Run any Skill in Manus with one click

my-investigate

Stars4

Forks1

UpdatedJuly 13, 2026 at 20:34

Investigate production, runtime, CI, or test issues by gathering evidence from logs, metrics, traces, code, and CI, then ranking hypotheses.

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

samcdavid

samcdavid/dotfiles

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Network and Computer Systems AdministratorsComputer and Mathematical Occupations·SOC 15-1244

File Explorer

13 files

SKILL.md

readonly

model	opus
name	my-investigate
description	Investigate production, runtime, CI, or test issues by gathering evidence from logs, metrics, traces, code, and CI, then ranking hypotheses.

Investigate

Coordinate a read-only runtime or CI investigation.

Load Rules

Read ~/.claude/rules/question-policy.md, ~/.claude/rules/no-outward-actions.md, and ~/.claude/rules/model-escalation.md when available. Use ~/.agents/rules/ under Codex. For full investigation procedure, read references/protocol-index.md.

Flow

Capture symptom, time range, affected service, artifacts, and user blast-radius hint.
Load Datadog/CircleCI skills before their tools when applicable.
Dispatch runtime-investigator with a structured bundle.
Review evidence, ranked hypotheses, and targeted questions.
Ask the user only for context tools cannot provide.
Do not mitigate or change infrastructure without explicit request.

Output

Return investigation summary, evidence, timeline, blast radius, ranked hypotheses, targeted questions, and read-only next checks.

More from this repository

same repository

address-pr-feedback

samcdavid/dotfiles

Address pending PR review feedback through verified triage, small fix phases, implementation, validation, and evidence-backed replies. Manual invocation only.

2026-07-134

autoresearch

samcdavid/dotfiles

Autonomous iteration loop for a measurable goal: review, ideate, modify, verify, keep or rollback, repeat until interrupted or capped.

2026-07-134

ci-babysit

samcdavid/dotfiles

Monitor a PR's CircleCI pipeline, diagnose failures, apply scoped fixes, push when requested, and continue until green or blocked.

2026-07-134

commit

samcdavid/dotfiles

Stage and commit changes in logical groups using the project's git message style, without mixing unrelated user changes.

2026-07-134

create-pr

samcdavid/dotfiles

Create or update a GitHub PR with concise description, review guidance, triggered specialty reviews, and focus areas.

2026-07-134

daily-summary

samcdavid/dotfiles

Build a daily work brief from yesterday/off-hours activity plus today's Linear, Calendar, Gmail, and Notion context; update Notion and produce standup/checklist.

2026-07-134

model	opus
name	my-investigate
description	Investigate production, runtime, CI, or test issues by gathering evidence from logs, metrics, traces, code, and CI, then ranking hypotheses.

Investigate

Coordinate a read-only runtime or CI investigation.

Load Rules

Flow

Capture symptom, time range, affected service, artifacts, and user blast-radius hint.
Load Datadog/CircleCI skills before their tools when applicable.
Dispatch runtime-investigator with a structured bundle.
Review evidence, ranked hypotheses, and targeted questions.
Ask the user only for context tools cannot provide.
Do not mitigate or change infrastructure without explicit request.

Output

Return investigation summary, evidence, timeline, blast radius, ranked hypotheses, targeted questions, and read-only next checks.