Ready to supercharge your AI agents?

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

Get Started Free →

collect-target-context — measured AI agent skill | DecimalAI

understudy-ai/collect-target-context

NewSkillScoreMaintained

Collect the baseline context bundle for the selected target.

by understudy-ai

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

Automatic

AI Engineer pack

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

pip install decimalai

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

decimalai skills pull understudy-ai-collect-target-context --out .claude/skills/

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

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

Raw file: /s/understudy-ai-collect-target-context/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-collect-target-context.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

22 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

—-44% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	-63%	0%
case-05	✗→✓	▲ Improved	-66%	0%
case-13	✗→✓	▲ Improved	-60%	0%
case-17	✗→✓	▲ Improved	-57%	0%
case-19	✗→✓	▲ Improved	-68%	0%

Showing 5 of 22 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/collect-target-context/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

collect-target-context

Overall Goal

Collect the baseline target metadata and first-pass context notes for the selected target.

Inputs

targetName
artifactsRootDir

Outputs

target.json
context.md

Staged Workflow

Normalize the target name and artifacts root path.
Gather stable baseline facts for the target bundle.
Write target.json and context.md.

Tool Route Options

shell for writing deterministic output files
gui when baseline facts must be grounded from the visible target surface

Detailed GUI Replay Hints

Prefer surface-local capture whenever the target is visible in a bounded window.
Quote visible labels if the operator needs to re-run the capture manually.

Failure Policy

Stop if no target name is available.
Preserve partial context output rather than overwriting it with empty data.

Want to see if understudy-ai/collect-target-context 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.