pdf-brain-ingest
Ingest PDF/Markdown/TXT files into joelclaw's docs memory pipeline with Inngest durability, durable NAS artifacts, and OTEL verification. Use when adding docs, running batch reindex, reconciling coverage, or recovering stuck runs. Triggers on: 'ingest pdf', 'ingest markdown', 'docs add', 'pdf-brain ingest', 'backfill books', 'docs reconcile', 'reindex docs', 'batch reindex'.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope, lists concrete actions, and provides explicit trigger guidance. It names specific technologies and workflows that make it highly distinguishable. The explicit 'Triggers on' list with natural user phrases is particularly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: ingesting PDF/Markdown/TXT files, batch reindex, reconciling coverage, recovering stuck runs. Also names specific technologies (Inngest, NAS artifacts, OTEL verification). | 3 / 3 |
Completeness | Clearly answers both 'what' (ingest PDF/Markdown/TXT files into docs memory pipeline with specific technologies) and 'when' (explicit 'Use when...' clause plus a 'Triggers on' list with specific phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'ingest pdf', 'ingest markdown', 'docs add', 'pdf-brain ingest', 'backfill books', 'docs reconcile', 'reindex docs', 'batch reindex'. These cover multiple variations users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: it's specifically about joelclaw's docs memory pipeline with Inngest durability and OTEL verification. The trigger terms like 'pdf-brain ingest' and 'docs reconcile' are very specific and unlikely to conflict with generic document processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow clarity and concrete CLI commands for every operation. Its main weakness is including too much implementation detail (chunking strategy internals, embedding benchmarks, extraction accuracy stats) inline rather than in referenced files, which inflates token cost without improving Claude's ability to execute the workflows. The recovery and monitoring sections are particularly well done.
Suggestions
Move Chunking Strategy, Embedding Model comparison, and Extraction Details sections to a linked reference file (e.g., PIPELINE-INTERNALS.md) and keep only what's needed to execute commands in the main skill.
Remove implementation trivia like '~150x faster than Typesense CPU auto-embed', '0.90 accuracy', and 'arxiv R100-0 finding: 45% higher precision' that don't affect how Claude uses the commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code blocks and tables, but includes some unnecessary detail like embedding model benchmarks, chunking strategy internals (ADR-0234 findings), and extraction speed stats that Claude doesn't need to execute the workflow. The architecture diagram and artifact details are useful but could be tighter. | 2 / 3 |
Actionability | Highly actionable with concrete, copy-paste-ready CLI commands for every operation: single ingest, batch reindex, monitoring, artifact inspection, retrieval, reconciliation, and recovery. Every step has specific executable commands with real flags and paths. | 3 / 3 |
Workflow Clarity | Clear numbered sequence from preflight through recovery with explicit monitoring/verification steps (OTEL search, artifact counts, status checks). Recovery section addresses failure modes with concrete retry strategies, and the pipeline architecture clearly shows the 4-stage progression with resumability built in. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and headers, but it's a monolithic file that includes detailed chunking strategy, embedding model comparisons, extraction internals, and Inngest event tables that could be split into reference files. For its length (~130 lines of content), some sections like Chunking Strategy and Embedding Model details would be better as linked references. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
825972c
- Reviewed
Table of Contents
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.