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'.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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.

Highly actionable command reference with a clear sequenced workflow and recovery guidance, but it is a near-monolithic document that inlines internals and fails to point to its own reference file. Trimming machine-specific noise and splitting deep-dive material into the reference would lift the weaker dimensions.

Suggestions

Move the Chunking Strategy, Embedding Model, and Inngest Events detail into references/ files and link them from the body so the SKILL.md stays an overview.

Reference the existing references/operator-guide.md from the body (e.g., 'See operator-guide.md for end-to-end aa-book acquisition') rather than leaving it unlinked.

Cut version/benchmark/hardware noise ('#1 in benchmarks, 0.90 accuracy', 'arxiv R100-0 finding', 'M4 Pro', 'panda') unless it changes an operator's decision.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse commands and a table, but carries unnecessary justification (opendataloader benchmark claims, 'arxiv R100-0 finding: 45% higher precision') and time-sensitive machine-specific noise (versions, 'M4 Pro', 'panda') that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready joelclaw commands for every common case (add, reindex-v2, batch-reindex, monitor, inspect, search, context, reconcile, recovery), all fully executable.	5 / 5
Workflow Clarity	Nine workflow steps are clearly sequenced and the Recovery section plus monitoring/OTEL commands give validation checkpoints and a feedback loop for this batch operation, but per-step verification gates are scattered rather than explicit before each stage.	4 / 5
Progressive Disclosure	Section headers give decent structure, but deep-dive internals (chunking strategy, embedding model details, Inngest events table) are inlined and the existing references/operator-guide.md is never linked or signaled from the body.	3 / 5
	Total	15 / 20 Passed

Description

91%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.

A strong, third-person description that clearly states capabilities and explicit trigger phrases, distinguishing it via the joelclaw binding. Minor gaps in capability coverage and a few generic trigger terms keep it just below perfect.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (ingest PDF/Markdown/TXT, add docs, batch reindex, reconcile coverage, recover stuck runs) but omits capabilities present in the body such as search/retrieval, leaving minor gaps rather than full coverage.	4 / 5
Completeness	Explicitly answers both 'what' (ingest files into joelclaw's docs memory pipeline with Inngest durability, NAS artifacts, OTEL verification) and 'when' (Use when adding docs, batch reindex, reconciling, recovering) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides a comprehensive explicit trigger list with synonyms and phrasings a user would naturally say ('ingest pdf', 'ingest markdown', 'docs add', 'pdf-brain ingest', 'backfill books', 'docs reconcile', 'reindex docs', 'batch reindex').	5 / 5
Distinctiveness Conflict Risk	Bound to the specific 'joelclaw docs memory pipeline' with named events, giving it a clear niche, but generic phrasings like 'ingest markdown' and 'docs add' carry minor overlap risk with other doc skills.	4 / 5
	Total	18 / 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: joelhooks/joelclaw
Path: skills/pdf-brain-ingest/SKILL.md
Commit: 7094ced

Reviewed: 3 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.