Conciseness

The body is dense with non-obvious, empirically derived caveats Claude would not know ("Numeric sample names are unsafe", "The helper uses a raw-count population Gini; MAGeCK's native count-summary Gini uses log(count + 1)", "MAGeCK 0.5.9.5 switches median normalization to total-count scaling for a zero median or more than 45% zero guides") and explains no basic concepts, matching 'Efficient; minor instances of over-explanation that could be trimmed'. Not 5: the synthetic-fixture evidence paragraph ("counts of 30 and 12 were recovered exactly... recovered 15, 7, and 0 reads") and parts of the report.json flag-semantics paragraph are provenance detail that could be trimmed or moved; not 3 because essentially all content is skill-specific knowledge rather than padding.

Actionability

Fully executable, copy-paste-ready commands: "mageck count -l library.tsv --fastq c1.fastq.gz ... --sample-label c1,c2,t1,t2 --trim-5 0 --norm-method none -n counts" and "python scripts/screen_analysis.py qc --counts counts.count.txt --library library.tsv --control c1 c2 --treatment t1 t2 --output qc.json", with exact input formats ("headerless TSV library containing guide ID, DNA sequence, gene"; header beginning "sgRNA, Gene"), exact flags and thresholds. Matches the anchor 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

Workflow Clarity

Seven clearly sequenced steps (design establishment → library validation → counting → QC → normalization → test → interpretation) with explicit validation checkpoints: "Verify both mageck --version and mageck test --help before an analysis", "Run QC before statistical testing", "Check the report's applied method, size factors, and warnings", and helper-enforced rejections (mismatched IDs, ambiguous sequences, reused results directories) with recovery guidance ("rename them before analysis", "resolve intentional multi-target guides explicitly upstream"). Matches the anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery' — no validation cap applies.

Progressive Disclosure

Structure is good: installation/runtime detail and multi-factor MLE design are split into real, clearly signaled one-level-deep files ("The tested source installation and external-runtime caveat are in [references/runtime.md](references/runtime.md)", "For a multi-factor design, see [references/design.md](references/design.md)") that exist in the bundle, and scripts/screen_analysis.py is present as referenced; neither reference nests further local files. Matches 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'. Not 5: the main body still inlines substantial detail that could live one level down (the test-fixture evidence paragraph, the deep report.json flag-semantics and RRA-null discussion); not 3 because the core overview plus targeted offload pattern is clearly present and navigable.

Specificity

Quotes: "Analyzes pooled CRISPR screen FASTQ reads and guide-count matrices with MAGeCK, validates guide libraries and contrasts, measures replicate and library QC, and produces gene hit rankings with effect sizes and FDR." Five distinct concrete actions cover the full count-to-ranking workflow comprehensively, matching the anchor 'Lists multiple specific concrete actions; comprehensive coverage'. Not 4: coverage is complete rather than having minor gaps. Third person voice throughout ('Analyzes', 'validates', 'measures', 'produces'), so no voice penalty applies.

Completeness

The 'what' is explicit and concrete (analyze FASTQ reads and count matrices with MAGeCK, validate libraries/contrasts, measure QC, produce gene rankings with effect sizes and FDR), and the 'when' is explicit: "Use for new knockout, CRISPRi, or CRISPRa screen analysis, enrichment or depletion contrasts, and MAGeCK count/test workflows." This matches the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'. Not 4: the 'when' clause is not merely adequate but enumerates concrete trigger scenarios and adds a boundary ('existing public dependency-score lookup belongs to DepMap').

Trigger Term Quality

Quotes: "pooled CRISPR screen FASTQ reads", "knockout, CRISPRi, or CRISPRa", "enrichment or depletion contrasts", "MAGeCK count/test workflows" — strong natural phrasing a screen analyst would actually say. Not 5: a few natural synonyms and variations are missing (e.g., 'sgRNA', 'guide library screen', 'viability screen', .fastq extensions); not 3 because keyword coverage is broad and domain-accurate rather than partial.

Distinctiveness Conflict Risk

Clear niche: pooled CRISPR screen analysis with MAGeCK, with triggers ('MAGeCK count/test workflows', 'CRISPRi', 'CRISPRa') unlikely to fire unrelated skills, plus an explicit disambiguation: "existing public dependency-score lookup belongs to DepMap." Matches the anchor 'Clear niche with distinct triggers; minimal conflict risk'. Not 4: no meaningful overlap with closely related skills is left unaddressed.