LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow.
Install Skill Lifecycle
$ npx skills add ceilf6/FrontAgent --skill skill-lifecycle -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ceilf6/FrontAgent skill-lifecycle --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/ceilf6/FrontAgent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-lifecycle .claude/skills/skill-lifecycle && 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 "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .claude/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycleType 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 ceilf6/FrontAgent --skill skill-lifecycle -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ceilf6/FrontAgent skill-lifecycle --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ceilf6/FrontAgent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-lifecycle .agents/skills/skill-lifecycle && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .agents/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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 ceilf6/FrontAgent --skill skill-lifecycle -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ceilf6/FrontAgent skill-lifecycle --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ceilf6/FrontAgent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-lifecycle .cursor/skills/skill-lifecycle && 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 "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .cursor/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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/ceilf6/FrontAgent.git --path skills/skill-lifecycle--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 ceilf6/FrontAgent --skill skill-lifecycle -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ceilf6/FrontAgent skill-lifecycle --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ceilf6/FrontAgent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-lifecycle .gemini/skills/skill-lifecycle && 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 "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .gemini/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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 ceilf6/FrontAgent skill-lifecycleInstalls 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 ceilf6/FrontAgent --skill skill-lifecycle -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ceilf6/FrontAgent.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-lifecycle .github/skills/skill-lifecycle && 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 "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .github/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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 ceilf6/FrontAgent --skill skill-lifecycle -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ceilf6/FrontAgent skill-lifecycle --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ceilf6/FrontAgent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-lifecycle .opencode/skills/skill-lifecycle && 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 "skill-lifecycle" agent skill from https://github.com/ceilf6/FrontAgent/tree/develop/skills/skill-lifecycle into .opencode/skills/skill-lifecycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-lifecycle", 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
skill-lifecycle- GitHub stars
- 120
- Token cost
- ~747 tokens
- SKILL.md length
- 308 words
- Files
- 5 (incl. references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow.
- Works in 8 steps: Read references/workflow.md to choose… → Read references/eval-guidelines.md… → If the skill does not exist yet,… → …
- Adding a new skill
- SKILL.md covers Trigger, Workflow, Output Contract and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Skill Lifecycle is an agent skill from ceilf6/FrontAgent. Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow. Use when adding a new skill, tuning an existing skill's trigger behavior, iterating on SKILL.md instructions, or deciding whether a candidate skill should replace the current version.
Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `ADAPTATION.md`, `agents/openai.yaml` and `references/eval-guidelines.md`).
It sits in AI & LLM Engineering, covering LLM evaluation. The repository describes itself as: Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models |…. The licence is MIT.
When your agent uses it
- Adding a new skill
- Tuning an existing skills trigger behavior
- Iterating on SKILL.md instructions
- Deciding whether a candidate skill should replace the current version
Example prompts
- “/skill-lifecycle”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Read references/workflow.md to choose the right Skill Lab sequence.
- Read references/eval-guidelines.md before creating or editing trigger evals.
- If the skill does not exist yet, scaffold a new skill package (e.g. frontagent skill scaffold ).
- If the skill does not yet have evals, initialize trigger evals (e.g. frontagent skill init-evals ).
- If behavior quality matters, initialize behavior evals (e.g. frontagent skill init-behavior-evals ).
- Run a benchmark before making changes (e.g. frontagent skill benchmark ). Use --behavior when behavior evals are available.
- When improvement is requested, generate a candidate and compare it with baseline (e.g. frontagent skill improve ). Use --behavior to…
- Only apply a candidate when the benchmark clearly improves and the user wants promotion (e.g. frontagent skill promote or…
What it can do on your machine
Read from SKILL.md and the folder at commit e78cbed. 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
Skill Lifecycle loads about 747 tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 308 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 ceilf6/FrontAgent at commit e78cbed, republished under its MIT licence (© ceilf6). 308 words, ~747 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-lifecycle/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- skill-lifecycle
- description
- Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow. Use when adding a new skill, tuning an existing skill's trigger behavior, iterating on SKILL.md instructions, or deciding whether a candidate skill should replace the current version.
- triggers.explicit
- $skill-lifecycle, skill-lifecycle
- triggers.keywords
- create a skill, new skill, improve this skill, benchmark this skill, tune skill triggers, 迭代技能, 优化技能, 评测技能, 创建技能
- triggers.negative
- review code, bugfix, 普通页面开发
- license
- Inspired by Claude skill-creator concepts
Skill Creator
Use this skill when the user wants to work on content skills themselves — creating, evaluating, improving, or benchmarking them.
