New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Triangulate Spec Review

by QoderAI in QoderAI/better-harness

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…

MITAuto-check passedDevelopment

Install Triangulate Spec Review

skills CLI
$ npx skills add QoderAI/better-harness --skill triangulate-spec-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install QoderAI/better-harness triangulate-spec-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/QoderAI/better-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/triangulate-spec-review .claude/skills/triangulate-spec-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
triangulate-spec-review
GitHub stars
2.4k
Token cost
~614 tokens
SKILL.md length
294 words
Files
3 (incl. scripts, references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

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…

  • Works in 8 steps: Resolve the target spec path and the… → Read the target spec and nearby repo… → Use the same read-only prompt for every… → …
  • Tasks that involve Architecture decision records
  • SKILL.md covers Workflow, Resources and Guardrails
  • Runs JavaScript scripts from its folder; calls git

What it does

Triangulate Spec Review is an agent skill from QoderAI/better-harness. 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.

Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/review-loop.md`).

It sits in Development, covering Architecture decision records and Proposals and quotes. The repository describes itself as: An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence… The licence is MIT.

When your agent uses it

  • Tasks that involve Architecture decision records
  • Tasks that involve Proposals and quotes

Example prompts

  • “/triangulate-spec-review”

Requirements

  • Node.js

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Resolve the target spec path and the acceptance gate. If the user did not
  2. Read the target spec and nearby repo instructions. Do not pass your suspected
  3. Use the same read-only prompt for every reviewer. Ask for structured
  4. Run at least two reviewers; prefer three when available. Use
  5. Normalize findings. Treat reviewers as evidence, not authority
  6. If the user asked for edits, patch only the owning spec or directly related
  7. Run local validation such as git diff --check, relevant tests, and targeted
  8. Repeat the reviewer pass until every requested reviewer reports no P1 or

What it can do on your machine

Read from SKILL.md and the folder at commit 34899f3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Triangulate Spec Review loads about 614 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 294 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~614
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from QoderAI/better-harness at commit 34899f3, republished under its MIT licence (© QoderAI). 294 words, ~614 tokens.

Download SKILL.mdSave it as .claude/skills/triangulate-spec-review/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
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.

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

  1. Resolve the target spec path and the acceptance gate. If the user did not name dimensions, default to complexity, convenience, and evolution.
  2. Read the target spec and nearby repo instructions. Do not pass your suspected fixes or conclusions to reviewers.
  3. Use the same read-only prompt for every reviewer. Ask for structured P1/P2/P3 findings and a p1_p2_clear boolean.
  4. Run at least two reviewers; prefer three when available. Use scripts/run-triad-review.mjs for repeatable local runs.
  5. Normalize findings. Treat reviewers as evidence, not authority: fix convergent P1/P2 issues first, challenge weak or contradictory findings, and leave P3 as backlog unless it is cheap and clarifying.
  6. If the user asked for edits, patch only the owning spec or directly related helper docs. Keep unrelated refactors out of the review loop.
  7. Run local validation such as git diff --check, relevant tests, and targeted rg checks for renamed concepts or stale paths.
  8. Repeat the reviewer pass until every requested reviewer reports no P1 or P2, or until the user stops the loop.

Resources

  • Read references/review-loop.md for 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 the triangulate-spec-review skill 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/P2 findings from the required review surface.

© QoderAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in .agents/skills/triangulate-spec-review of QoderAI/better-harness.

  • SKILL.md
  • references/review-loop.md
  • scripts/run-triad-review.mjs

Open the folder on GitHubat commit 34899f3

Compare with similar skills

Triangulate Spec Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Triangulate Spec Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Triangulate Spec Review this skillQoderAI/better-harness2.4k—~614Automated safety check: PassMIT
Dev Rfcpproenca/dot-skills215—~3.8kAutomated safety check: PassMIT
Agent Stylepchalasani/claude-code-tools2k—~1.4kAutomated safety check: PassMIT
Squid Architecture Reviewiusztinpaul/squid203—~2.6kAutomated safety check: PassApache-2.0
Write Vibe Design Docmistralai/mistral-vibe5.1k—~3kAutomated safety check: PassApache-2.0
Plan ArbiterBuilderIO/skills4.5k—~1kAutomated safety check: PassMIT

Similar skills

  • Dev Rfc

    pproenca/dot-skills

    Create well-structured RFCs and technical proposals for software projects.

