triangulate-spec-review
Review and improve architecture specs, ADRs, plugin or agent directory proposals, and other design documents by running multiple independent AI reviewers such as Claude, Qoder, Codex, or Cursor Agent against the same artifact, normalizing P1/P2/P3 findings, and iterating only on blocking or high-risk issues.
- License 许可
- MIT
- 最近更新
- 2026-11-11
- Stars
- ★ 2.5k
- Forks
- 205
01 前言 Front Matter
- name
- triangulate-spec-review
- description
- Review and improve architecture specs, ADRs, plugin or agent directory proposals, and other design documents by running multiple independent AI reviewers such as Claude, Qoder, Codex, or Cursor Agent against the same artifact, normalizing P1/P2/P3 findings, and iterating only on blocking or high-risk issues.
02 资源文件 2
- 参考文档references/review-loop.md2.6 KB
- 脚本scripts/run-triad-review.mjs7.2 KB
03 SKILL.md 正文
Triangulate Spec Review
Use independent AI reviewers as an evaluation surface for specs. The lead agent owns synthesis, edits, validation, and the final recommendation.
Workflow
- Resolve the target spec path and the acceptance gate. If the user did not
name dimensions, default to
complexity,convenience, andevolution. - Read the target spec and nearby repo instructions. Do not pass your suspected fixes or conclusions to reviewers.
- Use the same read-only prompt for every reviewer. Ask for structured
P1/P2/P3findings and ap1_p2_clearboolean. - Run at least two reviewers; prefer three when available. Use
scripts/run-triad-review.mjsfor repeatable local runs. - Normalize findings. Treat reviewers as evidence, not authority:
fix convergent
P1/P2issues first, challenge weak or contradictory findings, and leaveP3as backlog unless it is cheap and clarifying. - If the user asked for edits, patch only the owning spec or directly related helper docs. Keep unrelated refactors out of the review loop.
- Run local validation such as
git diff --check, relevant tests, and targetedrgchecks for renamed concepts or stale paths. - Repeat the reviewer pass until every requested reviewer reports no
P1orP2, or until the user stops the loop.
Resources
- Read
references/review-loop.mdfor the prompt contract, severity rubric, command matrix, and iteration patterns. - Run this skill's
scripts/run-triad-review.mjs --target <path>script, resolved relative to thetriangulate-spec-reviewskill directory, to execute a read-only review round and write normalized JSON output.
Guardrails
- Pass raw artifacts and task-local context to reviewers, not intended answers.
- Keep every reviewer prompt materially identical unless a tool requires command syntax changes.
- Do not let reviewers edit files. The lead agent applies changes after comparing findings.
- Do not declare acceptance from an average score. Acceptance requires no
P1/P2findings from the required review surface.
04 同仓库更多 Skills
verify
Verify one bounded change.
handoff
Prepare a bounded handoff.
intent-correlation-analysis
Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes. Use when reconstructing why an observed coding-agent change exists or when Studio needs evidence-backed Intent correlation. Do not use for raw transcript summaries, deterministic file-operation collection, or autonomous confirmation of inferred Intent.
better-harness
Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.
generate-harness-dsl
Generate, revise, or review complete Harness as Code `.harness` files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with `@qoder-ai/harness`.
memory-recap
Create evidence-linked work profiles, diagnose Coding Agent collaboration friction, and recommend concrete improvements from native memories or frozen exports. Use for memory recaps and agent-usage retrospectives, not memory maintenance or session-performance measurement.