issue-finding-report

name	issue-finding-report
description	Use when converting accumulated prompt history, run bundles, hook logs, skill/tool/workflow routing evidence, eval summaries, or agent reports into durable AgentCanon skill issues; groups repeated evidence by abstract cause, shards multi-agent review by evidence partition, and writes issue candidates from structured dashboard artifacts.

Issue Finding Report

Tool Commands

Use the command packet before applying this skill's workflow:

python3 tools/agent_tools/skill_tool_commands.py show --skill issue-finding-report --format text

Execute the required and task-matching conditional commands that the packet prints.

1. Read agents/skills/issue-finding-report.md.

2. Generate or cite structured log evidence before reading event files:

   python3 tools/agent_tools/runtime_log_archive_git.py status --porcelain
   python3 tools/agent_tools/generate_agent_runtime_dashboard.py \
     --root . \
     --compact-out reports/agent-runtime-dashboard/agent-log-analysis-compact.md \
     --api-out reports/agent-runtime-dashboard/agent-log-analysis-api.json
   

3. Confirm the API exposes unknown_event_count, status_by_hook_family, failure_by_hook_family, skip_by_hook_family, namespace_debt_by_hook_family, and oop_applicability.

4. Build an Issue Finding Packet for each abstract cause cluster. Use the taxonomy in agents/skills/issue-finding-report.md; keep one primary cause per cluster and cite structured dashboard headings or API JSON paths.

5. For multi-agent review, shard by repo_key, hook_family, skill_name, workflow_name, tool_name, issue_id, or path scope. Give each subagent one packet, structured artifact paths, candidate affected surfaces, allowed issue paths, validation route, and return schema.

6. Search existing durable surfaces before writing a new issue:

   git grep -n "<cause keywords>" -- issues memory notes/failures documents agents
   

7. Expand candidate affected surfaces with dependency review and record the resulting dependency_edit_scope.txt path in the candidate issue.

8. Write issues/open/AC-YYYYMMDD-short-slug.md after deduplicating existing issues. Use the required fields from issues/README.md.

9. Validate issue and skill wiring:

   python3 tools/agent_tools/issue_sync.py --root .
   python3 tools/agent_tools/check_skill_frontmatter.py --root .
   python3 tools/agent_tools/skill_tool_commands.py check