Skip to content
Agentmart
Submit a tool

review-entry

Create one dated, per-work-item retrospective after a change has merged: what worked, what did not, what to change next time, and sourced effort figures.

Skill by juangcarmona

IndexedMIT
Write a review

Chalk Labs

Need help deploying review-entry?

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/juangcarmona-review-entry

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

Create one dated, per-work-item retrospective after a change has merged: what worked, what did not, what to change next time, and sourced effort figures. Use when `review` closes out a work item.

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/review-entry

What's inside

Skill name
review-entry
Description
Create one dated, per-work-item retrospective after a change has merged: what worked, what did not, what to change next time, and sourced effort figures. Use when `review` closes out a work item.
License
MIT
Metadata
author: juangcarmona · plugin: agentic-sdlc
Instructions
48 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Purpose

Create exactly one retrospective record for one merged work item. The default path is `docs/reviews/issue-<number>.md`, configured by the project's `## Label conventions` section. One file per issue prevents parallel reviews from contending on a shared append-only file.

This skill does not measure effort. The caller supplies the effort figures and their source. Missing telemetry is recorded as `not captured`.

## When to use

- At post-merge close-out when `review` has drafted the reflections.
- When recording a retrospective for a completed work item.
- When a post-merge finding needs to be attached to the work item.

## When not to use

- Measuring effort; that is `collect-usage`.
- Amending the Definition of Ready or Definition of Done; `review` proposes that change for human approval.
- Recording a cross-item process rule; use the configured process ledger for that durable lesson.
- Authoring a decision record; use `adr` and link its identifier in the record.

## Workflow

The caller supplies the work item identifier and title, date (`YYYY-MM-DD`, default today), what worked, what did not, what to change next time, effort figures and their source, and the configured path.

1. **Resolve the target.** Read `docs/engineering-lifecycle.md` and use its configured per-item review path. If none is configured, use `docs/reviews/issue-<number>.md`. *Done when:* the exact target path is known.
2. **Check for an existing record.** If the target exists, stop and report it. Never overwrite it or append a second entry. *Done when:* the target is confirmed absent.
3. **Compose the record.** Include the work item and title, date, three reflections, sourced effort or `not captured`, and an amendments section. Route structural lessons to an ADR, process ledger, hardening change, or proposed Ready/Done amendment; use `none` when no amendment is warranted. *Done when:* every field is filled or explicitly marked absent.
4. **Create the file exclusively.** Use a create-if-absent write. If another run creates the same path first, stop and read the existing record; do not overwrite it. *Done when:* exactly one record exists at the target.
5. **Report the record.** Give the caller the work item, path, and any lesson routed to another destination. *Done when:* the record and its follow-up are clear.

## Validation

- Exactly one per-item record was created and any existing record remained unchanged.
- The record follows the configured format and includes all required reflections.
- Every effort figure names its source or is marked `not captured`.
- Structural lessons have a destination or the amendments section says `none`.
- No telemetry was read and no collector was started here.

## Common pitfalls

| Pitfall | Fix |
|---|---|
| Appending different issues to one shared file | Create one file per issue |
| Replacing an existing issue record | Stop; a correction is a later, explicit amendment, never an overwrite |
| Guessing an effort figure | Record `not captured` |
| Leaving a structural lesson buried in a retrospective | Route it to the process ledger, hardening work, Ready/Done amendment, or ADR |
| Running another capability from here | The calling `review` stage owns composition |

From juangcarmona/agent-toolkit, MIT.

More from juangcarmona/agent-toolkit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 19, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from juangcarmona

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 review-entry 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 review-entry?

CallGet help
Cite this page

review-entry skill. Agent Mart. https://agentmart.dev/skills/juangcarmona-review-entry (last updated 2026-10-24)