run-conversion-investigation
Run the governed conversion-drop investigation (ReAct + conditional ToT beam search with the multi-agent analyst team) and read the structured trace.
Skill by hreddy99
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hreddy99-run-conversion-investigation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/run-conversion-investigation
What's inside
- Skill name
run-conversion-investigation- Description
- Run the governed conversion-drop investigation (ReAct + conditional ToT beam search with the multi-agent analyst team) and read the structured trace.
- License
- MIT
- Instructions
- 16 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Run a Conversion Investigation
The flagship workflow: classify → catalog sync gate → retrieve → validate → relate →
baseline → ToT gate → dispatch analyst team (parallel) → critic + beam → evidence gate →
synthesize. Evidence strength is gated on the structural checks (metric + graph + SQL).
## Instructions
1. `from workflows.investigation import run_investigation`
2. `t = run_investigation("Why did digital conversion drop yesterday compared with the prior 7-day average?")`
3. Read: `t["answer"]` (headline, summary, drivers, exec_summary), `t["beam"]` /
`t["depth1"]` (scored branches), `t["steps"]` (decision log), `t["audit"]` (events).
4. Tune `beam_width`, `depth`, `top_k`, or `inject_failure` to explore behavior.
5. In the app, the **🔬 Run Analysis** page streams each step and exposes the review tabs.
Implementation: `workflows/graph.py` (LangGraph), `skills/tot_skill.py` (scoring), `agents/team.py` (team).From hreddy99/omnichannel-retail-analytics-assistant, MIT.
More from hreddy99/omnichannel-retail-analytics-assistant
- 0.507score
refresh-synthetic-data
hreddy99
Regenerate and validate the synthetic retail dataset.
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
add-governed-insight
hreddy99
Add a new direct analytics insight question (a single governed read-only query with a numeric summary and chart).
SkillCFreshness: C★ 2Claude Code +9 - 0.499score
sql-safety-check
hreddy99
Validate that a SQL statement is read-only and uses only catalog-approved tables.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 26, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hreddy99
- 0.507score
refresh-synthetic-data
hreddy99
Regenerate and validate the synthetic retail dataset.
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
add-governed-insight
hreddy99
Add a new direct analytics insight question (a single governed read-only query with a numeric summary and chart).
SkillCFreshness: C★ 2Claude Code +9 - 0.499score
sql-safety-check
hreddy99
Validate that a SQL statement is read-only and uses only catalog-approved tables.
SkillCFreshness: C★ 2Claude Code +9
Cite this page
run-conversion-investigation skill. Agent Mart. https://agentmart.dev/skills/hreddy99-run-conversion-investigation (last updated 2026-10-24)