Run any Skill in Manus with one click

ingesting-target

Stars0

Forks0

UpdatedMay 16, 2026 at 23:10

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.

Installation

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.

Run Skill in Manus

Source

AeyeOps

AeyeOps/aeo-diligence-marketplace

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

3 files

SKILL.md

readonly

name	ingesting-target
description	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.
argument-hint	<target> [--quick \| --full]
allowed-tools	Bash, Read

The user has invoked /code-diligence:ingest <target> [--quick|--full].

Resolve <target> to a settings file at ~/.claude/code-diligence-<target>.local.md. If it does not exist, tell the user to copy the template at settings/diligence.example.local.md (path relative to the plugin root) and edit it; do not proceed.
If neither --quick nor --full was passed, ask which tier and explain the trade-off in one sentence each:
- --quick (<30 min for ~280 repos) — git walker + cheap tools (git-fame, git-of-theseus, git-truck); Process axis confidence will be low because expensive tools and the GitHub platform pass are skipped.
- --full (1–3 hours) — adds hercules, code-maat, repowise, and the GitHub platform pass (PRs, Actions, releases, issues).

Run:

uv run --directory ${CLAUDE_PLUGIN_ROOT} code-diligence ingest <settings-path> --<tier>

After the CLI exits successfully, surface from its stdout:
- The path where the three curation YAMLs were written (storage.curation_dir)
- The count of "needs review" entries in each YAML — partners triage those before viewing the dashboard
If the CLI exits non-zero, surface stderr verbatim. Do not paraphrase tool errors — wrappers already log tool_failures rows for non-fatal cases.

What gets populated and in what order: references/pipeline-stages.md. Required external binaries and the skip behavior when they're missing: references/tool-prerequisites.md.

More from this repository

same repository

asking-diligence

AeyeOps/aeo-diligence-marketplace

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.

2026-05-160

interpreting-tool-output

AeyeOps/aeo-diligence-marketplace

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).

2026-05-160

refreshing-target

AeyeOps/aeo-diligence-marketplace

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.

2026-05-160

understanding-pe-diligence-axes

AeyeOps/aeo-diligence-marketplace

Reference for the People / Product / Process taxonomy, card-to-table mappings, confidence model, and narrative-writing contract (headline-first, cite warehouse numbers, hedge on low confidence). Use when interpreting what a dashboard card measures, writing or updating narrative rows, understanding confidence classifications, or avoiding hallucination in PE write-ups — not for querying the warehouse or executing tool commands.

2026-05-160

building-dashboard

AeyeOps/aeo-diligence-marketplace

Build the Observable Framework dashboard for a code-diligence target's warehouse, honoring the privacy gate on the working-pattern card. Use when the user invokes /code-diligence:dashboard, or auto-fired by the PostToolUse hook after a warehouse write.

2026-05-160

name	ingesting-target
description	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.
argument-hint	<target> [--quick \| --full]
allowed-tools	Bash, Read

The user has invoked /code-diligence:ingest <target> [--quick|--full].

Resolve <target> to a settings file at ~/.claude/code-diligence-<target>.local.md. If it does not exist, tell the user to copy the template at settings/diligence.example.local.md (path relative to the plugin root) and edit it; do not proceed.
If neither --quick nor --full was passed, ask which tier and explain the trade-off in one sentence each:
- --quick (<30 min for ~280 repos) — git walker + cheap tools (git-fame, git-of-theseus, git-truck); Process axis confidence will be low because expensive tools and the GitHub platform pass are skipped.
- --full (1–3 hours) — adds hercules, code-maat, repowise, and the GitHub platform pass (PRs, Actions, releases, issues).

Run:

uv run --directory ${CLAUDE_PLUGIN_ROOT} code-diligence ingest <settings-path> --<tier>

After the CLI exits successfully, surface from its stdout:
- The path where the three curation YAMLs were written (storage.curation_dir)
- The count of "needs review" entries in each YAML — partners triage those before viewing the dashboard
If the CLI exits non-zero, surface stderr verbatim. Do not paraphrase tool errors — wrappers already log tool_failures rows for non-fatal cases.

What gets populated and in what order: references/pipeline-stages.md. Required external binaries and the skip behavior when they're missing: references/tool-prerequisites.md.