agent-issue-delegation
Crear GitHub Issues de calidad profesional para delegar a agentes autónomos (Jules, Claude Code, Codex, OpenCode).
Skill by iberi22
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/iberi22-agent-issue-delegation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-issue-delegation
What's inside
- Skill name
agent-issue-delegation- Description
- Crear GitHub Issues de calidad profesional para delegar a agentes autónomos (Jules, Claude Code, Codex, OpenCode). Template con Current State medible, Anti-Hallucination Guard, Acceptance Criteria verificables, y pre-flight validation. Previene issues con body vacío, paths incorrectos, y ACs no verificables.
- License
- MIT
- Instructions
- 349 lines in SKILL.md · view on GitHub
Files (9)
- SKILL.md
- batch-pr-integration.md · references/
- dart-commands.md · references/
- label-refresh-and-pr-noise.md · references/
- ola6-incidentes-referencia.md · references/
- ola8-wave1-results.md · references/
- session-failure-patterns.md · references/
- wave10-validated-template.md · references/
- xavier-980-template.md · references/
SKILL.md (first lines)
# Agent Issue Delegation — Professional Issue Templates
> ⚠️ **CANONICAL TEMPLATE:** `gitcore-jules-issues` v3.0+ (unifica 6 skills previos, Jul 2026).
> Este skill contiene **reglas generales de delegación** válidas para cualquier agente.
> Para el template section-by-section exacto, cargar `gitcore-jules-issues`.
> ⚠️ **Rule:** Label `jules` triggers Jules. For other agents use their convention.
>
> ⚠️ **Language:** Issues, documentation, and code examples MUST be in English. Only user-facing conversation may be in the user's language. When the user writes in Spanish, respond in Spanish but keep code comments, issue bodies, documentation, and PR descriptions in English.
>
> ⚠️ **Wave Size = 14-15 issues:** Jules takes issues with the `jules` label up to ~14-15 simultaneously. Create waves of exactly 14-15 with disjoint file islands.
> - Less than 10 wastes parallel capacity
> - More than 16 becomes unmanageable for review/merge
> - Issue #15 = reconciliation (features.json update) — ALWAYS last
> - Each issue = single action. 1 issue = 1 file = 1 change. Multi-feature issues fail 100%.
>
> ⚠️ **features.json NOT modified during the wave.** Each issue writes progress to `.gitcore/ola8-progress/<feature-id>.json` (individual file). The reconciliation issue at wave end unifies all into features.json.
>
> ⚠️ **Single Action = Success:** Single-action issues (verify + update progress file) have ~70% success rate. Multi-feature issues have 0%. Always split.
>
> ⚠️ **Delivery binding:** Every issue delegated to an agent MUST result in committed+push to GitHub. Local-only changes are not a valid delivery.
>
> ⚠️ **Repo boundary:** Xavier (Rust) and isar_agent_memory (Dart) are separate repos. Do not cross-contaminate issues. They communicate via MCP/HTTP only.
## ⚠️ MANDATORY RULES FOR EVERY ISSUE
### 🔍 Web Research Required (MANDATORY — in EVERY issue)
⚠️ **The user WILL correct you if this section is missing. Always include it.**
Every issue MUST contain a Web Research Required section. This is non-negotiable.
The agent must research the most current approaches BEFORE implementing. Without this section, the agent implements with potentially outdated knowledge.
Include **3-4 specific, searchable queries**:
```markdown
## Web Research Required
1. `search: "[primary technology] best practices 2026"`
2. `search: "[alternative library/pattern] comparison"`
3. `search: "[crate/package] documentation latest API"`
4. `search: "[algorithm/approach] modern implementation"`
```
Failure to include this section = issue is INCOMPLETE. Do not delegate without it. Use `gitcore-jules-issues` skill for the exact template.
### ✅ Tests + Lint (MANDATORY)
**Every delivery MUST include:**
- Tests validating the functionality (unit + integration where applicable)
- Lint passes with 0 errors (use correct command per stack):
- **Rust:** `cargo clippy -p xavier --all-targets -- -D warnings`
- **Dart/Flutter:** `dart analyze lib/`
- If the agent cannot pass lint, document why in the PR
Without tests + green lint → the PR will NOT be merged.
### 📍 Documentation Language (MANDATORY)
All code comments, variable names, issue bodies, PR descriptions, README, docs, and commit messages MUST be in English. Only user-facing conversation may be in the user's language (e.g. Spanish when the user writes in Spanish). When in doubt, write in English.
### 🧱 Repo Boundaries (MANDATORY)
Before creating any issue, confirm the feature belongs to THIS repo:
- **Xavier** (`iberi22/xavier`) = Rust memory server — MCP/HTTP interface, mesh sync, security
- **isar_agent_memory** (`iberi22/isar_agent_memory`) = Dart/Flutter memory engine — offline-first, mobile/edge
- They communicate via MCP/HTTP only. Never create Xavier features in isar_agent_memory or vice versa.
### Delivery Requirements
**Every issue delegated to an agent MUST result in committed+push to GitHub.** Local-only changes are not a valid delivery — the repo on GitHub is the single source of truth.
**Documentation and code MUST be in English.** Only user-facing conversation may be in the user's language. Issue bodies, code comments, variable names, PR descriptions, API docs — all English.
**Xavier integration is via MCP only.** Never couple code between Xavier (Rust) and isar_agent_memory (Dart). They are separate repos that communicate through MCP/HTTP.
