tech-spec:review SKILL.md skillA

tech-spec:review from bendrucker/claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bendrucker/claude/tech-spec:review@git:20260827.12933dd

Pins git:20260827.12933dd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bendrucker/claude
Path
plugins/tech-spec/skills/review/SKILL.md
Versions recorded
5
Latest version
git:20260827.12933dd, committed Aug 27, 2026
First version recorded
Jan 30, 2026
Size
1,842 bytes
Repository stars
18
License
MIT

Review an existing technical specification for gaps, risks, and missing considerations.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Review Technical Specification

## Inputs

Ask the user to provide:

- **Tech spec**: Path to the specification file, or pasted content
- **Focus areas** (optional): Specific concerns to prioritize (e.g., "security", "API design")
- **Repositories** (optional): Codebases to consult when verifying spec claims

## Code Exploration

When repositories are provided, consult code to verify:
- Proposed patterns match existing conventions
- Referenced files and structures exist
- Implementation assumptions are accurate

Explore on demand during review, not upfront.

## Review Process

### Identify Expert Perspectives

Select relevant personas from [references/experts.md](references/experts.md):
- Always include standard personas (security, API, database, etc.)
- Add dynamic personas based on spec content (integrations, analytics, etc.)
- User-specified focus areas get priority

### Conduct Review

For each persona:

1. Scan the spec for areas within their expertise
2. Identify findings: gaps, risks, unclear decisions, missing considerations
3. Rate severity: blocking, important, or nice-to-have

### Present Findings

Group related findings into batches and present via `AskUserQuestion`:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bendrucker/claude/tech-spec:review@sha256:3aee90276fa905bd

The line at the top of this page pins the label git:20260827.12933dd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gegekomouopcvk2m.svg)](https://markdownregistry.com/a/art_gegekomouopcvk2m)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jan 30, 2026 and Aug 27, 2026, about one every 52 days.

versioncommittedcommitsizeaudit
git:20260827.12933dd latest2026-08-27 12933dd 1,842 BA view · diff
git:20260615.1ec44ee2026-06-15 1ec44ee 1,992 BA view · diff
git:20260605.8751e322026-06-05 8751e32 2,017 BA view · diff
git:20260208.23371e32026-02-08 23371e3 1,986 BA view · diff
git:20260130.dcbe1992026-01-30 dcbe199 1,976 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1842 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

bendrucker/claude · 18 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gegekomouopcvk2m
GET https://markdownregistry.com/api/v1/resolve?ref=bendrucker/claude/tech-spec:review
GET https://markdownregistry.com/api/v1/blob/3aee90276fa905bd8b89de2f071c7d7ee39fc4e36dcc378f331b724bd761a71b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from bendrucker/claude

agent-ideas SKILL.md skill
bendrucker/claude · .claude/skills/agent-ideas/SKILL.md · Harvest agent-tooling ideas from prominent developers.
git:20260916.5ad8621 · audit A · 18 stars
cli SKILL.md skill
bendrucker/claude · .claude/skills/cli/SKILL.md · Type-safe CLI argument parsing with commander and @commander-js/extra-typings, the standard parser for this repo's Bun…
git:20261017.46cee47 · audit A · 18 stars
prose-lab SKILL.md skill
bendrucker/claude · .claude/skills/prose-lab/SKILL.md · Turn the user's labels on repo prose, or their notes from reviewing a document in Plannotator, into calibrated Vale…
git:20261103.c79cbff · audit A · 18 stars
CLAUDE.md CLAUDE.md file
bendrucker/claude · CLAUDE.md
git:20261103.7402b16 · audit A · 18 stars
activitywatch:activity SKILL.md skill
bendrucker/claude · plugins/activitywatch/skills/activity/SKILL.md · Report real device usage from ActivityWatch. Covers per-app time, window titles, and active vs idle spans. Use when…
git:20260713.5ca4d49 · audit A · 18 stars
agents:agent-team SKILL.md skill
bendrucker/claude · plugins/agents/skills/agent-team/SKILL.md · Orchestrating Claude Code agent teams. Use when creating teams, spawning teammates, assigning tasks, configuring…
git:20261006.a882371 · audit A · 18 stars
agents:handoff SKILL.md skill
bendrucker/claude · plugins/agents/skills/handoff/SKILL.md · Hand the current conversation off to a fresh background agent that picks up the work immediately, so you can step away…
git:20261020.56c0e8f · audit A · 18 stars
atuin:history SKILL.md skill
bendrucker/claude · plugins/atuin/skills/history/SKILL.md · Report shell history from atuin's local capture. Covers what commands ran, when, where, and how they exited. Use when…
git:20261018.8bb1907 · audit A · 18 stars
bun SKILL.md skill
bendrucker/claude · plugins/bun/skills/bun/SKILL.md · Bun runtime patterns. Use when running bun commands, working with package.json/bun.lock, writing TypeScript scripts…
git:20261030.ee8bb41 · audit A · 18 stars
comments:audit SKILL.md skill
bendrucker/claude · plugins/comments/skills/audit/SKILL.md · Audit code comments for AI slop: restatement, narration/decision-log, self-praise, docstring-scope, and section-divider…
git:20261030.03f7155 · audit A · 18 stars
dispatch SKILL.md skill
bendrucker/claude · plugins/dispatch/skills/dispatch/SKILL.md · Hand new work bound for its own pull request to a fresh Claude session in a new worktree, opened in a Rex tab or a…
git:20261105.b14fe19 · audit A · 18 stars
evals:hill-climb SKILL.md skill
bendrucker/claude · plugins/evals/skills/hill-climb/SKILL.md · Hill-climb a skill, agent, rule, or CLAUDE.md against its eval suite. Use when changing one to raise an eval score…
git:20261030.ad16282 · audit A · 18 stars

Every file in bendrucker/claude

Browse by kind, by grade A, or by owner.