skills/comprehend/SKILL.md
Post-diff Socratic quiz that builds deep comprehension of agent-generated code. Analyzes recent changes, generates causal/design questions, quizzes the developer interactively, and logs comprehension gaps.
npx skillsauth add mjmorales/claude-prove comprehendInstall 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.
Generate 3-5 questions about a recent diff, quiz the developer interactively, and log comprehension gaps. Tone is collaborative, not evaluative. Max 5 questions (target 2-5 minutes).
$ARGUMENTS if provided (SHA, range, or path). Otherwise detect:
git diffgit diff HEAD~1git show HEADgit diff --stat on chosen scope. Empty diff -- inform and stop.Read the full diff and each changed file for surrounding context.
Generate 5 questions (drop to 3 if <3 functions or ~50 lines). Each targets one category:
| Category | Example | |----------|---------| | Causality | "What happens if this error handler is removed?" | | Design rationale | "Why was a Map used here instead of a plain object?" | | Data flow | "Where does this config value originate and what consumes it?" | | Edge cases | "What happens when this list is empty?" | | Integration | "How does this change affect existing callers?" |
Quality requirements:
Answer options per question: One correct answer, one plausible-but-wrong answer, "I'm not sure" (last). Randomize correct/wrong position.
For each question:
Present via AskUserQuestion: header "Q{n}/{total}", question prefixed with [Category], three options.
Respond:
Track: category, question, answer, correct/incorrect.
Score: X/{total}Skip if .prove/ directory does not exist.
AskUserQuestion (header "Log"):
If saving, write to .prove/learning/YYYY-MM-DD-<topic-slug>.md:
# Comprehension Log: <topic>
**Date**: YYYY-MM-DD
**Scope**: <diff description>
**Score**: X/{total}
**Rating**: Strong | Solid | Moderate | Needs Review
## Questions
### Q1: [Category] <question>
- **Answer**: <user's answer>
- **Correct**: Yes | No
- **Explanation**: <if wrong>
## Gaps
- <category>: <gap> -- re-read `<file>:<function>`
## Takeaway
<one sentence>
Inform user where the log was saved.
This skill does not modify project code. Delegate learning log commits to the commit skill.
tools
Clean and compact prove's durable memory layers — team Lore, the Codex (scrum decisions), annotations, and contributor artifacts — keeping the tribal knowledge that grows team accuracy and folding away the rot. Triggers on "janitor", "clean the lore", "compact the lore", "compact the codex", "memory cleanup", "clean up team memory", "prune stale decisions", "tidy tribal knowledge", "lore cleanup". You are the driver: the CLI emits inventories and executes writes; the `memory-janitor` agent judges each entry; a per-team batch gate approves; nothing is ever deleted — consolidation, promotion, and supersession only.
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).