Agent Skill
Autonomous Investigation skill
autonomous-investigationdeanpeters/Product-Manager-Skillsskills/autonomous-investigation/SKILL.md
The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.
always on
40 tokname + description
once used
2,475 tokSKILL.md body
bundled files
313 KB
repo stars
7.6kGitHub
Install the Autonomous Investigation skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/deanpeters/Product-Manager-Skills --skill autonomous-investigation
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/deanpeters/Product-Manager-Skills.git /tmp/Product-Manager-Skills mkdir -p ~/.claude/skills cp -R /tmp/Product-Manager-Skills/skills/autonomous-investigation ~/.claude/skills/autonomous-investigation
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 40 tok |
| When the agent uses it | The SKILL.md instructions | 2,475 tok |
| Only if opened | 3 bundled files (13 KB) | varies |
Until it is used, autonomous-investigation costs about 34× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 77 skills from deanpeters/Product-Manager-Skills would load 2,883 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Autonomous Investigation Protocol
- Purpose
- Input
- Key Concepts
- Two protocols, two jobs
- The contract
- The Confidence Stacking Rule
- Guardrails
- Application
- For skills implementing this protocol
- For agents running an investigation
- Examples
- Common Pitfalls
- References
More skills from deanpeters/Product-Manager-Skills
- acquisition-channel-advisordeanpeters/Product-Manager-Skills
Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.
7.6k34 tok idle · 5,366 in use - agent-orchestration-advisordeanpeters/Product-Manager-Skills
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
7.6k40 tok idle · 7,154 in use - ai-shaped-readiness-advisordeanpeters/Product-Manager-Skills
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
7.6k33 tok idle · 9,703 in use - altitude-horizon-frameworkdeanpeters/Product-Manager-Skills
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
7.6k33 tok idle · 2,912 in use - ansoff-matrixdeanpeters/Product-Manager-Skills
Map evidence-backed growth options across the Ansoff Matrix with risk-rated sequencing. Use when the question is where the next tranche of growth comes from, and at what risk.
7.6k40 tok idle · 2,405 in use - battle-card-builderdeanpeters/Product-Manager-Skills
Research and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.
7.6k36 tok idle · 2,168 in use - business-health-diagnosticdeanpeters/Product-Manager-Skills
Diagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes.
7.6k32 tok idle · 5,919 in use - company-inteldeanpeters/Product-Manager-Skills
Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
7.6k33 tok idle · 6,732 in use