Agent skill

Panning for Gold

by NateBJones-Projects in NateBJones-Projects/OB1

Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.

Custom licenceAuto-check passedAgent Workflows

Install Panning for Gold

skills CLI
$ npx skills add NateBJones-Projects/OB1 --skill panning-for-gold -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NateBJones-Projects/OB1 panning-for-gold --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NateBJones-Projects/OB1.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/panning-for-gold .claude/skills/panning-for-gold && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
panning-for-gold
GitHub stars
4.7k
Token cost
~5k tokens
SKILL.md length
2,214 words
Files
3
Skills in repo
24
Repo updated
First seen
Licence
Custom licence

At a glance

Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis.

  • Works in 7 steps: Save Raw Input → 5: Speaker Consolidation &… → Extract (Pan) → …
  • Processing a voice transcript that covers several topics
  • SKILL.md covers Overview, When to Use, Critical Rules (Learned from… and Process, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Raw, multi-topic capture such as voice transcripts, stream-of-consciousness notes and brain-dump exports becomes an evaluated list of ideas. The work has three phases: extract every thread without filtering, evaluate the highest-signal ones with deeper brainstorming, then synthesize a permanent gold-found file. Nothing is dismissed as noise on the first pass, because half-formed or personal remarks often hold the best ideas, and the raw input is saved to a file before any analysis. The description adds that results are captured to Open Brain.

Five rules come from past mistakes. Output from every phase is saved to files in the project's docs directory rather than left to agent memory. A summary file is used first, with the transcript read only for exact quotes and a completeness check. Background evaluator agents write their own evaluation files. The final synthesis is written by the main agent, not delegated. Transcripts get two extraction passes whose inventories are merged.

When your agent uses it

  • Processing a voice transcript that covers several topics
  • Mining a ChatGPT, Gemini or Claude brain-dump export for ideas
  • Turning stream-of-consciousness notes into an evaluated idea list
  • Answering what did I say in a long recording

Example prompts

  • “Pan for gold in this meeting transcript and save the inventory under docs/meetings.”
  • “Process this brain dump export and tell me which threads are worth pursuing.”
  • “What did I say in yesterday's voice note? Extract every idea thread.”

Requirements

  • A project docs directory where the inventory and evaluation files can be saved
  • Open Brain, if you want results captured there

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Save Raw Input
  2. 5: Speaker Consolidation & Identification (Multi-Speaker Transcripts Only)
  3. Extract (Pan)
  4. Evaluate (Brainstorm per Nugget)
  5. Synthesis
  6. 5: Capture to Open Brain
  7. Self-Improvement

What it can do on your machine

Read from SKILL.md and the folder at commit 238df6c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are dot and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Panning for Gold loads about 5k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 2,214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,214 words (~5,003 tokens).

“Transform raw brain dumps into evaluated, actionable idea inventories. Three phases: Extract every thread without filtering, Evaluate the highest-signal ones, then Synthesize into a permanent gold-found file.”

— opening of SKILL.md by NateBJones-Projects, Custom licence
name
panning-for-gold
author
Jared Irish
version
2.0.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files in skills/panning-for-gold of NateBJones-Projects/OB1.

  • SKILL.md
  • README.md
  • metadata.json

Open the folder on GitHubat commit 238df6c

Compare with similar skills

Panning for Gold next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Panning for Gold compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Panning for Gold this skillNateBJones-Projects/OB14.7k—~5kAutomated safety check: PassCustom licence
Video To Notelike-attract/video-to-note124—~1kAutomated safety check: PassMIT
YouTube Talk Notetakerdair-ai/dair-academy-plugins614—~2.3kAutomated safety check: PassMIT
Viral Short Form Ideasvyralcontent/content-skills1341 repos~2.9kAutomated safety check: PassMIT
Roundtable Debatelijigang/ljg-skills7.5k—~529Automated safety check: PassMIT
Ecosystemglebis/claude-skills391—~2.1kAutomated safety check: PassMIT

Similar skills

  • Video To Note

    like-attract/video-to-note

    Generate structured, timestamped Markdown notes from videos (Bilibili, Douyin, YouTube, or local media files) using the local VideoToNo service.

    124 GitHub stars~1k tokensUpdated 7 days ago
    Knowledge ManagementAuto-check passed
  • YouTube Talk Notetaker

    dair-ai/dair-academy-plugins

    Converts a YouTube talk into a markdown study note with slide images, a timestamped transcript and editable notes, browsable through a small local server.

    614 GitHub stars~2.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Viral Short Form Ideas

    vyralcontent/content-skills

    Generate short-form video ideas at volume and stop the blank-page problem for good.

