book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's life, NOT a therapist assigning homework. The reader decides what to do about it. Layout is a top-aligned HTML table or stacked sections, never a bare markdown pipe table (pipe tables center-misalign uneven columns). Output is a single brain page at media/books/<slug>-personalized.md plus an optional PDF via brain-pdf.

Quality

83%

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

81%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 highly actionable with executable code, a clearly sequenced multi-stage workflow, and strong validation/feedback checkpoints including an eval→fix→re-eval loop. Its main weakness is conciseness — several core rules (observe-don't-prescribe, consultant-mode, pipe-table layout) are restated across multiple sections, adding tokens without new information.

Suggestions

Consolidate the repeated OBSERVE-never-PRESCRIBE / consultant-mode / no-action-items guidance into a single authoritative section and reference it from the others to cut redundant tokens.

Move the dense anti-repetition constraint details (domain mapping, phrase caps, emotional-range math) and the cross-modal eval dimension definitions into reference files under references/ to improve progressive disclosure and reduce SKILL.md length.

Trim the duplicated pipe-table layout warning — it appears in the description, the layout hard rule, the anti-patterns list, and the output checklist; stating it once authoritatively is enough.

Dimension	Reasoning	Score
Conciseness	The body is thorough and mostly efficient, but several sections restate the same rules multiple times — the OBSERVE-never-PRESCRIBE point, the consultant-mode prohibition, and the pipe-table layout rule each appear across 'Quality system', 'Quality bar', 'Anti-patterns', and 'Output checklist' — which is notable repetition that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash and python snippets for EPUB extraction, PDF splitting, context-pack assembly, the gbrain invocation, and the eval gate, covering the common cases with concrete flags and values.	5 / 5
Workflow Clarity	The six-stage pipeline is explicitly sequenced (ACQUIRE→EXTRACT→CONTEXT→ANALYZE→ASSEMBLE→PDF) with validation checkpoints (word-count quality check, fact-check pass, eval gate with rebuild loop, output checklist) and idempotent retry feedback for failed chapters.	5 / 5
Progressive Disclosure	Structure is well-organized with clear section headers and one-level-deep references to related skills and conventions, but no bundle files exist in references/scripts/assets and some dense reference material (domain maps, phrase caps, eval dimensions) is inlined rather than split into separate files.	4 / 5
	Total	17 / 20 Passed

Description

86%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 specific, distinctive, and rich with natural trigger terms, clearly conveying the unique mirror-based book analysis value proposition. Its main weakness is that the 'when to use' guidance lives in a separate triggers block rather than an inline 'Use when...' clause, slightly weakening the completeness anchor.

Suggestions

Add an inline 'Use when...' sentence to the description prose (e.g. 'Use when the user wants a book personalized to their own life rather than a flat summary.') so the 'when' is explicit without relying on the separate triggers block.

Tighten the layout note about HTML tables vs pipe tables — it is valuable guidance but arguably belongs in the body, not the frontmatter description.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'produce a personalized chapter-by-chapter analysis', 'preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror)', 'render via brain-pdf' — with minor gaps in listing every sub-action.	4 / 5
Completeness	Clearly states what the skill does and includes explicit 'when' guidance via the triggers list, but the description prose itself relies on the separate triggers block rather than an inline 'Use when...' clause, making the 'when' slightly less explicit.	4 / 5
Trigger Term Quality	Includes comprehensive natural trigger phrases such as 'mirror this book', 'personalized version of this book', 'apply this book to my life', and 'how does this book apply to me' that a user would plausibly say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — personalized chapter-by-chapter book analysis with a mirror metaphor — with distinct triggers unlikely to fire for adjacent skills like strategic-reading or article-enrichment.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (601 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 suspicious	Warning

	Total	13 / 16 Passed

Repository: garrytan/gbrain
Path: skills/book-mirror/SKILL.md
Commit: 055ac6c

Reviewed: 2 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.