docs(team-leader): simplify worker name guidance

[RerankerGuo]

Summary

• replace defensive assignedTo warning blocks with a concise Matrix-localpart rule
• point DAG and Loop guidance at the same rule without duplicating examples
• simplify task-management Worker Name Canonicality while preserving hiclaw get workers / matrixUserID lookup guidance

Fixes #913.

Tests

• git diff --check
• rg -n "❌|mandatory before|Common mistake|Do NOT use CLI|strip prefixes|matrixUserID|assignedTo|assigned_to" manager/agent/team-leader-agent/skills/project-management/SKILL.md manager/agent/team-leader-agent/skills/project-management/references/dag-execution.md manager/agent/team-leader-agent/skills/task-management/SKILL.md

Temporary dependency

• This branch is temporarily stacked on test: make multi-worker bob setup deterministic #985 (78e9385), whose full CI passed all 10 integration matrices.
• Relative to test: make multi-worker bob setup deterministic #985, this PR retains only its original scoped changes; the shared test fix disappears from the diff after test: make multi-worker bob setup deterministic #985 merges.
• Fresh checks on 2d04f86d passed every build and all 10 integration matrices.

[github-actions]

📊 CI Metrics Report

Summary

Metric	Current	Baseline	Change
LLM Calls	120	81	+39 ↑ +48.1%
Input Tokens	3496914	2803871	+693043 ↑ +24.7%
Output Tokens	29836	16791	+13045 ↑ +77.7%
Total Tokens	3526750	2820662	+706088 ↑ +25.0%

By Role

Role	Metric	Current	Baseline	Change
🧠 Manager	LLM Calls	70	68	+2 ↑ +2.9%
	Input Tokens	2296785	2502214	-205429 ↓ -8.2%
	Output Tokens	11865	13725	-1860 ↓ -13.6%
	Total Tokens	2308650	2515939	-207289 ↓ -8.2%
🔧 Workers	LLM Calls	50	13	+37 ↑ +284.6%
	Input Tokens	1200129	301657	+898472 ↑ +297.8%
	Output Tokens	17971	3066	+14905 ↑ +486.1%
	Total Tokens	1218100	304723	+913377 ↑ +299.7%

Per-Test Breakdown

Test	Mgr Calls	Wkr Calls	Δ Calls	Mgr In	Wkr In	Mgr Out	Wkr Out	Δ Tokens	Trend
02-create-worker	6	0	-6 ↓ -50.0%	107245	0	511	0	-250866 ↓ -70.0%	✅ improved
03-assign-task	14	8	+7 ↑ +46.7%	358257	156535	1845	1029	+44010 ↑ +9.3%	⚠️ regressed
04-human-intervene	10	15	+12 ↑ +92.3%	237806	335059	1263	2597	+143727 ↑ +33.2%	⚠️ regressed
05-heartbeat	6	7	+6 ↑ +85.7%	178730	167347	1154	895	+72874 ↑ +26.5%	⚠️ regressed
06-multi-worker	34	20	+20 ↑ +58.8%	1414747	541188	7092	13450	+696343 ↑ +54.4%	⚠️ regressed

Trends

✅ 1 test(s) improved (fewer LLM calls)
⚠️ 4 test(s) regressed (more LLM calls)

---

Generated by HiClaw CI on 2026-07-13 15:51:38 UTC

---

📦 Download debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction / mgr=copaw / wk=hermes)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction / mgr=openclaw / wk=openclaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction / mgr=copaw / wk=copaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[RerankerGuo]

@shiyiyue1102 Hi! Both SHARD_A copaw/copaw and openclaw/openclaw failed. This is a docs-only PR (+14/-64 lines), so it's impossible for this change to affect runtime behavior — and the failures hit three different runtime combinations across multiple PRs (copaw/hermes on #984 / #972 / #973, copaw/copaw on #984, openclaw/openclaw on this PR), confirming a test infrastructure flake rather than any branch-local regression.

The SHARD_A test that's failing is test-06-multi-worker; on the #984 run I downloaded, Manager never invoked hiclaw create worker --name bob (no hiclaw-worker-bob session directory at all) — Manager only created alice. Could you re-run CI or merge this docs-only PR if you agree the flake is unrelated?

[github-actions]

❌ Integration Tests Failed (controller-cr / mgr=copaw / wk=copaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (controller-cr / mgr=copaw / wk=hermes)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (controller-cr-2 / mgr=copaw / wk=copaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction-2 / mgr=openclaw / wk=openclaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (controller-cr / mgr=openclaw / wk=openclaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction-2 / mgr=copaw / wk=copaw)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts

[github-actions]

❌ Integration Tests Failed (llm-interaction-2 / mgr=copaw / wk=hermes)

Commit: 316f831
Workflow run: #1651

Test Results

No test output captured.

Debug Log (tail)

No debug logs available.

---

📦 Download full debug logs & test artifacts