, always select a Codex skill explicitly with `--target-skill-path` (for
example `.agents/skills/<name>/SKILL.md`). If project `CLAUDE.md` is not a
desired secondary target, set `"evolve_memory": false` inView the complete source on GitHubskillopt-sleep
When your agent uses it
Use when the user wants Cursor to learn from recent local sessions, asks for an offline sleep or dream cycle, wants to consolidate recurring work into a Cursor skill, or requests SkillOpt-Sleep status, harvest, dry-run, run, scheduling, review, or adoption. Drives the validation-gated skillopt_sleep engine with Cursor transcripts and the optional Cursor Agent CLI backend.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
2,256 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Cursor target
- Choose the runner
- Core workflow
- Commands
- Reviewable data path
- Scheduling
- Report results
- Hard rules
Files
SKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytesSKILL.mdcore9,709 bytes
Read SKILL.md
# SkillOpt-Sleep for Cursor
SkillOpt-Sleep reviews recent local Cursor sessions, mines recurring tasks,
replays those tasks, and proposes bounded improvements to a project Cursor
skill. With the default gate enabled, a proposal is accepted only when it
improves the held-out score. A normal run stages the proposal for review;
nothing live changes until explicit adoption. There is no model-weight training.
This plugin has no session-end hook and no MCP server. Run the cycle only when
the user asks, or install a schedule only when the user explicitly requests one.
## Cursor target
Always use this project-relative target for Cursor-visible learning:View the complete source on GitHubskillopt-sleep
When your agent uses it
Use when the user wants the dsh agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, skill/memory consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule background self-optimization. Drives the skillopt_sleep engine through the skillopt_* tools: harvest past sessions -> mine recurring tasks -> replay via a selected backend -> consolidate validated skills behind a held-out gate.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
1,448 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- The cycle (six stages)
- Driving it
- Parameters
- Configuration (cordis.yml / bundle patch)
- Hard rules
- Validate / demo (no API spend)
Files
SKILL.mdcore5,775 bytesSKILL.mdcore5,775 bytes
Read SKILL.md
# SkillOpt-Sleep: usage-driven self-evolution for the dsh agent
SkillOpt-Sleep is Microsoft's [SkillOpt](https://github.com/microsoft/SkillOpt)
deployment-time companion engine: it reviews your past sessions (harvest), mines
recurring tasks (mine), replays them through a selected backend (replay), and
consolidates what it learns into skill documents behind a **held-out validation
gate** (consolidate).
This skill drives the engine through the 7 `skillopt_*` tools exposed by the
dsh-skillopt plugin. The default `mock` backend makes no model calls, which is
useful for verifying the plumbing; a real backend consumes your API budget.
## When to use
View the complete source on GitHubskillopt-sleep
When your agent uses it
Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,090 tokensWhen the skill is activated
Reference documents
12,815 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What is included
- Known porting gaps
- Shared-engine features are not wrapper features
- Data and credential boundary
- Further information
Scripts executed separately
run_sleep.pyrun_sleep_cron.shskillopt_sleep_openclaw.pyslash_sleep.py
Files
../../docs/sleep/README.mddoc33,264 bytes../README.mddoc17,122 bytesREADME.mddoc5,109 bytesSKILL.mdcore5,133 bytesSKILL.mdcore5,133 bytesSKILL.mdcore5,133 bytesconfig.jsonasset763 bytesrun_sleep.pyruns5,178 bytesrun_sleep_cron.shruns2,205 bytesskillopt_sleep_openclaw.pyruns10,208 bytesslash_sleep.pyruns12,006 bytestests/devops-tasks.jsonasset5,248 bytestests/research-cron-tasks.jsonasset7,014 bytestests/wiki-tasks.jsonasset5,155 bytes
Read SKILL.md
# SkillOpt-Sleep OpenClaw reference adaptation
This directory is a contributed **reference**, not a supported, plug-and-play
OpenClaw integration. It illustrates one way to connect the shared
`skillopt_sleep` cycle to a custom DeepSeek Chat Completions backend and a set of
environment-specific task fixtures.
Do not run or schedule the files unchanged. Several scripts and the sample
configuration preserve assumptions from the contributor's original machine,
and parts of the wrapper have not yet been ported to the current shared-engine
interfaces. Start with the directory's [README.md](README.md), which is the
authoritative status and adaptation guide.
