Conciseness

At roughly 30 lines, every section (Outcome, When to use, Workflow, Notes) earns its place with no padding and no explanation of concepts Claude already knows — even the Notes (node PATH fallback, track-does-not-change-stage caveat) are load-bearing, matching anchor 5.

Actionability

The commands are copy-paste ready ("node scripts/edit-thread.mjs --list", "--match \"<id-or-title>\" --track") with the --match uniqueness constraint and the --stage/--note options stated explicitly, covering the discovery and common cases per anchor 5 rather than the minor-gaps level of anchor 4.

Workflow Clarity

The four-step sequence is clear and step 1 (--list) plus the "must match exactly one thread" constraint act as pre-mutation checkpoints, but there is no post-change verification step (e.g., re-listing to confirm the thread shows track/manual_tracking), which is the minor validation gap of anchor 4 rather than the explicit feedback loops of anchor 5. The cap-at-3 rule for destructive/batch operations does not apply since this is a single-record, reversible flag change.

Progressive Disclosure

The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ bundle exists), and its sections are clearly organized with one-level, clearly signaled pointers to "skills/thread-state" — per the simple-skill scoring note this earns a 5.

Specificity

"Force an AI work thread to be actively tracked on the thread registry/board" names a concrete action against concrete artifacts (registry/board, Funnel / Triage, wait-for-threshold), but the skill exposes only this single capability with no mention of its options (--stage, --note), leaving minor gaps in coverage rather than the comprehensive multi-action coverage of anchor 5.

Completeness

It explicitly answers both: what ("Force an AI work thread to be actively tracked on the thread registry/board even if the auto-classifier left it in Funnel / Triage or marked it wait-for-threshold") and when ("Use when a session matters but did not trip the automatic tracking heuristics"), with the when-clause tied to a concrete failure mode — matching anchor 5 rather than anchor 4, where the when would be less explicit.

Trigger Term Quality

Terms like "actively tracked", "thread registry", "board", "Funnel / Triage", and "wait-for-threshold" echo the exact states a user of this system would see, giving good coverage; however, more natural user phrasings such as "put this thread on the board" or "pin this thread" are missing, so it falls short of the comprehensive synonym coverage of anchor 5.

Distinctiveness Conflict Risk

The niche (manual tracking override for a thread registry) is distinct with system-specific triggers, but the trigger space (thread, board, registry, Funnel / Triage) is shared with the sibling skill "thread-state", creating minor overlap risk with a closely related skill — anchor 4 rather than 5.