Conciseness

The body is dense with non-obvious domain facts (sample endpoint semantics, `slices`/`reaction_reference_count` interpretation, single-vs-multi-path key limits) and assumes Claude's competence, but a few passages could be trimmed: the `<skill-dir>` resolution digression (two install locations plus glob advice) and the reaction-reference shape explained twice (once under 'Read what the activity sample left out', again under 'Cover every feed group'). Fits the 4 anchor (efficient, minor instances that could be trimmed) rather than 5 (every token earns its place); it is well above 3, which requires unnecessary explanation of things Claude already knows.

Actionability

Fully executable guidance throughout: copy-paste bash blocks with exact commands ("python3 <skill-dir>/fetch_sample.py --out v3sync-sample.json", the `--feed` invocation), exact endpoint paths, concrete error-code meanings (401/403 = wrong secret or user token, 404 = endpoints unavailable), exact defaults ("comments already covers [\"comment\", \"reply\"]"), a worked output JSON example, and per-field decision rules. Matches the 5 anchor: copy-paste ready commands with specific examples covering the common cases.

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints: error-code interpretation after the fetch, empty-sample diagnosis (reactions prove activities exist), cross-checking the code inventory against the sample (agreement confirms, code-only is rare, sample-only asks the user), and a pre-finalize check of every emitted key against worked examples. Feedback loops are present (re-run the sample to firm up single-row decisions; a failed `--feed` is recorded and does not stop the run). The operation is read-only against v2, so the destructive/batch cap does not apply. Matches the 5 anchor (clear sequence, explicit validation, feedback loops, checklists).

Progressive Disclosure

The SKILL.md body is a well-signaled overview pointing one level deep to purpose-described references ("Read [mapping-keys.md] for the full key catalogue, defaults, exact resolution rules, and worked examples", code-inventory.md, porting-plan.md), each with clear guidance on when to load it. However, the bundle as provided contains no reference or script files — mapping-keys.md, code-inventory.md, porting-plan.md, fetch_sample.py, and scan_v2_calls.py are all referenced but absent from the file listing — so the navigation cannot be fully verified. Fits the 4 anchor (good structure, references mostly clear, minor organization gaps) rather than 5.

Specificity

Multiple specific concrete actions are stated: "Generate the v2 -> v3 sync mapping", "sampling its live v2 activities and reactions", "reading its write paths", and "plan how the app's code moves from v2 to v3" — comprehensive coverage of what the skill does. It matches the 5 anchor (multiple specific concrete actions) and clearly exceeds the 4 anchor, which implies coverage gaps; the three capabilities (sample, map, port plan) cover the skill's full scope.

Completeness

Explicitly answers both questions: the "what" (generate the v2->v3 sync mapping by sampling live data and, when available, reading integration code to also produce a porting plan) and the "when" ("Use when setting up a Feeds v2 to v3 migration, when asked to build, review, or debug a v3 sync mapping, when someone asks 'what mapping do we need for our app?'...") with concrete trigger phrases. Matches the 5 anchor exactly; the 4 anchor requires a weaker or less specific 'when', which does not apply.

Trigger Term Quality

Comprehensive natural-term coverage including synonyms: "v2 to v3", "feeds migration", "activity feeds migration", "sync mapping", "porting plan", plus symptom phrases a user would actually say ("missing text, missing attachments, comments that are not comments, or bookmarks that went missing") and jargon terms ("extra_context", "reaction kinds") that practitioners use. Not below 5 since no obvious synonym variation is missing for this domain.

Distinctiveness Conflict Risk

Clear niche (Stream Activity Feeds v2->v3 migration) with distinct triggers ("v3sync", "activity feeds migration", "v3 sync mapping") that would not fire for unrelated skills. It even scopes the porting aspect to "an app's v2 Feeds code", minimizing overlap with generic migration or porting skills. Matches the 5 anchor (clear niche, distinct triggers, minimal conflict risk).