メニュー
Review public-facing prose for formulaic AI writing patterns without changing technical meaning. Skip source code and precision-first technical artifacts unless the user explicitly asks for a prose pass.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run a five-axis panel review of a completed change — code style, architecture, spec conformance, security, testing — with parallel specialist reviewers, adversarial verification of major findings, and a self-contained fix report written to .boris/reviews/. Invoke on "panel review", "full review", "review this across all axes", or when a substantial unit of work needs a thorough pre-merge check. Skip for small plan-step reviews — spawn the code-reviewer agent directly. Skip for a single-axis check — the narrower built-in (/security-review, /code-review) is cheaper; panel-review is for all five axes plus the refactoring track, the kill step, and a durable report. Work built THIS session is fine to panel-review; /adversarial-review is the lighter single-reviewer check for work that doesn't warrant five axes.
Consolidation pass over this project's native Claude memory store ($CLAUDE_CONFIG_DIR/projects/<slug>/memory/, default ~/.claude/…): merges duplicate notes, resolves contradictions, prunes stale entries, repairs [[wikilinks]], and rebuilds the MEMORY.md index. Invoke when the store has grown noisy or repetitive, or for periodic cleanup: "dream", "consolidate memory", "clean up project memory". Not for authoring new memories or improving skills/rules — that's kaizen.
Independent, unprimed review of work you produced THIS session — the brief withholds your conclusions so the reviewer reaches its own verdict; findings are relayed in its words. Invoke on "adversarial review", "red-team this", "unbiased second opinion on what I just did". For code you did NOT write (PR review, external audit) → /review or /code-review instead.
Pick up an implementation plan written by /plan (or any .boris/plans/*.md plan) and execute it faithfully in a fresh session. Invoke when the user points at a plan file and wants it built — "build @.boris/plans/...", "implement this plan", "resume", "pick up where we left off". Takes the plan path as an argument; if none is given, list the plan files in .boris/plans/ (those without a -spec/-options/-grilled/-diagnosis suffix) and ask which one.
Investigate a bug or unexpected behavior down to a confirmed root cause. Invoke at the START of looking into a failure, before the cause is known: "debug this", "why is this failing", "investigate this bug". Confirms the cause but lands no fix (/plan → /build) and writes no durable report (/diagnose, run after). Dumping in-flight state to a fresh session → /handoff.
Write a read-only diagnosis report — root cause, rules broken, five-whys — to a durable file once this session's investigation has concluded (cause confirmed, or leads exhausted and best hypothesis recorded). Invoke on "diagnose this", "root-cause report", "document what went wrong". Proposes NO fixes — that's /plan, run later off the report. Fix approach already settled → /plan; cause still under investigation → /debug; pausing that investigation → /handoff.
| name | stop-slop |
| description | Review public-facing prose for formulaic AI writing patterns without changing technical meaning. Skip source code and precision-first technical artifacts unless the user explicitly asks for a prose pass. |
| metadata | {"trigger":"Writing prose, editing drafts, reviewing content for AI patterns","author":"Hardik Pandya (https://hvpandya.com)"} |
Remove formulaic AI writing patterns from public-facing prose. Technical accuracy, logical qualification, project terminology, and the author's voice outrank every pattern below. Treat patterns as review signals, not bans.
Cut filler phrases. Remove throat-clearing openers and emphasis crutches. Keep adverbs that carry necessary degree, timing, or uncertainty. See references/phrases.md.
Break formulaic structures. Rewrite repeated binary contrasts, negative listings, dramatic fragments, rhetorical setups, and false agency when they are mannerisms rather than the clearest logic. See references/structures.md.
Prefer active voice. Use passive voice when the actor is unknown, irrelevant, or deliberately de-emphasized. Do not force a human subject into technical statements.
Be specific. No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work.
Put the reader in the room. No narrator-from-a-distance voice. "You" beats "People." Specifics beat abstractions.
Vary rhythm. Mix sentence lengths and structures. Do not change a complete three-part list or a useful em dash merely to satisfy a pattern check.
Trust readers. State facts directly. Skip softening, justification, hand-holding.
Cut quotables. If it sounds like a pull-quote, rewrite it.
Before delivering prose:
Rate 1-10 on each dimension:
| Dimension | Question |
|---|---|
| Directness | Statements or announcements? |
| Rhythm | Varied or metronomic? |
| Trust | Respects reader intelligence? |
| Authenticity | Sounds human? |
| Density | Anything cuttable? |
Below 35/50: revise.
See references/examples.md for before/after transformations.
MIT
