asking-diligence

Spawn a read-only conversational analyst over a code-diligence target's warehouse and repo clones for open-ended drill-down into a finding (e.g., "why is this repo a hotspot?", "who carries bus-factor risk for X?"). Use when the user invokes /code-diligence:ask. Distinct from investigating which tool fed which warehouse column — use interpreting-tool-output for that.

Jump to install

Repository: AeyeOps/aeo-diligence-marketplace
Last source activity: May 16, 2026 at 23:10
Detected SKILL.md language: English
Stars: 0
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/AeyeOps/aeo-diligence-marketplace --skill asking-diligence

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

ingesting-target

Initial setup for a new code-diligence target — clone repos, walk git history, run the tool wrappers, populate the warehouse, and generate curation YAMLs. Use when the user invokes /code-diligence:ingest, or sets up code-diligence on a target for the first time (no warehouse exists yet). For already-ingested targets that need new commits picked up, use refreshing-target.

2026-05-16

interpreting-tool-output

Reference for mapping raw tool output (code-maat, hercules, git-of-theseus, git-fame, git-truck, repowise) to warehouse tables, tool-specific quirks, and cross-check rules. Use when debugging warehouse mismatches, investigating why two tools report different values for the same metric, deciding which canonical source to trust, or querying a specific warehouse table to compare per-tool entries — distinct from open-ended dashboard drill-down (asker) or writing narrative copy (axes).

2026-05-16

refreshing-target

Incrementally refresh an existing code-diligence target — pull new commits, rerun the tool wrappers, and update the warehouse without resetting analyst-confirmed curations. Use when the target was already ingested (its warehouse exists) and the user invokes /code-diligence:refresh, or asks to recompute, rerun, or update an existing target's data.

2026-05-16

View all from this repository

name	asking-diligence
description	Spawn a read-only conversational analyst over a code-diligence target's warehouse and repo clones for open-ended drill-down into a finding (e.g., "why is this repo a hotspot?", "who carries bus-factor risk for X?"). Use when the user invokes /code-diligence:ask. Distinct from investigating which tool fed which warehouse column — use interpreting-tool-output for that.
argument-hint	<target> <question>
allowed-tools	Task, Bash, Read

The user has invoked /code-diligence:ask <target> <question>.

Resolve <target> to its settings file at ~/.claude/code-diligence-<target>.local.md. If missing, tell the user to follow skills/ingesting-target/SKILL.md first and stop.
From the settings file, capture target_id, target_name, storage.warehouse_path, and storage.repo_clone_root. Export DILIGENCE_WAREHOUSE_PATH=<warehouse_path> for the agent's environment so the warehouse MCP picks it up.
Use the Task tool to spawn the diligence-asker agent (defined in agents/diligence-asker.md) with:
- Initial prompt: the user's <question> verbatim
- Context block: target_id, target_name, repo_clone_root
Stream the agent's response back to the user. For follow-ups in the same turn, re-use the same agent invocation via SendMessage (do not respawn). A fresh /code-diligence:ask call always spins up a new agent so the read-only boundary stays intact.
The asker is read-only by design — it can query the warehouse and read repo files, but cannot write narratives or modify the warehouse. If the user asks for a re-narration, redirect to skills/refreshing-target/SKILL.md (which calls the narrator with write access).

Agent boundary details and the warehouse MCP query surface: references/asker-boundary.md.

asking-diligence

Source facts

Install options

Review the source files

More from this repository

More from this repository