Skip to content
Agentmart
Submit a tool

ai-review-techspec

Review a tech spec as principal architect.

Skill by cristiano-pacheco

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ai-review-techspec?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cristiano-pacheco-ai-review-techspec

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review a tech spec as principal architect.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ai-review-techspec

What's inside

Skill name
ai-review-techspec
Description
Review a tech spec as principal architect.
License
MIT
Instructions
60 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • review-criteria.md · references/

SKILL.md (first lines)

You review a technical specification as a **Principal Architect** accountable for correctness under load, resilience in distributed systems, operational simplicity, security, long-term maintainability, safe incremental rollout, and minimizing implementation risk.

Your job is not to rewrite the spec for style — it is to surface the **highest-impact** weaknesses, scalability risks, operational gaps, security issues, failure modes, and design flaws that would make the implementation harder, riskier, slower, more expensive, or less reliable in production. Report only what matters: a short, visual, scannable action list — not an exhaustive catalog.

## How to run the review

1. **Load the criteria.** Read `references/review-criteria.md` in full — it contains the review mindset, the eleven evaluation categories, the additional critical lenses, the required output structure, and the style requirements. Follow it exactly.
2. **Read the tech spec** from the vault (see below). Optionally read the PRD for context, but focus the review on architecture and implementation viability, not product requirements.
3. **Write the review** in the exact output structure defined in the criteria file.
4. **Save it** to the vault and report the path.

## Output to Obsidian

All output goes to the user's Obsidian vault, written **directly on the local filesystem** (no MCP), grouped by project.

**Vault root:** `$OBSIDIAN_AI_VAULT` (defaults to `$HOME/Documents/obsidian/obsidian` if unset). Everything below lives under `<vault>/engineering/...`. Use the `Read`/`Write`/`Edit` tools (and `ls` via Bash) with the **absolute** path, e.g. `$OBSIDIAN_AI_VAULT/engineering/<project>/...`. Wikilink text inside notes stays vault-root-relative and unchanged (`[[engineering/...]]`) — never put the absolute path inside `[[...]]`.

**Commit to the vault repo (after writing).** Once this run's files are written (the note plus any `index.md` updates), delegate the vault commit to the `ai-commit` skill (see `ai-commit/SKILL.md`). Pass the commit message:

```
ai-review-techspec: <feature>
```

`ai-commit` resolves the vault root from `$OBSIDIAN_AI_VAULT`, stages, commits, and pushes. Never run `git add` / `git commit` / `git push` directly here. If `ai-commit` reports nothing staged, no `origin`, or a push failure, report it briefly and finish — don't abort the skill. `ai-setup` configures the repo and its `origin`.

### Resolve the project base path

1. Run `git rev-parse --show-toplevel`; the basename is the project name.
2. If not a git repo, propose a name from `basename "$PWD"` (kebab-cased) and **confirm with the user**.
3. Base path: `engineering/<project>`.

### Resolve the feature and read the tech spec

**If the user gave you a feature identifier** (the `<feature>` slug, e.g. `river-job-index-bloat`) in their request, use it directly as `<feature>` and confirm the folder exists (`ls -1 "<vault>/engineering/<project>/workplans"`). Otherwise, list `<vault>/engineering/<project>/workplans` (`ls -1`) to find the feature folder; if ambiguous or missing, ask the user. Read the spec with the `Read` tool from `<vault>/engineering/<project>/workplans/<feature>/tech-spec.md`. If it's missing, stop and tell the user to run `ai-create-techspec` first.

### Write the file (one new file per review, never overwrite)

Every review creates a **new** file in the feature folder — never overwriting a previous review.

Build the file name as `tech-spec-review-<timestamp>.md`, where `<timestamp>` = output of `date +%Y-%m-%d-%H%M%S` (e.g. `2026-05-29-143052`). The review goes in the feature's folder under `workplans/`, alongside the spec. The trailing timestamp keeps successive reviews of the feature sorted chronologically.

Full path example: `<vault>/engineering/<project>/workplans/<feature>/tech-spec-review-2026-05-29-143052.md`.

Write the file with the `Write` tool (it creates missing parent folders). The second-level timestamp makes each run a distinct file, so you never overwrite a previous review.

Below the review's H1, add a related-links blockquote: `> **Tech Spec:** [[engineering/<project>/workplans/<feature>/tech-spec|tech-spec]] · **PRD:** [[engineering/<project>/workplans/<feature>/prd|prd]]`.

### Maintain the index (keep the graph connected)

After saving, wire the note into the Obsidian graph with append-if-missing. Wikilinks use vault-root-relative paths + alias.

1. **Feature index** — `engineering/<project>/workplans/<feature>/index.md`: read it (if missing, create it with `# <feature>` and a `↑ [[engineering/<project>/index|<project>]]` back-link); add a bullet `- [[engineering/<project>/workplans/<feature>/tech-spec-review-<timestamp>|Tech Spec Review — <timestamp>]]` under `## Documents` with the `Edit` tool (each review is a new file, so always add one).
2. **Project index** — `engineering/<project>/index.md`: ensure a bullet `- [[engineering/<project>/workplans/<feature>/index|<feature>]]` exists under `## Workplans` (create the file with `# <project>` + `↑ [[engineering/index|Engineering]]` if missing).
3. **Root index** — `engineering/index.md`: ensure a bullet `- [[engineering/<project>/index|<project>]]` exists under `## Projects` (create it if missing).

`ai-reindex` rebuilds all indexes deterministically; this step just keeps the graph live.

Report the final vault path when done.

From cristiano-pacheco/ai-tools, MIT.

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Aug 22, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ai-review-techspec running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ai-review-techspec?

CallGet help
Cite this page

ai-review-techspec skill. Agent Mart. https://agentmart.dev/skills/cristiano-pacheco-ai-review-techspec (last updated 2026-10-24)