agentscope-ai/synthesize-report
agentscope-examples/agents/agentscope-builder/src/main/resources/templates/research-assistant/skills/synthesize-report/SKILL.md
Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
$ install --global
skillsauthnpx skillsauth add agentscope-ai/agentscope-java synthesize-reportInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 27, 2026, 5:08 AM110.2s1 file scanned
SKILL.md
- name:
- synthesize-report
- description:
- Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
Synthesize a report from sources
A playbook for producing a citation-grounded summary across one or more source files in the workspace.
When to use
The user asks for a summary, briefing, literature review, or comparison and the
material is reachable via list_files / read_file / grep_files.
Steps
- Inventory. Run
list_fileson the user-specified directory (or the whole workspace) and pick the files most likely to contain the answer. - Skim. Read each candidate file once. Note the headings and any obvious claim sentences.
- Extract. For every claim worth keeping, capture:
- the claim in one sentence,
- the shortest supporting quote (≤ 25 words), and
- the file path.
- Group. Cluster claims by topic, not by source file.
- Compose. Use the template in
AGENTS.mdto write the report. Prefer bulleted lists; reserve prose for the introduction and conclusion. - Self-check. Re-read the draft and remove any sentence that is not supported by a citation.
Output
Markdown report following the AGENTS.md template. End with a ## Sources
section listing every cited file with a one-line gloss.
Related Skills
agentscope-ai/docs/v2/zh/docs/harness
documentation
VerifiedTrustedCommunity
四层技能合成、技能市场、自学习闭环
3,469SKILL.mdUpdated Jun 4, 2026
agentscope-ai/docs/v2/en/docs/harness
documentation
VerifiedTrustedCommunity
Four-layer skill composition, skill marketplaces, the self-learning loop
3,469SKILL.mdUpdated Jun 4, 2026
agentscope-ai/docs/v1/zh/docs/harness
tools
VerifiedTrustedCommunity
# 技能（Skill） 一个 skill 就是一份写好的能力包：一个目录里放一份 `SKILL.md`（说明用途、给 agent 看的指令），可以再带一些参考文档、脚本或样例。写好后丢给 agent，它会在合适的时候自己用。 harness 让你从两个地方装 skill： - **接 skill 市场**：Git 仓库、Nacos、MySQL、classpath、或者自己写的后端 - **放在工作区**：项目里 `workspace/skills/` 下的就所有人共用；放在 `<userId>/skills/` 下的只有那个用户看得到 两类来源同时生效，不需要二选一。 > 关于 skill 自身的结构、`SKILL.md` 写法、资源加载、tool 绑定、代码执行这些通用概念，见 [Agent Skill](../task/agent-skill.md)。本文只讲 harness 这一层的用法。 --- ## 一个例子 把团队的 skill 仓库接进来，agent 立刻就能用： ```java HarnessAgent agent = HarnessAgent.bui
3,469SKILL.mdUpdated Jun 4, 2026
agentscope-ai/sql-analysis
data-ai
VerifiedTrustedCommunity
Answer a quantitative business question by writing a SQL query against the data warehouse, validating it, and presenting the result. Use when the user asks "how many...", "what's the trend of...", "compare X vs Y over...", "what's our top N...", or anything that resolves to a query against tabular data. Produces a small result table plus the underlying query.
3,469SKILL.mdUpdated Jun 4, 2026