Content Intelligence

Rules that go beyond structural validation to analyze the quality of instruction files. Built on attention research (lost-in-the-middle, instruction-following limits) and prompt engineering best practices. Most support LLM-powered fixes via skillsaw fix --llm. See the research page for the full research basis behind each rule.

Rule ID	Description	Default Severity	Autofix
content-weak-language	Detect hedging, vague, and non-actionable language in instruction files	warning (auto)	llm
content-tautological	Detect tautological instructions that the model already follows by default	warning (auto)	llm
content-critical-position	Detect critical instructions in the middle of files where LLM attention is lowest	info (auto)	llm
content-redundant-with-tooling	Detect instructions that duplicate .editorconfig, ESLint, Prettier, or tsconfig settings	warning (auto)	llm
content-instruction-budget	Check if instruction count in a file exceeds LLM instruction budget (~150)	warning (auto)	llm
content-negative-only	Detect prohibitions without a positive alternative (agent has no path forward)	info (auto)	llm
content-section-length	Warn about markdown sections longer than ~500 tokens	info (auto)	llm
content-contradiction	Detect likely contradictions within instruction files using keyword-pair heuristics	warning (auto)	llm
content-hook-candidate	Detect instructions that should be automated as hooks instead of prose instructions	info (auto)	llm
content-actionability-score	Score instruction files on actionability (verb density, commands, file references)	info (auto)	llm
content-cognitive-chunks	Check that instruction files are organized into cognitive chunks with headings	info (auto)	llm
content-embedded-secrets	Detect potential API keys, tokens, and passwords in instruction files	error (auto)	llm
content-banned-references	Detect banned or deprecated model names, APIs, and custom patterns	warning (auto)	llm
content-inconsistent-terminology	Detect inconsistent terminology across instruction files (e.g., mixing 'directory' and 'folder')	info (auto)	llm
content-broken-internal-reference	Detect markdown links where the target file does not exist	warning (auto)	auto
content-unlinked-internal-reference	Detect bare path-like strings not wrapped in markdown link syntax	info (auto)	auto
content-placeholder-text	Detect TODO markers, bracket placeholders, and unfilled template text	warning (auto)	-

content-critical-position parameters:

Parameter	Description	Default
min-lines	Minimum file length (in lines) before the rule activates	50

content-section-length parameters:

Parameter	Description	Default
max-tokens	Maximum estimated tokens per section before triggering a warning	500

content-banned-references parameters:

Parameter	Description	Default
banned	Additional banned patterns as list of {pattern, message} dicts	[]
skip-builtins	Disable built-in deprecated model/API checks	false

content-unlinked-internal-reference parameters:

Parameter	Description	Default
patterns	Glob patterns for path-like strings to flag when unlinked	["./**/*.*", "references/**/*.md"]