## What is includedView the complete source on GitHubSkills included
- skillopt-sleep
- skillopt-sleep
- skillopt-sleep
- skillopt-sleep
- skillopt-sleep
Repository facts
- License
- MIT
- Created
- May 8, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 1,800
- Open issues
- 32
- Project activity
- Active
Rank over the last 12 weeks
Now #97 · best #91 · down 2 in 30 days
- #98 on Oct 25
- #97 from Oct 28 to Oct 29
- #98 from Oct 30 to Nov 1
- #97 on Nov 2
- #98 on Nov 3
- #97 since Nov 4
32 earlier periods
- #88 on Aug 2
- #91 from Aug 7 to Aug 8
- #90 on Aug 9
- #91 from Aug 10 to Aug 13
- #92 from Aug 14 to Aug 15
- #91 on Aug 16
- #92 from Aug 17 to Aug 21
- #91 on Aug 22
- #92 from Aug 23 to Aug 24
- #93 on Aug 25
- #94 from Aug 26 to Aug 29
- #93 on Aug 30
- #94 on Aug 31
- #95 on Sep 1
- #94 on Sep 2
- #95 on Sep 3
- #94 on Sep 4
- #96 on Sep 5
- #95 on Sep 6
- #96 from Sep 7 to Sep 9
- #97 from Sep 10 to Sep 14
- #96 from Sep 15 to Sep 18
- #97 on Sep 19
- #98 from Sep 20 to Sep 25
- #97 from Sep 26 to Sep 27
- #95 from Sep 28 to Oct 2
- #96 from Oct 3 to Oct 5
- #95 from Oct 6 to Oct 14
- #94 from Oct 15 to Oct 17
- #95 from Oct 18 to Oct 20
- #96 on Oct 21
- #97 from Oct 22 to Oct 24
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 36 notes
plugins/claude-code/scripts/sleep.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/claude-code/scripts/sleep.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/claude-code/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/claude-code/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/skillopt-sleep/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 55 network referencesin 9 files: docs/sleep/README.md:10 openclaw/skillopt_sleep_openclaw.py:24 plugins/claude-code/.claude-plugin/marketplace.json:1 and 6 more
- No hidden or obfuscated text
- No instruction overrides
- 8 executable scriptsin 6 files: plugins/claude-code/scripts/sleep.sh:1 openclaw/run_sleep.py:1 openclaw/run_sleep_cron.sh:1 and 3 more
- 10 references to secretsin 2 files: openclaw/skillopt_sleep_openclaw.py:28 openclaw/run_sleep_cron.sh:43
- No requests to vote in Hot
Show all 73 signals by file
docs/sleep/README.md
- Network accessline 10
> **Preview.** This is an early preview we are actively iterating on; interfaces and > defaults may change. The engine lives in the top-level [`skillopt_sleep/`](https://github.com/microsoft/SkillOpt/tree/main/skillopt_sleep) - Network accessline 11
> defaults may change. The engine lives in the top-level [`skillopt_sleep/`](https://github.com/microsoft/SkillOpt/tree/main/skillopt_sleep) - Network accessline 171
One engine, thin per-agent shells (see [`plugins/`](https://github.com/microsoft/SkillOpt/tree/main/plugins)): - Network accessline 173
| Platform | Folder | Install | |---|---|---| | **Claude Code** | [`plugins/claude-code`](https://github.com/microsoft/SkillOpt/tree/main/plugins/claude-code) | `/plugin marketplace add ./plugins/claude-code` → `/skillopt-sleep` | - Network accessline 174
|---|---|---| | **Claude Code** | [`plugins/claude-code`](https://github.com/microsoft/SkillOpt/tree/main/plugins/claude-code) | `/plugin marketplace add ./plugins/claude-code` → `/skillopt-sleep` | | **Codex** | [`plugins/codex`](https://g - Network accessline 175
| **Claude Code** | [`plugins/claude-code`](https://github.com/microsoft/SkillOpt/tree/main/plugins/claude-code) | `/plugin marketplace add ./plugins/claude-code` → `/skillopt-sleep` | - Network accessline 176
| **Codex** | [`plugins/codex`](https://github.com/microsoft/SkillOpt/tree/main/plugins/codex) | `bash plugins/codex/install.sh` → `skillopt-sleep` skill | - Network accessline 177
| **Cursor** | [`plugins/cursor`](https://github.com/microsoft/SkillOpt/tree/main/plugins/cursor) | `bash plugins/cursor/install.sh` → `/skillopt-sleep` | - Network accessline 178
| **Copilot** | [`plugins/copilot`](https://github.com/microsoft/SkillOpt/tree/main/plugins/copilot) | register `plugins/copilot/mcp_server.py` as an MCP server | - Network accessline 179
| **Devin** | [`plugins/devin`](https://github.com/microsoft/SkillOpt/tree/main/plugins/devin) | register `plugins/devin/mcp_server.py` as an MCP server | - Network accessline 180
| **OpenClaw** | [`plugins/openclaw`](https://github.com/microsoft/SkillOpt/tree/main/plugins/openclaw) | adapt the reference wrapper and paths for your installation | - Network accessline 323
For model calls, install and configure OpenCode using its [official documentation](https://opencode.ai/docs/), then confirm the CLI is - Network accessline 324
[official documentation](https://opencode.ai/docs/), then confirm the CLI is - Network accessline 556
**(a) End-to-end on real agents — [gbrain-evals](https://github.com/garrytan/gbrain-evals) `skillopt-v1`.** - Network accessline 592
See the [SkillOpt documentation index](../index.md), the [CLI reference](../reference/cli.md), and the integration-specific READMEs under [`plugins/`](https://github.com/microsoft/SkillOpt/tree/main/plugins). - Network accessline 594
[`plugins/`](https://github.com/microsoft/SkillOpt/tree/main/plugins).
