source-command-learn-extended

Extract learnings from the current session and convert them to actionable repo content. Phase 4 of #1760.

5 stars

Best use case

source-command-learn-extended is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Extract learnings from the current session and convert them to actionable repo content. Phase 4 of #1760.

Teams using source-command-learn-extended 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

$curl -o ~/.claude/skills/source-command-learn-extended/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/source-command-learn-extended/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/source-command-learn-extended/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How source-command-learn-extended Compares

Feature / Agentsource-command-learn-extendedStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Extract learnings from the current session and convert them to actionable repo content. Phase 4 of #1760.

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

# source-command-learn-extended

Use this skill when the user asks to run the migrated source command `learn-extended`.

## Command Template

Run the learning extraction pipeline on recent sessions:

```bash
cd $(git rev-parse --show-toplevel 2>/dev/null || echo /mnt/local-analysis/workspace-hub)
bash scripts/learnings/extract-learnings.sh HEAD
```

Then present results to the user:
1. Show any patterns detected (repeated bugs, TDD gaps, skill updates)
2. Show any auto-generated issue recommendations
3. Ask: "Create these issues? [y/n] or edit first?"

Related Skills

llm-wiki-source-extraction-coverage

5
from vamseeachanta/workspace-hub

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.

worldenergydata-source-readiness

5
from vamseeachanta/workspace-hub

Route agents to the canonical worldenergydata source-readiness skill and summary script. Use when asked for worldenergydata data completeness, data locations, latest known data dates, scheduler freshness, source-readiness status, or acceptance-criteria inputs across the repo ecosystem.

multi-source-tax-document-reconciliation

5
from vamseeachanta/workspace-hub

Verify generated tax forms against source documents by line-by-line comparison, not just totals

learned-git-worktree-hook-path-and-real-hook-shape-review

5
from vamseeachanta/workspace-hub

Catch hook-installation and governance bugs that only appear in linked git worktrees or against the real generated hook shape, not simplified test fixtures.

source-command-gsd-workstreams

5
from vamseeachanta/workspace-hub

Manage parallel workstreams — list, create, switch, status, progress, complete, and resume

source-command-gsd-review-backlog

5
from vamseeachanta/workspace-hub

Review and promote backlog items to active milestone

source-command-gsd-join-discord

5
from vamseeachanta/workspace-hub

Join the GSD Discord community

source-command-gsd-from-gsd2

5
from vamseeachanta/workspace-hub

Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format

source-command-compound-extended

5
from vamseeachanta/workspace-hub

Run cross-agent memory bridge. Sync learnings between machine agents, update shared knowledge. Phase 5 of #1760.

github-issue-label-audit-and-command-bundles

5
from vamseeachanta/workspace-hub

Safely turn drafted issue bodies into reusable gh issue create commands by auditing repo labels, exact duplicates, and auth first.

extract-learnings-to-issues

5
from vamseeachanta/workspace-hub

Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.

agent-learnings-portability

5
from vamseeachanta/workspace-hub

Git-track AI agent learnings so they survive machine loss — memory snapshots, corrections, patterns, insights across Codex, Hermes, Codex, and Gemini.