Ready to supercharge your AI agents?

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

Get Started Free →

target-brief-baseline-stage — measured AI agent skill | DecimalAI

understudy-ai/target-brief-baseline-stage

NewSkillScoreMaintained

Single-stage acceptance playbook for the baseline context phase.

by understudy-ai

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

Automatic

Research pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-target-brief-baseline-stage/SKILL.md

decimalai skills pull understudy-ai-target-brief-baseline-stage --out .claude/skills/

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

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

Raw file: /s/understudy-ai-target-brief-baseline-stage/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-target-brief-baseline-stage.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

—-36% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-34%	0%
case-03	✗→✓	▲ Improved	-21%	0%
case-05	✗→✓	▲ Improved	-62%	0%
case-06	✗→✓	▲ Improved	-73%	0%
case-07	✗→✓	▲ Improved	-63%	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/target-brief-baseline-stage/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

target-brief-baseline-stage

Goal

Run the baseline context stage end to end for a selected target.

Inputs

targetName

Child Artifacts

collect-target-context

Stage Plan

skill] collect-target-context -> Collect baseline target context | inputs: targetName, artifactsRootDir | outputs: target.json, context.md | retry: retry_once
approval] baseline-preview -> Wait for human approval | outputs: approval.state | approval: baseline_review

Output Contract

target.json
context.md

Approval Gates

Human review before continuing beyond the baseline stage

Failure Policy

Keep the partial context output if the stage cannot finish in one pass

Want to see if understudy-ai/target-brief-baseline-stage 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.