plugins/claude-code/.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 17
"source": { "source": "git-subdir", "url": "https://github.com/microsoft/SkillOpt.git", - Network accessline 18
"source": "git-subdir", "url": "https://github.com/microsoft/SkillOpt.git", "path": "plugins/claude-code", - Network accessline 19
"url": "https://github.com/microsoft/SkillOpt.git", - Network accessline 21
"ref": "main" }, "homepage": "https://github.com/microsoft/SkillOpt" - Network accessline 22
}, "homepage": "https://github.com/microsoft/SkillOpt" } - Network accessline 23
"homepage": "https://github.com/microsoft/SkillOpt"
plugins/claude-code/.claude-plugin/plugin.json
- Network accessline 7
"email": "yifanyang@microsoft.com" }, "homepage": "https://github.com/microsoft/SkillOpt", - Network accessline 8
}, "homepage": "https://github.com/microsoft/SkillOpt", "repository": "https://github.com/microsoft/SkillOpt", - Network accessline 9
"homepage": "https://github.com/microsoft/SkillOpt", - Network accessline 10
"repository": "https://github.com/microsoft/SkillOpt",
plugins/claude-code/scripts/sleep.sh
plugins/claude-code/skills/skillopt-sleep/SKILL.md
- Network accessline 155
See the [SkillOpt-Sleep documentation](https://github.com/microsoft/SkillOpt/tree/main/docs/sleep)
plugins/codex/skills/skillopt-sleep/SKILL.md
- Network accessline 187
benchmark evidence for that configuration, not a guarantee for other skills, tasks, or models; see the [recorded results](https://github.com/microsoft/SkillOpt/blob/main/docs/sleep/RESULTS.md) - Network accessline 188
tasks, or models; see the [recorded results](https://github.com/microsoft/SkillOpt/blob/main/docs/sleep/RESULTS.md) for context and limitations. - Network accessline 189
[recorded results](https://github.com/microsoft/SkillOpt/blob/main/docs/sleep/RESULTS.md)
plugins/dsh/skills/skillopt-sleep/SKILL.md
plugins/openclaw/README.md
- Network accessline 3
This directory is a contributed reference for connecting [SkillOpt-Sleep](https://github.com/microsoft/SkillOpt) to - Network accessline 4
[SkillOpt-Sleep](https://github.com/microsoft/SkillOpt) to - Network accessline 5
[OpenClaw](https://github.com/openclaw/openclaw) with a custom DeepSeek/Ollama - Network accessline 49
git clone https://github.com/microsoft/SkillOpt.git
plugins/openclaw/run_sleep.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/openclaw/run_sleep_cron.sh
plugins/openclaw/skillopt_sleep_openclaw.py
- Executable scriptline 1
Executable file - Network accessline 24
"""Call DeepSeek V4 Pro via curl + jq. No extra Python deps needed.""" - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 31
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 39
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Network accessline 46
"stream": False, } req = urllib.request.Request( - Network accessline 47
} req = urllib.request.Request( f"{base}/chat/completions", - Network accessline 48
req = urllib.request.Request( - Access to secretsline 53
[Credential-related source omitted] - Network accessline 55
) try: with urllib.request.urlopen(req, timeout=180) as resp: - Network accessline 56
try: with urllib.request.urlopen(req, timeout=180) as resp: data = _json.loads(resp.read().decode("utf-8")) - Network accessline 57
with urllib.request.urlopen(req, timeout=180) as resp: - Network accessline 69
try: req = urllib.request.Request( - Network accessline 70
req = urllib.request.Request( - Network accessline 71
"http://127.0.0.1:11434/api/embeddings", - Network accessline 73
headers={"Content-Type": "application/json"}, ) with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 74
) with urllib.request.urlopen(req, timeout=30) as resp: data = _json.loads(resp.read().decode("utf-8")) - Network accessline 75
with urllib.request.urlopen(req, timeout=30) as resp:
plugins/openclaw/slash_sleep.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/openclaw/tests/devops-tasks.json
- Network accessline 5
"rubric": "Score 1.0 if output matches the exact format [STATUS] devops-agent | Site Uptime \u2192 geoxylia.com OK (200) | DD/MM HH:MM MYT, with a real current time. Score 0.5 if format is close but missing one field. Score 0.0 if wrong for - Network accessline 6
"project": "devops-infrastructure-check", "intent": "Site Uptime check. Run: `curl -o /dev/null -s -w '%{http_code}' https://geoxylia.com`. Interpret the result 200, and report in our standard format: 'STATUS | TASK \u2192 RESULT | TIME - Network accessline 7
"intent": "Site Uptime check. Run: `curl -o /dev/null -s -w '%{http_code}' https://geoxylia.com`. Interpret the result 200, and report in our standard format: 'STATUS | TASK \u2192 RESULT | TIME'. If not 200, escalate.",
plugins/run-sleep.sh
- Executable scriptline 1
#!/usr/bin/env bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 1 fact
