panning-for-gold

Use when processing voice transcripts, brain dumps, stream-of-consciousness notes, or any raw multi-topic capture. Extracts every idea thread, then evaluates each one with deep brainstorming, then captures results to Open Brain. Trigger on transcripts, exports, "process this", "pan for gold", "brain dump", "what did I say", or multi-topic markdown files.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, actionable workflow with strong sequencing and validation, but it is let down by verbosity and repetition of the speaker-label lesson across multiple sections. Tightening the redundant prose would lift conciseness without losing signal.

Suggestions

Consolidate the speaker-label guidance: it appears as Phase 0.5 prose, a Lessons Log row, and Common Mistakes #9/#10 — keep one canonical telling and cross-reference it instead of restating.

Convert the Phase 0.5 'Speaker Label Audit' pseudocode block into a concrete runnable command or a precise numbered procedure so the only non-executable snippet becomes actionable.

Trim explanatory restatements like 'This is a data quality problem that must be solved before any analysis' that reiterate the preceding sentence without adding instruction.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but repeats the same speaker-label lesson across Phase 0.5's prose, the Lessons Log, and Common Mistakes #9/#10 (~4 tellings), and some sections explain at length rather than instruct, matching the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Provides copy-paste-ready templates (per-idea evaluation prompt), exact file-path conventions, and concrete agent config (model tiers, run_in_background); only the speaker-audit pseudocode block is non-executable, leaving minor gaps.	4 / 5
Workflow Clarity	A clear multi-phase sequence with a DOT diagram, explicit checkpoints (two-pass verification, the 'User confirms?' decision gate), and decision thresholds with feedback loops (re-extraction decision), matching the top anchor for sequenced validation.	5 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-structured file with clear section headers and tables. Structure is good, though Phase 0.5's length could arguably live in a separate reference file — a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it names concrete actions, gives a comprehensive set of natural trigger phrases, and cleanly separates what from when. It is specific, distinctive, and concise with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions — 'Extracts every idea thread, then evaluates each one with deep brainstorming, then captures results to Open Brain' — covering the full extract→evaluate→capture flow comprehensively.	5 / 5
Completeness	Explicitly answers both what (extract/evaluate/capture) and when ('Use when processing...', 'Trigger on...') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including quoted user phrases ('process this', 'pan for gold', 'brain dump', 'what did I say') alongside file-type terms and synonyms, all things a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	A clear niche — raw multi-topic brain-dump/transcript processing — with distinct triggers ('pan for gold', 'what did I say') that minimize overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NateBJones-Projects/OB1
Path: skills/panning-for-gold/SKILL.md
Commit: e79e9cb

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.