rna4219/skills/claude
skills/claude/SKILL.md
# Claude Skill for insight-agent ## 目的 Claude がこの repo を読むときに、設計の芯と変更境界を短時間でつかめるようにするためのガイドです。 ## まず理解すること - この repo は課題発見エンジン - 入力の正規化先は `InsightRequest` - 実行の正規入口は `run()` - 既定出力は `output_schema_v2` - CLI と API は同じ canonical runner を通る ## 推奨読順 1. `README.md` 2. `docs/src/output_schema_v2.json` 3. `insight_core/schemas.py` 4. `insight_core/runner.py` 5. `insight_core/result_formatter.py` 6. `insight_core/pipeline.py` ## どこを直すべきか - 入力の扱い: `insight_core/request_loader.py` - 設定の優先順位: `insi
$ install --global
skillsauthnpx skillsauth add rna4219/insight-agent skills/claudeInstall 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: Apr 12, 2026, 2:02 AM10.1s1 file scanned
SKILL.md
Claude Skill for insight-agent
目的
Claude がこの repo を読むときに、設計の芯と変更境界を短時間でつかめるようにするためのガイドです。
まず理解すること
- この repo は課題発見エンジン
- 入力の正規化先は
InsightRequest - 実行の正規入口は
run() - 既定出力は
output_schema_v2 - CLI と API は同じ canonical runner を通る
推奨読順
README.mddocs/src/output_schema_v2.jsoninsight_core/schemas.pyinsight_core/runner.pyinsight_core/result_formatter.pyinsight_core/pipeline.py
どこを直すべきか
- 入力の扱い:
insight_core/request_loader.py - 設定の優先順位:
insight_core/runtime_config.py - CLI の振る舞い:
insight_core/cli.py - 出力 contract:
insight_core/result_formatter.py - 実行フロー:
insight_core/pipeline.py
変更の原則
- 新しいユーザー向け挙動は
run()に集約する - pipeline に I/O 都合の分岐を増やさない
- provider / timeout / routing の切り替えは config に寄せる
- 論文固有の補正は formatter 側に閉じ込める
検証
python -m pytest -q
python -m insight_core.cli run --help
python -m insight_core.cli run --text material/6296_Support_Vector_Generation.txt
レビュー観点
- wrapper が本体扱いになっていないか
- README と実装の入口が一致しているか
- ルート直下に生成物や補助スクリプトが散らかっていないか
artifacts/,examples/,scripts/manual/,skills/の役割が保たれているか
Related Skills
rna4219/skills/codex
tools
VerifiedTrustedCommunity
# Codex Skill for insight-agent ## 目的 この repo で Codex が迷わず作業開始できるようにするための最小ガイドです。 ## 最初に見る場所 1. `README.md` 2. `docs/src/output_schema_v2.json` 3. `insight_core/runner.py` 4. `insight_core/runtime_config.py` 5. `insight_core/request_loader.py` ## 正規入口 - API の本命は `run()` - CLI の本命は `python -m insight_core.cli run ...` - `run_pipeline_result()` / `run_insight_result()` は互換 wrapper ## 変更方針 - 入口を増やすより `run()` に寄せる - 挙動差分は config で吸収する - 入力形式差分は loader 層で吸収する - 出力形式差分は formatter 層で吸収する - 既定の外
2SKILL.mdUpdated Apr 12, 2026
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026