fix(aidd-dev): review leaves out-of-diff phases and the verified percent undefined

Start with plugins/aidd-dev/skills/05-review/SKILL.md and actions/02-review-functional.md, then compare review-template.md and references/review-rubric.md against the stated scope. Update the Test section to cover out-of-scope phases, deterministic reruns, and percentage calculation. Done means the four acceptance scenarios pass and all four documents agree without contradiction.

Problem

05-review does not say what happens to plan phases outside the reviewed diff, nor how the verified percent is computed. Reviewing one phase of a multi-phase plan, three models on the same skill produced three incompatible review.md files.

The skill contradicts itself:

• SKILL.md:30 says review.md is overwritten each run: "a snapshot of the current diff, not a history".
• 02-review-functional.md:23 says the Phases section holds "one block per plan phase".
• Nothing says whether the previous review.md is read before writing.
• review-template.md:33 renders {{pct}}% ({{n_checked}}/{{n_total}}), but nothing says which phases enter n_total. not-applicable is only defined as "neither a finding nor a blocker" (review-rubric.md:19), never for the percent, and never when to use it.

Observed on a 7-phase plan, phase 4 reviewed in three worktrees, aidd-dev 2.4.1 (05-review is unchanged in 2.5.0):

• Mistral Medium and Qwen have word-for-word identical blocks for phases 1, 2, 3, 5, 6 and 7: both copied the previous review.md. Mistral's phase 2 still says "ajoutés par ce diff" while its own Files checked lists only phase-4 files. Copied evidence reads as fresh verification.
• GLM dropped the six other phases.
• Qwen tagged the 15 criteria of out-of-diff phases not-applicable, Mistral used the same tag for a partially verifiable phase-4 criterion: one tag, two meanings.

Scope

• review.md stays a snapshot: the skill never reads the previous review.md, and says so.
• Every run renders one block per plan phase, re-derived from the plan.
• A phase the diff does not touch keeps its block, marked out of scope in its heading, with its criteria unchecked and no evidence. Nothing is copied from an earlier review.
• A phase the diff touches is verified as today: [x] with evidence, or [ ] tagged fix, not-applicable or fixed.
• Define not-applicable: a criterion of a phase in scope that this change cannot satisfy by nature (for example, it depends on a later phase). It is never used to mark a phase out of scope.
• The verified percent counts only the criteria of phases in scope, minus not-applicable ones, and matches the boxes rendered.
• Update the Test section of 02-review-functional.md to check the four rules above.

Acceptance criteria

• Reviewing phase 4 of a 7-phase plan renders 7 phase blocks, 6 of them marked out of scope.
• An out-of-scope block holds no [x] and no file:line.
• Re-running the review on the same diff gives the same Phases and Verification, whatever the content of the previous review.md.
• With 6 criteria in scope, 5 checked and 1 not-applicable, the report shows 100% (5/5).
• SKILL.md, 02-review-functional.md, review-template.md and review-rubric.md agree on these rules, with no contradiction left.

Prior art in this repository

• SKILL.md:30: the snapshot rule, kept.
• 02-review-functional.md:17: "the percent and count of checked criteria", to make precise.
• review-rubric.md:19: the only definition of not-applicable, to extend.

Out of scope

• How "the diff against the repository default branch" resolves (5 occurrences in 05-review, never defined). A clone whose origin/HEAD points at a feature branch diffs against it. Separate issue.
• Enforcing review-validator.yml: a section outside the list survived in the three reviews above. Separate issue.

Reported on Discord: https://discord.com/channels/1173363373115723796/1547134531188822047