Ready to supercharge your AI agents?

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

Sitemap Task Bias — measured AI agent skill | DecimalAI

agentlas-ai/sitemap-task-bias

NewSkillScoreMaintained

Use when creating or auditing an agent-team sitemap, Task Bias ledger, concept coverage, product surface map, validation chain, or missing-concept check.

agent-toolingby agentlas-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/agentlas-ai-sitemap-task-bias/SKILL.md

decimalai skills pull agentlas-ai-sitemap-task-bias --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/agentlas-ai-sitemap-task-bias/SKILL.md https://app.decimal.ai/s/agentlas-ai-sitemap-task-bias/SKILL.md

Raw file: /s/agentlas-ai-sitemap-task-bias/SKILL.md ↗ · machine-readable summary at /s/agentlas-ai-sitemap-task-bias.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 20h ago

—-21% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-34%	0%
case-03	✗→✓	▲ Improved	117%	0%
case-04	✗→✓	▲ Improved	-44%	0%
case-05	✗→✓	▲ Improved	-19%	0%
case-06	✗→✓	▲ Improved	-48%	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/sitemap-task-bias/SKILL.md

View on GitHub ↗

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

Skill contents

SKILL.md

Sitemap Task Bias

Procedure

List the user-facing surfaces, workflows, agent roles, skills, memory scopes,

runtime adapters, policy gates, and verification lanes.

Compare the request against required concept coverage:

sitemap;
PM Soul;
memory architecture;
all-LLM runtime architecture;
public/private boundary;
install and verification path.

Add task biases that protect the build from dropping important concerns.
Record skipped or blocked concepts in .agentlas/validation-ledger.jsonl.

Output

Return covered, missing, task_biases, and evidence_files.

Want to see if agentlas-ai/sitemap-task-bias 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.