Self-Improvement Tournament Loop
zereight/gitlab-mcp
Runs an autonomous evolutionary loop that improves a codebase against a measurable benchmark, using agent roles, tournament selection and recorded history until a stop condition.
Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents.
Install Effective Harnesses
$ npx skills add liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install liangdabiao/exa-research-mcp-skill effective-harnesses --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/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/effective-harnesses .claude/skills/effective-harnesses && 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 "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .claude/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnessesType 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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install liangdabiao/exa-research-mcp-skill effective-harnesses --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/effective-harnesses .agents/skills/effective-harnesses && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .agents/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install liangdabiao/exa-research-mcp-skill effective-harnesses --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/effective-harnesses .cursor/skills/effective-harnesses && 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 "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .cursor/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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/liangdabiao/exa-research-mcp-skill.git --path skills/effective-harnesses--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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install liangdabiao/exa-research-mcp-skill effective-harnesses --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/effective-harnesses .gemini/skills/effective-harnesses && 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 "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .gemini/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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 liangdabiao/exa-research-mcp-skill effective-harnessesInstalls 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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/effective-harnesses .github/skills/effective-harnesses && 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 "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .github/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install liangdabiao/exa-research-mcp-skill effective-harnesses --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liangdabiao/exa-research-mcp-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/effective-harnesses .opencode/skills/effective-harnesses && 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 "effective-harnesses" agent skill from https://github.com/liangdabiao/exa-research-mcp-skill/tree/main/skills/effective-harnesses into .opencode/skills/effective-harnesses/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effective-harnesses", 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
effective-harnesses- GitHub stars
- 110
- Token cost
- ~1.5k tokens
- SKILL.md length
- 658 words
- Files
- 2
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- None found
At a glance
Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents.
- Works in 6 steps: Identify the project goal, stack,… → Create feature_list.json from the schema… → Create a repeatable bootstrap if useful:… → …
- Maintain projects that need feature decomposition
- SKILL.md covers Purpose, Core Principles, Harness Files and Initialize a Project, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Effective Harnesses is an agent skill from liangdabiao/exa-research-mcp-skill. Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents. Use to initialize or maintain projects that need feature decomposition, resumable progress tracking, test-gated completion, session recovery, and git-backed checkpoints through files such as featurelist.json, init.sh, progress logs, and coding standards.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering Code quality and Autonomous loops. It works with Git. The repository describes itself as: 基于 Claude Code 和 Exa 搜索引擎的 AI 驱动企业与市场研究工具。核心特性 - 智能公司研究: 自动收集公司信息、新闻、社交媒体动态、财务数据和 LinkedIn 资料 - 竞争对手分析: 快速构建竞争对手列表，分析市场定位 - 市场研究: 跟踪行业趋势、并购活动、技术发展 - 上下文隔离: 所有搜索在独立代理中运行，保持主对话整洁 -….
When your agent uses it
- Maintain projects that need feature decomposition
- Resumable progress tracking
- Test-gated completion
- Session recovery
Example prompts
- “/effective-harnesses”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Identify the project goal, stack, default test command, and startup command.
- Create feature_list.json from the schema below.
- Create a repeatable bootstrap if useful: init.sh for Unix-like shells, init.ps1 or init.py for Windows native. Do not require Bash on…
- Create agent-progress.md with initial context, assumptions, and next feature.
- Create or update CODING_STANDARDS.md only when project conventions are known or requested.
- Run the bootstrap and/or test command if safe in the current environment.
What it can do on your machine
Read from SKILL.md and the folder at commit 6a345be. 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 json and markdown).
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
Effective Harnesses loads about 1.5k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 658 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 658 words (~1,516 tokens).
“Use this skill to keep long-running implementation or research projects reliable across many agent sessions. Maintain a small set of durable project files so any compatible agent can resume work without relying on hidden chat context.”
- name
- effective-harnesses
Files
SKILL.md and 1 other file in skills/effective-harnesses of liangdabiao/exa-research-mcp-skill.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 6a345be
Compare with similar skills
Effective Harnesses 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 |
|---|---|---|---|---|---|---|
| Effective Harnesses this skillliangdabiao/exa-research-mcp-skill | 110 | — | ~1.5k | Automated safety check: Pass | None | |
| Self-Improvement Tournament Loopzereight/gitlab-mcp | 2k | 1 repos | ~1.8k | Automated safety check: Warn | MIT | |
| Repository Health and Gap AssessoropenJiuwen-ai/agent-core | 446 | — | ~613 | Automated safety check: Pass | Apache-2.0 | |
| Code Reviewaiskillstore/marketplace | 433 | — | ~2.3k | Automated safety check: Pass | None | |
| Qt C++ Code Reviewx-tools-author/x-tools | 1.1k | 2 repos | ~4.3k | Automated safety check: Pass | BSD-3-Clause | |
| Skill Doctorwarpdotdev/common-skills | 610 | 2 repos | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Repository Health and Gap Assessor
openJiuwen-ai/agent-core
Runs a read-only assessment in one of two modes, a repository health check or a runtime extension gap review, and reports findings as a markdown table.
