SkillOpt is a tool for improving reusable natural-language skills used by fixed-weight language-model agents through training runs, trajectory-based edits, validation checks, and generated best_skill.md files. It is intended for developing, evaluating, and deploying agent skills without changing the underlying model weights. Catalogue add-ons support SkillOpt workflows and integrations with coding agents.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/SkillOpt --skill openclawgit clone --depth 1 https://github.com/microsoft/SkillOptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/skillopt/openclaw)<a href="https://agentmods.dev/skills/microsoft/skillopt/openclaw"><img src="https://agentmods.dev/badge/skills/microsoft/skillopt/openclaw/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/skillopt/openclaw"><img src="https://agentmods.dev/badge/skills/microsoft/skillopt/openclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01090 |
| Opus 5.5 | $0.00015 | $0.00436 |
| Sonnet 5.5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
skillopt-sleep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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, which is the authoritative status and adaptation guide.
What is included
skillopt_sleep_openclaw.py— a contributed DeepSeek backend prototype. It also contains an Ollama embedding helper, but that helper is not wired into the current shared sleep cycle.run_sleep.py— a custom cycle wrapper with environment-specific paths and a backend-registration shim.slash_sleep.py— an experimental command helper written for an older staging-manifest shape.run_sleep_cron.sh— a machine-specific category runner, not a portable cron installer.config.json— a sample configuration, not a set of guaranteed or enforced runtime limits.tests/*.json— example task fixtures from one environment, not a universal OpenClaw benchmark.
Known porting gaps
Before treating this as an integration, a maintainer must at least:
- Replace every absolute workspace, repository, state, skill, log, and task path with explicit user configuration.
- Update the custom backend factory to the current
get_backendcall contract, including the project directory, and update its backend methods and edit records to the current protocol. - Replace the experimental adoption logic with the current staging manifest
and
skillopt_sleep.staging.adoptbehavior. Current staging artifacts useproposed_SKILL.md/proposed_CLAUDE.md,manifest.json, and report files; they do not expose the oldmanifest.proposed_skillfield. - Decide how real OpenClaw transcripts are converted into a supported session
format. Pointing
claude_homeat an arbitrary agent directory does not by itself make its files Claude Code-compatible JSONL. - Build scheduling around the adapted wrapper. The shared scheduler launches the shared CLI; it does not automatically preserve this custom backend or its category task-file flow.
- Add isolated end-to-end tests for dry-run, accepted/rejected gates, staging, adoption and backup, credential failure, and scheduled execution.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 104 lines · 37 tokens per session scan A d1d9dcd81214
skillopt-sleep is a skill published in the GitHub repository microsoft/SkillOpt (18,486 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 1,090 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
evo-adaptive-cruise-control
Complete Adaptive Cruise Control simulation system with PID controllers, single-loop ACC architecture (cruise/follow/emergency modes), TTC safety, Euler integration simulation, and full I/O pipeline.
evo-pptx-embedded-excel-updater
Provides utilities for finding and manipulating embedded Excel OLE objects within PPTX files, reading text boxes for context, modifying Excel cell values while preserving formulas, and saving the updated PPTX. Use when you need to extract embedded Excel spreadsheets from PowerPoint presentations, update exchange rates…
evo-protein-expression-analysis
Use when populating Excel workbooks for quantitative proteomics tasks - computing expression lookups, group statistics, and log2 fold-change values using Python and writing numeric results via openpyxl while preserving cell formatting. Handles two-sheet workbooks (Task + Data) with 2D protein×sample expression…
evo-suricata-custom-exfil
Generates and validates Suricata 7.0 rules for detecting data exfiltration hidden in HTTP telemetry traffic, using sticky buffers, exact URI matching, header inspection, and PCRE body pattern matching.
evo-video-filler-word-remover
Detects filler words in video/audio interviews using ASR (faster-whisper) with word-level timestamps, saves annotations as JSON, and extracts filler clips into a compilation video.