skills/review/SKILL.md
Assemble per-commit intent manifests into a review document. Launch the browser-based review UI for structured accept/reject per intent group. Falls back to LLM reconstruction when manifests are missing.
npx skillsauth add mjmorales/claude-prove reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read-only -- write ACB/review artifacts only; never modify project code. Respect .gitignore.
Base branch: Use $ARGUMENTS if provided, otherwise main. Verify with git rev-parse --verify <base>. Fall back to master, then halt.
Gather diff data (parallel):
git diff --stat <base>...HEAD
git diff --name-status <base>...HEAD
git log --oneline <base>..HEAD
git rev-parse <base>
git rev-parse HEAD
Edge cases: Empty diff -- inform and stop. Exclude binary and generated files (dist/, build/, lock files) from intent groups.
Check for manifests in the SQLite store:
PYTHONPATH="$PLUGIN_DIR" python3 -c "
from tools.acb.store import open_store
s = open_store('.')
branch = '$(git rev-parse --abbrev-ref HEAD)'
print(len(s.list_manifests(branch)))
s.close()
"
PYTHONPATH="$PLUGIN_DIR" python3 -m tools.acb assemble --base <base>
The ACB document is saved to the SQLite store (.prove/acb.db). If uncovered files remain, use Path B for those files and merge.
Reconstruct intent groups from the diff when no manifests exist or for uncovered files.
Grouping criteria (priority order):
Per intent group:
id: slug (e.g., auth-middleware), title: short nameclassification: explicit | inferred | speculativeambiguity_tags: from underspecified, conflicting_signals, assumption, scope_creep, conventiontask_grounding: one sentence connecting group to taskfile_refs: files with path, ranges, view_hintannotations: judgment_call, note, or flag entriesMark reconstructed groups with annotation: type note, body "Reconstructed post-hoc, not declared by the implementing agent."
Constraints:
Save the reconstructed ACB to the store:
PYTHONPATH="$PLUGIN_DIR" python3 -c "
import json
from tools.acb.store import open_store
s = open_store('.')
acb = json.load(open('.prove/reconstructed_acb.json'))
s.save_acb('$(git rev-parse --abbrev-ref HEAD)', acb)
s.close()
"
Build ACB with acb_version: "0.2", change_set_ref (base/head SHAs), task_statement, intent_groups, negative_space, open_questions, uncovered_files, generated_at (ISO), agent_id: "prove-review", manifest_count.
Construct task_statement.turns (role user) from:
.prove/PRD.md or .prove/TASK_PLAN.mdgit log <base>..HEADPYTHONPATH="$PLUGIN_DIR" python3 -m tools.acb serve --base <base>
Open the printed URL in the browser (open <url>). Tell the user the review is available. Review state auto-saves to the SQLite store.
Output after launch:
testing
Anchor session context into prove primitives before compaction and rehydrate from them after. Built-in compaction summarizes by recency and drops the claude-prove state an agent needs to reorient; this skill externalizes volatile context into durable anchors (scrum tasks, decisions, run-state, a compact-anchors pointer file) pre-compact, then runs a deterministic reorientation sequence post-compact. Use before a manual /compact, when context is about to auto-compact, or immediately after a compaction. Triggers on "smart compact", "prepare for compaction", "anchor before compact", "context is getting long", "rehydrate", "reorient after compact".
tools
Apply model-driven CONTENT reshaping to stored run artifacts that sit behind the current schema, on explicit operator invocation only. Triggers on "migrate runs", "migrate run artifacts", "run content migration", "reshape run artifacts", "bring runs to current schema". You are the driver: the `run-state migrate-runs` CLI mechanically detects which artifacts are behind and emits a plan naming each one plus its migration-instruction file; you read the instructions and reshape the prose/findings, gated by the operator. The deterministic `schema migrate` handles structural column moves; this skill covers only the content reshaping beyond them. Never run as a background or resident loop — only when the operator asks.
tools
Synthesize the 7-section risk-forward Review Brief from a run's reasoning log. Triggers on "reasoning brief", "review brief", "synthesize the brief", "generate the brief", "brief the run", "brief for review", "story brief". You are the driver: the `acb brief` CLI renders a mechanical preservation-safe backbone and proves preservation; you synthesize the narrative prose (summary + changes), single-pass or multipass over episode chunks, then gate it through Stage-1 (mechanical, blocking) and Stage-2 (prose judge, advisory).
tools
Prune stale cached versions of the prove plugin from Claude Code's plugin cache. Use when superseded versions pile up under plugins/cache and agents read stale skills/references from them, or when reclaiming plugin-cache disk space. Triggers on "clean up cached plugin versions", "prune the plugin cache", "remove old prove versions", "stale plugin cache".