Trigger
- Requests to create a new content skill
- Requests to improve or benchmark an existing skill
- Requests to reduce false positives or false negatives in skill triggering
- Requests to compare the current skill against a revised candidate
Workflow
- Read
references/workflow.mdto choose the right Skill Lab sequence. - Read
references/eval-guidelines.mdbefore creating or editing trigger evals. - If the skill does not exist yet, scaffold a new skill package (e.g.
frontagent skill scaffold <skill-name>). - If the skill does not yet have evals, initialize trigger evals (e.g.
frontagent skill init-evals <skill-name>). - If behavior quality matters, initialize behavior evals (e.g.
frontagent skill init-behavior-evals <skill-name>). - Run a benchmark before making changes (e.g.
frontagent skill benchmark <skill-name>). Use--behaviorwhen behavior evals are available. - When improvement is requested, generate a candidate and compare it with baseline (e.g.
frontagent skill improve <skill-name>). Use--behaviorto include behavior scoring. - Only apply a candidate when the benchmark clearly improves and the user wants promotion (e.g.
frontagent skill promote <skill-name> <candidate-id>or--apply-if-better).
Platform-specific commands listed above use the
frontagent skillCLI. SeeADAPTATION.mdfor how to map these steps to a different platform.
Output Contract
- Keep the user informed of:
- where eval files live
- where candidate skills were written
- whether benchmark scores improved
- Prefer benchmark-backed recommendations over intuition.
- Treat the skill package itself as the artifact under iteration:
SKILL.mdagents/openai.yaml- existing
references/andassets/
Guardrails
- Do not trust starter evals blindly. Encourage editing them toward real prompts before strong conclusions.
- Do not auto-apply candidates unless the user requested it or the command explicitly says to do so.
- Do not silently broaden a skill's scope just to improve trigger rate.
- Prefer preserving existing references/assets over inventing new file paths.
© ceilf6, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in skills/skill-lifecycle of ceilf6/FrontAgent.
- SKILL.md
- ADAPTATION.md
- agents/openai.yaml
- references/eval-guidelines.md
- references/workflow.md
Open the folder on GitHubat commit e78cbed
Compare with similar skills
Skill Lifecycle 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 |
|---|---|---|---|---|---|---|
| Skill Lifecycle this skillceilf6/FrontAgent | 120 | — | ~747 | Automated safety check: Pass | MIT | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Fine-Tuning ExpertJeffallan/claude-skills | 12k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Looperksimback/looper | 710 | — | ~2.7k | Automated safety check: Notes | MIT | |
| Hugging Face Local Model Evalshuggingface/skills | 11k | 2 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Fine-Tuning Expert
Jeffallan/claude-skills
Guides LLM fine-tuning with LoRA and QLoRA through Hugging Face PEFT, from dataset validation and training checks to adapter merging, quantization and deployment.
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
- Official
Hugging Face Local Model Evals
huggingface/skills
Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.
- Official
Agent Eval Engineering
langchain-ai/langchain-skills
Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.
More from ceilf6/FrontAgent
Frontend Design
ceilf6/FrontAgent
Create distinctive, production-grade frontend interfaces with a clear visual direction while respecting project design specification constraints, existing design systems, and minimal-diff…
Frontend Reviewer
ceilf6/FrontAgent
Review frontend code, UI changes, generated implementations, and pull requests with severity-based findings and checklist-driven analysis.
Requirement Interviewer
ceilf6/FrontAgent
Gather missing product, UX, technical, and delivery constraints before planning or coding.
Related
Categories
Questions about Skill Lifecycle
What does Skill Lifecycle do?
Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow. Skill Lifecycle is an agent skill from ceilf6/FrontAgent. Create, evaluate, improve, and benchmark content skills using the local Skill Lab workflow.
When should I use Skill Lifecycle?
Skill Lifecycle fits situations like: adding a new skill; tuning an existing skills trigger behavior; iterating on SKILL.md instructions; deciding whether a candidate skill should replace the current version.
How do I install Skill Lifecycle in Claude Code?
Run `npx skills add ceilf6/FrontAgent --skill skill-lifecycle -a claude-code`. Or copy the skill folder (skills/skill-lifecycle in ceilf6/FrontAgent) into .claude/skills/skill-lifecycle in your project. Claude Code loads it when a task matches its description.
How do I install Skill Lifecycle in Codex?
Run `npx skills add ceilf6/FrontAgent --skill skill-lifecycle -a codex`. Or copy the skill folder (skills/skill-lifecycle in ceilf6/FrontAgent) into .agents/skills/skill-lifecycle in your project. Codex loads it when a task matches its description.
Can I use Skill Lifecycle 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 ceilf6/FrontAgent --skill skill-lifecycle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-lifecycle, .gemini/skills/skill-lifecycle, .github/skills/skill-lifecycle and .opencode/skills/skill-lifecycle in your project.
What does Skill Lifecycle need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Lifecycle is instructions for the agent only.
Does Skill Lifecycle 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 Skill Lifecycle 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 Skill Lifecycle use?
Skill Lifecycle 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 Skill Lifecycle use?
About 747 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 734 tokens, read only when the agent opens those files.
What are the alternatives to Skill Lifecycle?
Skills that share tags, products or a category with Skill Lifecycle: LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars), Azure AI Projects Python SDK (microsoft/skills, 3.1k stars), Fine-Tuning Expert (Jeffallan/claude-skills, 12k stars) and Looper (ksimback/looper, 710 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Lifecycle?
ceilf6 (a GitHub user) maintains it in ceilf6/FrontAgent, which has 120 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 30, 2026.
Source: ceilf6/FrontAgent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.