    134 GitHub starsUsed in 1 repo~2.9k tokens
    Media & CreativeAuto-check passed
  • Roundtable Debate

    lijigang/ljg-skills

    Hosts a structured roundtable debate on one topic with 3 to 5 real people, an ASCII structure diagram each round, user-controlled pacing and a saved org-mode transcript.

    7.5k GitHub stars~529 tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed
  • Ecosystem

    glebis/claude-skills

    Audit the Claude Code ecosystem — skill health and staleness, project activity pulse, CLAUDE.md instruction drift, Mac Mini service status.

    391 GitHub stars~2.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Idea Refinement

    addyosmani/agent-skills

    Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.

    105k GitHub starsUsed in 6 repos~2k tokens
    Agent WorkflowsAuto-check passed

More from NateBJones-Projects/OB1

All 24 skills in this repo
  • Heavy File Ingestion

    NateBJones-Projects/OB1

    Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.

    4.7k GitHub stars~995 tokensUpdated 2 days ago
    Auto-check passed
  • Aiception Skill Extraction

    NateBJones-Projects/OB1

    Pulls reusable knowledge out of work sessions and turns it into new skills, checking existing notes and skills first to avoid duplicates.

    4.7k GitHub stars~2k tokensUpdated 2 days ago
    Auto-check: notes
  • Claude Code Auto-Capture Hook

    NateBJones-Projects/OB1

    Fires a Stop hook that captures a Claude Code session transcript automatically when the session ends without a verbal wrap-up.

    4.7k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check: notes
  • Open Brain Local HTTP

    NateBJones-Projects/OB1

    Captures and searches personal notes in a self-hosted Open Brain using plain curl calls over HTTP, for setups where MCP is disabled or blocked.

    4.7k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check: notes
  • Agentic Harness Design and Review

    NateBJones-Projects/OB1

    Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

    4.7k GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Weekly Signal Diff

    NateBJones-Projects/OB1

    Turns a noisy week of AI or software market news into a short list of structural changes, weighted by what the user already tracks in Open Brain memory.

    4.7k GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed

Questions about Panning for Gold

What does Panning for Gold do?

Processes voice transcripts and brain dumps in three phases, extracting every idea thread, evaluating the strongest and saving a permanent inventory and synthesis. Raw, multi-topic capture such as voice transcripts, stream-of-consciousness notes and brain-dump exports becomes an evaluated list of ideas. The work has three phases: extract every thread without filtering, evaluate the highest-signal ones with deeper brainstorming, then synthesize a permanent gold-found file.

When should I use Panning for Gold?

Panning for Gold fits situations like: processing a voice transcript that covers several topics; mining a ChatGPT, Gemini or Claude brain-dump export for ideas; turning stream-of-consciousness notes into an evaluated idea list; answering what did I say in a long recording.

How do I install Panning for Gold in Claude Code?

Run `npx skills add NateBJones-Projects/OB1 --skill panning-for-gold -a claude-code`. Or copy the skill folder (skills/panning-for-gold in NateBJones-Projects/OB1) into .claude/skills/panning-for-gold in your project. Claude Code loads it when a task matches its description.

How do I install Panning for Gold in Codex?

Run `npx skills add NateBJones-Projects/OB1 --skill panning-for-gold -a codex`. Or copy the skill folder (skills/panning-for-gold in NateBJones-Projects/OB1) into .agents/skills/panning-for-gold in your project. Codex loads it when a task matches its description.

Can I use Panning for Gold in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NateBJones-Projects/OB1 --skill panning-for-gold -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/panning-for-gold, .gemini/skills/panning-for-gold, .github/skills/panning-for-gold and .opencode/skills/panning-for-gold in your project.

What does Panning for Gold need to run?

SKILL.md names no scripts, command-line tools or credentials: Panning for Gold is instructions for the agent only. Our summary lists: A project docs directory where the inventory and evaluation files can be saved; Open Brain, if you want results captured there.

Does Panning for Gold access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Panning for Gold safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Panning for Gold use?

Panning for Gold has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Panning for Gold use?

About 5k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Panning for Gold?

Skills that share tags, products or a category with Panning for Gold: Video To Note (like-attract/video-to-note, 124 stars), YouTube Talk Notetaker (dair-ai/dair-academy-plugins, 614 stars), Viral Short Form Ideas (vyralcontent/content-skills, 134 stars) and Roundtable Debate (lijigang/ljg-skills, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Panning for Gold?

NateBJones-Projects (a GitHub organization) maintains it in NateBJones-Projects/OB1, which has 4,710 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

Source: NateBJones-Projects/OB1 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.