Ready to supercharge your AI agents?

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

PM Soul — measured AI agent skill | DecimalAI

agentlas-ai/pm-soul

SkillScore77Maintained

Use when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager continuity layer of an agent team.

agent-toolingby agentlas-ai

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

Automatic

Product Management pack

decimalai skills pull agentlas-ai-pm-soul

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agentlas-ai-pm-soul/SKILL.md

Raw file: /s/agentlas-ai-pm-soul/SKILL.md ↗ · machine-readable summary at /s/agentlas-ai-pm-soul.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

—0% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-39%	0%
case-07	✗→✓	▲ Improved	516%	0%
case-10	✗→✓	▲ Improved	425%	0%
case-11	✗→✓	▲ Improved	580%	0%
case-12	✗→✓	▲ Improved	356%	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

agentlas-ai / agentlas-os

skills/pm-soul/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

PM Soul

Procedure

Read .agentlas/project-soul-memory.md when present.
Extract user promise, target audience, current decision state, open loops,

and acceptance criteria.

Connect sitemap changes to product intent.
Emit ## Memory Events for durable updates instead of silently rewriting

shared memory.

Output

Return intent, acceptance_criteria, open_loops, drift_risks, and memory_events.

Want to see if agentlas-ai/pm-soul 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.