Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Product Opportunity Tree · stijnman | DecimalAI

productivityby stijnman

Product Opportunity Tree

stijnman/product-opportunity-tree

Source stijnman/grok-custom-skills ↗License MIT

Map a measurable product outcome to customer opportunities, solution options, and assumption tests.

SkillScore86Maintained

Automatic

Product Management pack

Last verified 9/6/2026

What it changes

Passed 19 of 22 test cases with the skill, and 14 of 22 without it.

Without skill64%

With skill86%

Checks it passed that the model alone missed

The response includes open questions.
The response explicitly labels the proposed proxy metric as a draft.
The response labels developer guesses as inferred and unstudied areas as unknown.

and 4 more in the full report

6 fixed13 passed either way2 still failing1 broke

Pass-rate lift: +23 pp
Tokens: +8%
Agent turns: 0%
Response time: -5%

Model gemini-3.6-flashMeasured 9/6/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-product-opportunity-tree/SKILL.md https://app.decimal.ai/s/stijnman-product-opportunity-tree/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-product-opportunity-tree, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-product-opportunity-tree/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-product-opportunity-tree

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-product-opportunity-tree/SKILL.md https://app.decimal.ai/s/stijnman-product-opportunity-tree/SKILL.md

Raw file: /s/stijnman-product-opportunity-tree/SKILL.md ↗ · machine-readable summary at /s/stijnman-product-opportunity-tree.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Our executive team wants us to 'make the platform feel modern and delightful' this half. Help us map this effort using a structured discovery breakdown. Be realistic about whether this objective works as a top-level anchor, and suggest appropriate adjustments if needed.

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies that 'make the platform feel modern and delightful' is non-measurable.	Passed	Passed
The response proposes a measurable proxy metric.	Passed	Passed
The response explicitly labels the proposed proxy metric as a draft.	Missed	Passed

case-04 · gemini-3.6-flash · 9/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md32 linessingle file

Product Opportunity Tree

Purpose

Create an evidence-aware opportunity tree that connects a desired outcome to customer needs, candidate solutions, and assumption tests. Use it to avoid treating a feature idea as the problem definition.

Workflow

Define one measurable outcome that the team can influence, including its current baseline if known.
List customer opportunities as needs, barriers, or desired outcomes rather than proposed features.
Attach evidence to each opportunity and label it as observed, reported, inferred, or unknown.
Generate multiple solution options for promising opportunities; do not select a solution merely because it was proposed first.
Identify the riskiest assumption for each selected solution and define the smallest ethical test that could reduce uncertainty.
Prioritize the next branch using impact, confidence, effort, and evidence quality.
Deliver a tree, evidence notes, open questions, and the next experiment.

Output format

Use a concise hierarchy: Outcome → Opportunities → Solutions → Assumption tests. Include a Mermaid diagram when it improves readability, but keep the textual hierarchy authoritative.

Quality boundaries

Do not invent research evidence, customer quotes, baselines, or business impact. Distinguish a hypothesis from a validated opportunity. Do not present the tree as a commitment or roadmap without the relevant stakeholder approval.

Error handling

Situation	Response
Outcome is not measurable	Propose a measurable proxy and label it as a draft.
Evidence is sparse	Keep opportunities provisional and recommend discovery work before prioritization.
Solution list is already fixed	Record the constraint and identify the assumptions that still need testing.
Stakeholders disagree	Represent competing outcomes or assumptions rather than forcing a false consensus.

Track record

Benchmark

19 / 22

test cases passed, vs 14 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/product-opportunity-tree/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/15/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Product Opportunity Tree

Purpose

Workflow

Output format

Quality boundaries

Error handling

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills