From learning-agents
Creates kebab-case YAML issue files tracking problems observed in LearningAgent sessions from log folder paths and descriptions. Useful for real-time failure reporting via direct invocation or identify skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/learning-agents:report-issueThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create an issue file documenting a problem observed in a LearningAgent session.
Create an issue file documenting a problem observed in a LearningAgent session.
$0: Path to the session log folder (e.g., .deepwork/tmp/agent_sessions/<session_id>/<agent_id>/)$1: Brief description of the issue observedIf $0 is not provided or does not point to an existing directory, stop and output: "Error: session log folder path is required and must be an existing directory."
If $1 is not provided or is empty, stop and output: "Error: issue description is required."
From the issue description in $1, derive a short kebab-case name of 3-6 words maximum. Focus on the most distinctive noun and verb from the failure. Avoid filler words like "the", "a", "in", "with".
Examples:
wrong-retry-strategymissed-validation-edge-casehallucinated-api-endpointCreate the file at $0/<issue-name>.issue.yml with the following content:
status: identified
seen_at_timestamps:
- "<current ISO 8601 timestamp>"
issue_description: |
<Freeform text from $1 explaining what went wrong.
Focus on the PROBLEM, not the cause.
Be specific enough that someone can understand the failure
without seeing the transcript.>
Example of a completed issue file:
status: identified
seen_at_timestamps:
- "2026-02-17T14:32:00Z"
issue_description: |
The agent retried the tool call 5 times after receiving a 429 response,
but each retry was issued immediately with no backoff delay. All 5 calls
occurred within the same second.
The YAML block above is the authoritative template. See issue_yml_format.md for additional schema details.
Output a two-line confirmation:
Created: <path to the created issue file>
Recorded: <one-sentence summary of the issue>
investigation_report field — that is added during the investigate stepidentifiedissue_description factual and observable — describe symptoms, not root causesnpx claudepluginhub unsupervisedcom/deepwork --plugin learning-agentsInvestigates identified issues in LearningAgent sessions by analyzing transcripts, determining root causes like knowledge gaps or missing docs, and updating YAML issue files with reports.
Files structured GitHub bug reports for agent-validator by collecting runtime evidence (config, debug logs, execution state) and drafting issues. Useful when users encounter a suspected defect.
Captures verified solutions to non-obvious coding problems as categorized Markdown files with YAML frontmatter in .agents/lessons for fast lookup. Auto-triggers on phrases like 'it's fixed'; manual /report-fix.