Skip to content
Back to skills

Investigation Focus

ASecurity

Guide a substantial evidence-led investigation, whether the requested result is already clear or the human needs to narrow a diffuse question, retain context across sessions, or make several decision-ready outputs. Do not use for ordinary repository delivery or a one-off factual answer.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 3, 2026
developmentgit

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add valsteen/pinboard --skill investigation-focus --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Investigation Focus?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Investigation Focus
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/valsteen-investigation-focus/badge)](https://www.skillsdirectory.com/skills/valsteen-investigation-focus)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: investigation-focus
description: Guide a substantial evidence-led investigation, whether the requested result is already clear or the human needs to narrow a diffuse question, retain context across sessions, or make several decision-ready outputs. Do not use for ordinary repository delivery or a one-off factual answer.
---

# Investigation focus

Deliver the human's requested result through a bounded investigation. Keep the inquiry broad enough to test that result against varied available sources. The human owns the direction, any inquiry home, and any action beyond investigation.

## Start or resume

When the request already fixes a tangible result, audience or format, and usable sources, begin the investigation. Deliver the complete requested artifact at the authorized destination. Do not make selection of another outcome or inquiry home a prerequisite. Ask only for a choice that materially changes the result or is needed to proceed. Keep the first pass bounded by the request and available evidence; explain before expanding into materially different research or outputs.

For a continuing inquiry, use the caller's selected local inquiry home separate from repositories and other evidence sources. Ask the caller to select one only when durable multi-session state is needed and no authorized home is available. Git is optional. Before resuming, read the existing note there, including the last agreed direction, source windows, corrections, dismissed leads, gaps, and output relationships. For a new continuing inquiry, create a human-readable note with a stable inquiry ID, purpose, and first pass. Do not use chat as the only continuity record or write into a source repository merely because it can be read.

When the request genuinely branches into different results, present a few concrete outcomes grounded in what is known and ask the human to choose. Record that choice and a pass bound: time, effort, sources, or a stopping observation when using a continuing note. A correction changes the next direction; retain the previous agreement and observations with their dates or revisions. Use [the note example](references/inquiry-note.md) when a concrete continuity shape helps; adapt it to the inquiry rather than filling empty sections mechanically.

## Investigate and report

Check varied relevant source types that the caller permits. For each consequential observation, save the original source locator, revision or time window, and a short checkable excerpt when useful. Distinguish an observation from an inference, proposal, human agreement, disputed claim, or unknown. A link or temporal sequence alone does not establish cause. Record inaccessible and unsearched sources as coverage gaps, not negative evidence. Keep dismissed leads and why they were dismissed so a fresh session does not reopen them silently.

Make a bounded pass useful even when evidence is incomplete. Stop at the agreed bound, a supported answer with stated limits, diminishing returns, a necessary unavailable source, or an urgent finding that needs human attention. Put consequential findings, their checkable sources, uncertainty, and the human acknowledgement or decision needed before research detail. Surface urgent evidence promptly without changing production state, sending messages, or starting delivery work on that basis alone.

When using an inquiry note, save each pass with its stop reason and next useful question. Append new source windows and corrections rather than replacing earlier ones. For each audience output, record its own ID, revision, audience, purpose, and the observations and human decisions it uses. Revise one output deliberately without implying another changed. Use Technical Writing to shape substantial prose after the evidence and decision context is clear. Return the complete requested output in its requested format; keep optional follow-up work behind it.

Files in this skill

  • SKILL.md3.8 KB
  • agents/openai.yaml399 B
  • references/inquiry-note.md3.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.