Code Review
aiskillstore/marketplace
This skill should be used when the user requests a code review of changed files.
Qt C++ Code Review
x-tools-author/x-tools
Read-only review of Qt6 C++ code that combines a deterministic lint script with six parallel analysis agents and reports only high-confidence issues.
Skill Doctor
warpdotdev/common-skills
Grades agent skills by scoring agent conversations for efficiency, code quality, procedure compliance, and verbosity, then drafts concrete skill edits and a shareable report.
Ponytail Debt Ledger
DietrichGebert/ponytail
Collects every ponytail: comment in a codebase into one debt ledger, flags shortcuts with no upgrade trigger and reports without changing any files.
More from liangdabiao/exa-research-mcp-skill
Renewable Market Research
liangdabiao/exa-research-mcp-skill
Workflow skill for evidence-based renewable energy market research, V4 full country wind-market status reports, source-to-final continuity, project pipeline verification, deduplication, product-fit…
Company Research
liangdabiao/exa-research-mcp-skill
Company, competitor, and market intelligence research using Exa or an equivalent web-search/MCP tool.
Foreign Trade Research
liangdabiao/exa-research-mcp-skill
Deep foreign-trade and overseas market-entry research for a target country plus product/category.
Foreign Trade Research
liangdabiao/exa-research-mcp-skill
深度外贸市场调研技能。对目标国家+产品领域进行全面竞争对手分析，覆盖品牌商、制造商、经销商，生成含市场格局、定价策略、渠道分析和进入建议的完整调研报告。
Company Research
liangdabiao/exa-research-mcp-skill
Company research using Exa search. An agent skill from liangdabiao/exa-research-mcp-skill.
Effective Harnesses
liangdabiao/exa-research-mcp-skill
长时间运行 Agent 框架 - 项目初始化、feature 管理、进度追踪
Related
Works with
Categories
Questions about Effective Harnesses
What does Effective Harnesses do?
Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents. Effective Harnesses is an agent skill from liangdabiao/exa-research-mcp-skill. Long-running agent project harness for Codex, OpenClaw, Claude Code, and other coding agents.
When should I use Effective Harnesses?
Effective Harnesses fits situations like: maintain projects that need feature decomposition; resumable progress tracking; test-gated completion; session recovery.
How do I install Effective Harnesses in Claude Code?
Run `npx skills add liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a claude-code`. Or copy the skill folder (skills/effective-harnesses in liangdabiao/exa-research-mcp-skill) into .claude/skills/effective-harnesses in your project. Claude Code loads it when a task matches its description.
How do I install Effective Harnesses in Codex?
Run `npx skills add liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a codex`. Or copy the skill folder (skills/effective-harnesses in liangdabiao/exa-research-mcp-skill) into .agents/skills/effective-harnesses in your project. Codex loads it when a task matches its description.
Can I use Effective Harnesses 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 liangdabiao/exa-research-mcp-skill --skill effective-harnesses -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/effective-harnesses, .gemini/skills/effective-harnesses, .github/skills/effective-harnesses and .opencode/skills/effective-harnesses in your project.
What does Effective Harnesses need to run?
SKILL.md names no scripts, command-line tools or credentials: Effective Harnesses is instructions for the agent only. Our summary lists: Python 3.
Does Effective Harnesses 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 Effective Harnesses 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 Effective Harnesses use?
No licence was found for Effective Harnesses or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Effective Harnesses use?
About 1.5k tokens (SKILL.md is roughly 6.1k 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 Effective Harnesses?
Skills that share tags, products or a category with Effective Harnesses: Self-Improvement Tournament Loop (zereight/gitlab-mcp, 2k stars), Repository Health and Gap Assessor (openJiuwen-ai/agent-core, 446 stars), Code Review (aiskillstore/marketplace, 433 stars) and Qt C++ Code Review (x-tools-author/x-tools, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Effective Harnesses?
liangdabiao (a GitHub user) maintains it in liangdabiao/exa-research-mcp-skill, which has 110 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 8, 2026.
Source: liangdabiao/exa-research-mcp-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.