### Post-Creation QA Audit
After creating ALL issues in a wave, run verification BEFORE applying any `jules` label:
```bash
# 1. Check body length (empty body = wasted session)
for n in $(gh issue list --repo <repo> --label wave-N --state open --json number --jq '.[].number'); do
body=$(gh issue view $n --repo <repo> --json body --jq '.body | length')
title=$(gh issue view $n --repo <repo> --json title --jq .title)
if [ "$body" -lt 50 ]; then
echo "❌ #$n EMPTY BODY ($body chars): $title"
elif [ "$body" -lt 200 ]; then
echo "⚠️ #$n SHORT BODY ($body chars): $title"
else
echo "✅ #$n ($body chars)"
fi
done
# 2. Check Web Research Required section exists
for n in $(gh issue list --repo <repo> --label wave-N --state open --json number --jq '.[].number'); do
body=$(gh issue view $n --repo <repo> --json body --jq .body)
if echo "$body" | grep -q "Web Research"; then
echo "✅ #$n has Web Research"
else
echo "❌ #$n MISSING Web Research Required — FIX BEFORE DELEGATING"
fi
done
# 3. Check Acceptance Criteria and Failure Recovery
for n in $(gh issue list --repo <repo> --label wave-N --state open --json number --jq '.[].number'); do
body=$(gh issue view $n --repo <repo> --json body --jq .body)
has_ac=$(echo "$body" | grep -c "Acceptance Criteria")
has_fr=$(echo "$body" | grep -c "Failure Recovery")
echo "#$n: AC=$has_ac FR=$has_fr"
done
# 4. Verify file islands are disjoint
python3 -c "
issues = {}
for n in [LIST_OF_ISSUE_NUMBERS]:
# Extract Files to Modify from each issue
issues[f'#{n}'] = ['path1.rs', 'path2.rs'] # fill from issue bodies
for i1, f1 in issues.items():
for i2, f2 in issues.items():
if i1 < i2 and set(f1) & set(f2):
print(f'❌ CONFLICT: {i1} and {i2} share files!')From iberi22/skills, MIT.
More from iberi22/skills
- 0.567score
linux-performance-profiles
iberi22
Switchable Linux system performance profiles (gaming, sen/headless work, default) via sysfs/sysctl/Hyprland.
SkillAFreshness: AClaude Code +9 - 0.566score
cron-fleet-maintenance
iberi22
Use when auditing or repairing a fleet of cron jobs.
SkillAFreshness: AClaude Code +9 - 0.565score
issue-triage
iberi22
Use when moving issues or external PRs through the issue tracker's triage state machine (needs-triage, ready-for-agent, wontfix).
SkillAFreshness: AClaude Code +9 - 0.565score
bug-triage
iberi22
Use when diagnosing a bug in code.
SkillAFreshness: AClaude Code +9 - 0.561score
jules-recovery-protocol
iberi22
Protocolo de recuperación para Jules cuando falla una sesión.
SkillAFreshness: AClaude Code +9 - 0.561score
swal-theme-creator
iberi22
Allows AI agents (Hermes, Antigravity, Jules) to generate, validate, and switch visual themes in SWAL Desktop using declarative JSON tokens.
SkillAFreshness: AClaude Code +9 - 0.560score
cpanel-node-ops
iberi22
Use when deploying Node backends on cPanel hosting.
SkillAFreshness: AClaude Code +9 - 0.560score
rclone-cloud-backup
iberi22
Use when auditing a running rclone cloud sync job.
SkillAFreshness: AClaude Code +9 - 0.557score
hermes-gateway-troubleshooting
iberi22
Debug Hermes Gateway connectivity and platform integration issues — Telegram, Discord, WhatsApp.
SkillAFreshness: AClaude Code +9 - 0.556score
background-transfer-monitor
iberi22
Use when running long background uploads: track progress.
SkillAFreshness: AClaude Code +9 - 0.521score
caveman
iberi22
Ultra-compressed communication mode para coding agents.
SkillBFreshness: BClaude Code +9 - 0.521score
claude-design-principles
iberi22
Principios de diseño UI/UX distillados del system prompt de Claude Design.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 3
- Last commit (this folder)
- Oct 8, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/iberi22/skills
- Website
- github.com/iberi22/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from iberi22
- 0.567score
linux-performance-profiles
iberi22
Switchable Linux system performance profiles (gaming, sen/headless work, default) via sysfs/sysctl/Hyprland.
SkillAFreshness: AClaude Code +9 - 0.566score
cron-fleet-maintenance
iberi22
Use when auditing or repairing a fleet of cron jobs.
SkillAFreshness: AClaude Code +9 - 0.565score
issue-triage
iberi22
Use when moving issues or external PRs through the issue tracker's triage state machine (needs-triage, ready-for-agent, wontfix).
SkillAFreshness: AClaude Code +9 - 0.565score
bug-triage
iberi22
Use when diagnosing a bug in code.
SkillAFreshness: AClaude Code +9 - 0.561score
jules-recovery-protocol
iberi22
Protocolo de recuperación para Jules cuando falla una sesión.
SkillAFreshness: AClaude Code +9 - 0.561score
swal-theme-creator
iberi22
Allows AI agents (Hermes, Antigravity, Jules) to generate, validate, and switch visual themes in SWAL Desktop using declarative JSON tokens.
SkillAFreshness: AClaude Code +9
Cite this page
agent-issue-delegation skill. Agent Mart. https://agentmart.dev/skills/iberi22-agent-issue-delegation (last updated 2026-10-24)