extract-learnings-to-issues
Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.
Best use case
extract-learnings-to-issues is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.
Teams using extract-learnings-to-issues should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/extract-learnings-to-issues/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How extract-learnings-to-issues Compares
| Feature / Agent | extract-learnings-to-issues | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Extract Learnings to Issues Convert unstructured user thoughts, reflections, and learnings into structured, actionable GitHub issue content that enhances existing issues rather than creating noise. ## When to Use - User shares random thoughts/workflow reflections and wants them "captured" - User says "put this into issues" or "filter this to repos" - Post-session learnings that should compound in the repo - User wants their reflections to "straighten the twisted brain" ## Pattern ### Phase 1: Distill Themes Parse the unstructured thoughts and extract core themes. Look for: - Problems/gaps identified - Insights about what works (secret sauce) - Proposed improvements or next steps - Metrics or evidence of problems - Connections to existing work ### Phase 2: Map to Existing Issues CRITICAL: Before creating any new issues, search the existing landscape: ```bash cd /mnt/local-analysis/workspace-hub # Search by label categories gh issue list --label cat:harness --state open --limit 10 gh issue list --label cat:platform --state open --limit 10 gh issue list --label domain:knowledge --state open --limit 10 # Search by keywords gh issue search "keyword1 OR keyword2" --state open --limit 10 # View key issues gh issue view $NUM 2>/dev/null ``` Map each distilled theme to the most relevant existing issue. ### Phase 3: Route as Comments (NOT New Issues) Write a body file and add as a comment to the existing issue: ```bash cat > /tmp/comment_$NUM.md << 'EOF' ## Context Update (date) [Distilled insight from user's reflection] [Specific additions to acceptance criteria] [Related issues to link] [Quotes from user for context] EOF gh issue comment $NUM --body-file /tmp/comment_$NUM.md ``` If no existing issue covers a theme, create a focused new issue with clear acceptance criteria and references. ### Phase 4: Close Any Unnecessary Issues If you created issues before realizing they're duplicates: ```bash gh issue comment $NUM --body "Closing as duplicate of #EXISTING - see context added there." gh issue close $NUM ``` ## Key Principles - ROUTE over CREATE: Always prefer enhancing existing issues - Quote the user: Preserve their exact words for context - Be specific: Add actionable acceptance criteria, not just commentary - Cross-link: Connect related issues explicitly - Minimize noise: The goal is signal, not issue proliferation
Related Skills
llm-wiki-source-extraction-coverage
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a reviewer can re-verify or revise against the actual document, (4) deciding whether OCR fallback or manual transcription is needed. Codifies workspace-hub's existing OCR fallback chain and python-docx / openpyxl / trafilatura patterns into a format-specific routing table. Companion to research/llm-wiki-page-shape-contract (Rule 7 input-layer pages) and research/llm-wiki — this skill is the defense against silent extraction failure.
sodir-data-extractor
Extract and process Norwegian Petroleum Directorate field and production data from SODIR
bsee-data-extractor
Extract and process BSEE (Bureau of Safety and Environmental Enforcement) data including production, WAR (Well Activity Reports), and APD (Application for Permit to Drill) data. Use for querying production data, well activities, drilling permits, completions, and workovers by API number, block, lease, or field with automatic data normalization and caching.
portable-baseline-pattern-extraction
Extract and separate portable baseline config from machine-specific overrides in multi-environment projects
extract-skills-from-hermes-sessions
Automatically analyze Codex session transcripts to identify and extract reusable skills using LLM analysis via OpenRouter
extract-skills-from-Codex-sessions
Automatically extract reusable skills from Codex session transcripts using LLM analysis and wire them into a Stop hook
extract-and-archive-tax-summary-data
Capture structured tax return summaries as YAML when PDF downloads are blocked or inaccessible
parallel-llm-wiki-gap-to-issues
Use parallel subagents to mine remaining LLM-wiki/document-intelligence gaps, de-duplicate against existing GitHub issues, then create only the strongest bounded follow-on issues.
llm-wiki-ecosystem-gap-to-issues
Review the workspace-hub LLM-wiki/document-intelligence ecosystem, identify high-leverage gaps, and create grounded GitHub feature issues without duplicating existing work.
github-visual-planning-issues
Create review-friendly GitHub planning issues that supersede stale/seasonal issues and include source-backed image thumbnails for faster human review.
github-issues
Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.
doc-extraction-naval-architecture
Layer 3 domain sub-skill for extracting naval architecture data from SNAME PNA, IMO stability codes, IACS structural rules, and classification society guidelines. Provides detection heuristics for stability constants, resistance equations, hull form coefficients, hydrostatic curves, IMO stability criteria, and structural scantling tables. type: reference