/critique
Advisory review of the last plan, code, architecture, or UI output. Runs four analysis passes and emits a structured report. Never blocks — advisory only.
Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.
Caller Options. Before executing, run the Caller Options protocol (caller-options/SKILL.md): triage this invocation for material optionality across the venues and modes declared in front-matter; if one path clearly dominates, proceed silently; otherwise surface the options to the caller. A resolved-invocation marker means COP already ran — execute the fixed combination directly, do not re-enter COP.
Phase 1 — Classify
Identify what is being critiqued. Pick exactly one: Code, Plan, Architecture, UI. If the subject is ambiguous, ask for clarification before proceeding.
Phase 2 — Analysis
Run all four passes. Passes 1–3 are independent. Pass 4 depends on Risks.
- Summary — what is this? State purpose, scope, and approach concisely.
- Strengths — what is well-designed, sound, or admirable? Be specific. Do not pad.
- Risks — what is fragile, dangerous, underspecified, or likely to fail? Rank by severity: High / Medium / Low.
- Fixes — for each risk, propose a concrete actionable change. Distinguish must-fix from nice-to-fix.
Phase 3 — Render Report
Output a structured report with four labeled sections: Summary, Strengths, Risks, Fixes. Then set a verdict:
- ✅ Approved — all risks are Low or cosmetic
- ⚠️ Conditional — risks present but fixable; apply fixes then proceed to
/plan-execute
- 🚫 Not Approved — High risks present;
/plan-create or a redesign is required
Constraints
- Advisory only. Never block or halt the user's work unless a kernel-prime violation is detected.
- Never mark Approved when any risk is rated Medium or above.
- Do not pad Strengths to soften the critique. If there are few strengths, say so.
Downstream
Suggest the natural next command — these mirror the next-skills: front-matter:
/insight-adversarial — stress-test the critiqued work from multiple POVs/plan-create — if the verdict is 🚫 Not Approved and a redesign is needed/plan-execute — apply the targeted fixes / proceed if the verdict is ✅ Approved or ⚠️ Conditional
Human output. This skill's handler-facing output obeys the human-output
contract (human-output/SKILL.md).
Next skills. On completion, run the Next Skills protocol (next-skills/SKILL.md): surface the next-skills recommendations from front-matter for the caller to pick. Offer only — never auto-invoke.
Self-improvement. On completion, run the Self-Improvement Protocol (self-improve/SKILL.md): if this run surfaced a concrete, blocking-or-recurring weakness in this skill, propose a specific fix for the handler to approve. Conservative — silent otherwise. Never auto-apply.
1---2name: insight-critique3description: Advisory review workflow. Reviews the last plan, code, architecture, or UI output and returns a structured report: Summary, Strengths, Risks, Fixes. Use when the user runs /critique, asks to "review this", "critique this", or "what's wrong with this", or wants focused feedback on a specific output. Also trigger as a quality gate before /execute. Advisory only — never blocks unless a kernel-prime violation is present. For multi-POV adversarial stress-testing with personas, use /insight-adversarial instead.4---56# /critique78Advisory review of the last plan, code, architecture, or UI output. Runs four analysis passes and emits a structured report. Never blocks — advisory only.910> **Structured execution spec:** [`protocol.yon`](protocol.yon). Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the `@STAMP` date.1112> **Caller Options.** Before executing, run the Caller Options protocol (`caller-options/SKILL.md`): triage this invocation for material optionality across the venues and modes declared in front-matter; if one path clearly dominates, proceed silently; otherwise surface the options to the caller. A resolved-invocation marker means COP already ran — execute the fixed combination directly, do not re-enter COP.1314## Phase 1 — Classify1516Identify what is being critiqued. Pick exactly one: `Code`, `Plan`, `Architecture`, `UI`. If the subject is ambiguous, ask for clarification before proceeding.1718## Phase 2 — Analysis1920Run all four passes. Passes 1–3 are independent. Pass 4 depends on Risks.21221. **Summary** — what is this? State purpose, scope, and approach concisely.232. **Strengths** — what is well-designed, sound, or admirable? Be specific. Do not pad.243. **Risks** — what is fragile, dangerous, underspecified, or likely to fail? Rank by severity: **High** / **Medium** / **Low**.254. **Fixes** — for each risk, propose a concrete actionable change. Distinguish **must-fix** from **nice-to-fix**.2627## Phase 3 — Render Report2829Output a structured report with four labeled sections: Summary, Strengths, Risks, Fixes. Then set a verdict:3031- ✅ **Approved** — all risks are Low or cosmetic32- ⚠️ **Conditional** — risks present but fixable; apply fixes then proceed to `/plan-execute`33- 🚫 **Not Approved** — High risks present; `/plan-create` or a redesign is required3435## Constraints3637- Advisory only. Never block or halt the user's work unless a kernel-prime violation is detected.38- Never mark Approved when any risk is rated Medium or above.39- Do not pad Strengths to soften the critique. If there are few strengths, say so.4041## Downstream4243Suggest the natural next command — these mirror the `next-skills:` front-matter:4445- `/insight-adversarial` — stress-test the critiqued work from multiple POVs46- `/plan-create` — if the verdict is 🚫 Not Approved and a redesign is needed47- `/plan-execute` — apply the targeted fixes / proceed if the verdict is ✅ Approved or ⚠️ Conditional4849> **Human output.** This skill's handler-facing output obeys the human-output50> contract (`human-output/SKILL.md`).5152> **Next skills.** On completion, run the Next Skills protocol (`next-skills/SKILL.md`): surface the `next-skills` recommendations from front-matter for the caller to pick. Offer only — never auto-invoke.5354> **Self-improvement.** On completion, run the Self-Improvement Protocol (`self-improve/SKILL.md`): if this run surfaced a concrete, blocking-or-recurring weakness in this skill, propose a specific fix for the handler to approve. Conservative — silent otherwise. Never auto-apply.
allemaar