- Contacts api.deepseek.com, which SKILL.md, the README and the plugin manifest do not mentionopenclaw/skillopt_sleep_openclaw.py:39High confidence
Signal confidence: 58 facts
- Network access in prose of documentationdocs/sleep/README.md:10Low confidence
- Network access in prose of documentationdocs/sleep/README.md:11Low confidence
- Network access in prose of documentationdocs/sleep/README.md:171Low confidence
- Network access in prose of documentationdocs/sleep/README.md:173Low confidence
- Network access in prose of documentationdocs/sleep/README.md:174Low confidence
- Network access in prose of documentationdocs/sleep/README.md:175Low confidence
- Network access in prose of documentationdocs/sleep/README.md:176Low confidence
- Network access in prose of documentationdocs/sleep/README.md:177Low confidence
- Network access in prose of documentationdocs/sleep/README.md:178Low confidence
- Network access in prose of documentationdocs/sleep/README.md:179Low confidence
- Network access in prose of documentationdocs/sleep/README.md:180Low confidence
- Network access in prose of documentationdocs/sleep/README.md:323Low confidence
- Network access in prose of documentationdocs/sleep/README.md:324Low confidence
- Network access in prose of documentationdocs/sleep/README.md:556Low confidence
- Network access in prose of documentationdocs/sleep/README.md:592Low confidence
- Network access in prose of documentationdocs/sleep/README.md:594Low confidence
- Executable script in code of a file that runsplugins/claude-code/scripts/sleep.sh:1High confidence
- Executable script in code of a file that runsplugins/claude-code/scripts/sleep.sh:1High confidence
- Executable script in code of a file that runsplugins/claude-code/scripts/sleep.sh:1High confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:155Low confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:187Low confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:188Low confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:189Low confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:8Low confidence
- Network access in prose of the SKILL.mdskillopt-sleep/SKILL.md:120Low confidence
- Network access in prose of documentationopenclaw/README.md:3Low confidence
- Network access in prose of documentationopenclaw/README.md:4Low confidence
- Network access in prose of documentationopenclaw/README.md:5Low confidence
- Network access in code of documentationopenclaw/README.md:49Low confidence
- Executable script in code of a file that runsopenclaw/run_sleep.py:1High confidence
- Executable script in code of a file that runsopenclaw/run_sleep_cron.sh:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/run_sleep_cron.sh:43Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/run_sleep_cron.sh:44Low confidence
- Executable script in prose of a file that runsopenclaw/skillopt_sleep_openclaw.py:1Low confidence
- Network access in prose of a file that runsopenclaw/skillopt_sleep_openclaw.py:24Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/skillopt_sleep_openclaw.py:28Low confidence
- Access to secrets in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:29High confidence
- Access to secrets in a comment of a file that runsopenclaw/skillopt_sleep_openclaw.py:30Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/skillopt_sleep_openclaw.py:31Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/skillopt_sleep_openclaw.py:35Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/skillopt_sleep_openclaw.py:36Low confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:39High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueopenclaw/skillopt_sleep_openclaw.py:39Low confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:46High confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:47High confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:48High confidence
- Access to secrets in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:53High confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:55High confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:56High confidence
- Network access in code of a file that runsopenclaw/skillopt_sleep_openclaw.py:57High confidence
and 8 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest plugins/claude-code/.claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/claude-code/skills/skillopt-sleep/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/claude-code/skills/skillopt-sleep/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/claude-code/skills/skillopt-sleep/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/claude-code/skills/skillopt-sleep/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/claude-code/skills/skillopt-sleep/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/microsoft-skillopt/)