Ready to supercharge your AI agents?

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

Get Started Free →

explore-unfamiliar-target — measured AI agent skill | DecimalAI

understudy-ai/explore-unfamiliar-target

NewSkillScoreMaintained

Goal-driven worker for exploring an unfamiliar target.

Testingby understudy-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-explore-unfamiliar-target/SKILL.md

decimalai skills pull understudy-ai-explore-unfamiliar-target --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/understudy-ai-explore-unfamiliar-target/SKILL.md https://app.decimal.ai/s/understudy-ai-explore-unfamiliar-target/SKILL.md

Raw file: /s/understudy-ai-explore-unfamiliar-target/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-explore-unfamiliar-target.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-37% tokens0% turns78% of whole cases pass with skill (18/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-44%	0%
case-08	✗→✓	▲ Improved	-54%	0%
case-10	✗→✓	▲ Improved	-60%	0%
case-11	✗→✓	▲ Improved	-52%	0%
case-12	✗→✓	▲ Improved	-54%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

understudy-ai / understudy

packages/gateway/src/__tests__/fixtures/handwritten-playbook-demo/skills/explore-unfamiliar-target/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

explore-unfamiliar-target

Goal

Explore the unfamiliar target currently assigned to the run.

Operating Contract

Work from the visible app state rather than assuming a fixed flow.
Capture enough evidence for highlights, limitations, and a short brief.
Prefer user-visible value over exhaustive settings exploration.

Inputs

targetName
artifactsRootDir
analysisFocus

Outputs

findings.md
highlights.json
limitations.json
worker-summary.json
screenshots/

Budget

maxMinutes=12
maxActions=60
maxScreenshots=12

Allowed Surfaces

Only the surfaces assigned to the run
Supporting workspace windows only when required

Stop Conditions

Enough evidence exists for 2-3 highlights and 1 limitation.
The budget is exhausted.
A hard block such as authentication or missing permissions prevents further exploration.

Decision Heuristics

Prefer first-run onboarding and core feature paths.
Capture screenshots only when they materially improve the brief.

Failure Policy

Escalate if payment is required.
Escalate if personal account creation is required.
Escalate if the app crashes repeatedly.

Want to see if understudy-ai/explore-unfamiliar-target would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.