Conciseness

The body is dense and Grida-specific, assumes competence (no explanation of ripgrep, YAML, or search basics), and every section carries non-obvious facts. It is not 5 because the opening paragraph largely restates the frontmatter description and the "Intentional seed" blockquote is meta-commentary that could be trimmed. It is well above 3 — there is no generic padding or explanation of concepts Claude already knows.

Actionability

Commands are copy-paste ready and cover the common cases: "rg PATTERN editor/grida-canvas packages", "rg PATTERN -g '!**/docs/_history/**'", and the docsearch invocations with a concrete script path (verified scripts/docsearch.py exists and supports exactly those subcommands). Concrete file anchors (supabase/migrations/, data/ai/facts.json) and staleness checks (draft: true, doc_tasks:, git log -1) leave no gaps.

Workflow Clarity

The process is discernible and validation checkpoints exist — name the surface, consult the authority table, "Disagreement → decide which wins _and why_ (git log -1 recency, what the running entrypoint imports, what tests assert)", and the draft/doc_tasks/git-log staleness checks before trusting a doc. It is not 5 because this sequence is implicit in section order rather than an explicit ordered workflow or checklist; it is above 3 because concrete checkpoints and decision guidance are present.

Progressive Disclosure

The ~80-line body is self-contained and well-sectioned (source of truth, dead-tree traps, docs grounding, related skills), with a single one-level, clearly-signaled script reference (scripts/docsearch.py, with usage shown inline) that exists in the bundle. There are no nested references and no inlined content that belongs in a separate file, fitting the self-contained-skill pattern.

Specificity

The description enumerates multiple concrete actions — "locate the authoritative source and reconcile sources that disagree (code vs doc, migration vs schema, memory vs current code, live vs archived)", "scoped ripgrep", and "the docs/tags.yml + docsearch.py index" — with coverage matching the skill's full scope. It is not 4 because there are no gaps: the closing enumeration mirrors every body capability, and there is no vague filler.

Completeness

It explicitly answers what ("Establish what is actually true and current for the surface you are about to change... locate the authoritative source and reconcile sources that disagree") and when ("Use before any grep/find/explore... when deciding which of several definitions is the real one, or when a doc or memory conflicts with the code") with concrete trigger phrases. Not 4: the when-clause is already explicit and specific rather than merely present.

Trigger Term Quality

Natural trigger phrases are present ("Use before any grep/find/explore of the codebase or docs", "when a doc or memory conflicts with the code", "deciding which of several definitions is the real one"), giving good keyword coverage. It is not 5 because common synonyms users might say ("search", "look up", "verify", "source of truth" as a plain phrase) are missing.

Distinctiveness Conflict Risk

The source-of-truth/reconciliation niche is clearly distinct from other skills and anchored by specific artifacts (tags.yml, docsearch.py). Not 5 because the trigger "before any grep/find/explore of the codebase" is broad and could overlap with generic exploration or research skills; not 3 because the niche and triggers are far more specific than a generic skill.