    215 GitHub stars~3.8k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Agent Style

    pchalasani/claude-code-tools

    Literature-backed English technical-prose writing rules (agent-style, 21 rules).

    2k GitHub stars~1.4k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Squid Architecture Review

    iusztinpaul/squid

    Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings shaped as refactor proposals /squid-refactor can consume directly.

    203 GitHub stars~2.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Write Vibe Design Doc

    mistralai/mistral-vibe

    Official

    Create or update implementation-ready design proposals for Mistral Vibe under docs/design, including a bounded design-tree decision review before drafting.

    5.1k GitHub stars~3k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Plan Arbiter

    BuilderIO/skills

    A skill your agent uses when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed…

    4.5k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

  • Qv Quality Reporting

    tetherto/qvac

    Run the deterministic code-quality audit, turn related findings into contextual remediation groups, prepare approval-gated Asana proposals, reconcile recurring runs, or configure twice-monthly…

    681 GitHub stars~1.6k tokensUpdated today
    DevelopmentAuto-check passed

More from QoderAI/better-harness

All 11 skills in this repo

  • Intent Correlation Analysis

    QoderAI/better-harness

    Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes.

    2.4k GitHub stars~1.2k tokensUpdated 10 days ago
    Auto-check passed

  • Better Harness

    QoderAI/better-harness

    A skill your agent uses when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable…

    2.4k GitHub stars~3k tokensUpdated 10 days ago
    Auto-check passed

  • Generate Harness Dsl

    QoderAI/better-harness

    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…

    2.4k GitHub stars~761 tokensUpdated 10 days ago
    Auto-check passed

  • Harness Skill Creator

    QoderAI/better-harness

    A skill your agent uses when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain.

    2.4k GitHub stars~844 tokensUpdated 10 days ago
    Auto-check passed

  • Skill Review

    QoderAI/better-harness

    A skill your agent uses when reviewing Codex, Qoder, or repo-local skills and their prompt chains for trigger quality, workflow clarity, progressive disclosure, duplicated instructions, template…

    2.4k GitHub stars~802 tokensUpdated 10 days ago
    Auto-check passed

  • Diagnose Backend Bug

    QoderAI/better-harness

    Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records.

    2.4k GitHub stars~1.2k tokensUpdated 10 days ago
    Auto-check passed

Categories

Questions about Triangulate Spec Review

What does Triangulate Spec Review do?

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…. Triangulate Spec Review is an agent skill from QoderAI/better-harness. 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.

When should I use Triangulate Spec Review?

Triangulate Spec Review fits situations like: tasks that involve Architecture decision records; tasks that involve Proposals and quotes.

How do I install Triangulate Spec Review in Claude Code?

Run `npx skills add QoderAI/better-harness --skill triangulate-spec-review -a claude-code`. Or copy the skill folder (.agents/skills/triangulate-spec-review in QoderAI/better-harness) into .claude/skills/triangulate-spec-review in your project. Claude Code loads it when a task matches its description.

How do I install Triangulate Spec Review in Codex?

Run `npx skills add QoderAI/better-harness --skill triangulate-spec-review -a codex`. Or copy the skill folder (.agents/skills/triangulate-spec-review in QoderAI/better-harness) into .agents/skills/triangulate-spec-review in your project. Codex loads it when a task matches its description.

Can I use Triangulate Spec Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QoderAI/better-harness --skill triangulate-spec-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/triangulate-spec-review, .gemini/skills/triangulate-spec-review, .github/skills/triangulate-spec-review and .opencode/skills/triangulate-spec-review in your project.

What does Triangulate Spec Review need to run?

Going by SKILL.md and its folder, Triangulate Spec Review needs JavaScript for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: Node.js.

Does Triangulate Spec Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Triangulate Spec Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Triangulate Spec Review use?

Triangulate Spec Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Triangulate Spec Review use?

About 614 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 654 tokens, read only when the agent opens those files.

What are the alternatives to Triangulate Spec Review?

Skills that share tags, products or a category with Triangulate Spec Review: Dev Rfc (pproenca/dot-skills, 215 stars), Agent Style (pchalasani/claude-code-tools, 2k stars), Squid Architecture Review (iusztinpaul/squid, 203 stars) and Write Vibe Design Doc (mistralai/mistral-vibe, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Triangulate Spec Review?

QoderAI (a GitHub organization) maintains it in QoderAI/better-harness, which has 2,364 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 28, 2026.

Source: QoderAI/better-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.