Review Prep

Review Prep is a skill for Claude Code, Codex from YuiZhou/dayarc-agent. It costs 27 tokens per session (1,581 once invoked), scanned A, original, MIT.

A guide that turns saved monthly work summaries into speaking points for performance reviews, one-to-one meetings, and self-assessments.

In plain words
What is it for?
Use it to prepare review or one-to-one talking points for a chosen period, using up to six monthly summaries.
Why use it?
It saves time when preparing for a work conversation and helps organize achievements and topics from several months of notes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare review or one-to-one talking points for a chosen period, using up to six monthly summaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuizhou/dayarc-agent/dayarc-review-prep
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add YuiZhou/dayarc-agent --skill dayarc-review-prep
Clone the repo
git clone --depth 1 https://github.com/YuiZhou/dayarc-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Review Prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuizhou/dayarc-agent/dayarc-review-prep/github.svg)](https://agentmods.dev/skills/yuizhou/dayarc-agent/dayarc-review-prep)
Your own site
<a href="https://agentmods.dev/skills/yuizhou/dayarc-agent/dayarc-review-prep"><img src="https://agentmods.dev/badge/skills/yuizhou/dayarc-agent/dayarc-review-prep/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Review Prep

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuizhou/dayarc-agent/dayarc-review-prep"><img src="https://agentmods.dev/badge/skills/yuizhou/dayarc-agent/dayarc-review-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01581
Opus 5 $0.00014 $0.00790
Sonnet 5 $0.00005 $0.00316
Haiku 4.5 $0.00003 $0.00158

Measured 9d ago against content hash 443c51038ecf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Review Prep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/dayarc-review-prep/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Trigger this skill when the user says anything like:

  • "Generate self-review talking points for Q1"
  • "Prep my 1:1 with my manager"
  • "Generate review talking points"
  • "What should I say in my performance review?"
  • "Prepare self-assessment for {period}"
  • "1:1 prep" / "review prep"
  • Any request combining "review", "self-assessment", "1:1", or "talking points" with a time period or the user's work history

Overview

This skill reads 1–6 monthly summaries and synthesizes structured talking points for a performance review, 1:1, or self-assessment. Output is rendered to the terminal only — no email, no memory write.


Input

Monthly summaries from memory:

  • monthly-archive/{YYYY-MM}.json — archived monthly summaries (up to 6)
  • monthly-summary.json — the most recent monthly summary

The skill determines how many months to include based on the user's request:

  • If the user names a quarter (e.g., "Q1"), include the 3 months of that quarter.
  • If the user names a specific range (e.g., "last 3 months"), include that many.
  • If no period is specified, default to the last 3 months.
  • Cap at 6 months regardless of what is requested.

Instructions

Step 1 — Read Monthly Summaries

Via dayarc-memory, read:

  1. monthly-summary.json (most recent month)
  2. All files in monthly-archive/ directory

Sort by month descending (most recent first). Select the months that fall within the requested period. If fewer months are available than requested, proceed with what exists and note the gap in the output.

If no monthly summaries exist at all, output:

⚠️ No monthly summaries found. Run a monthly brief first (or wait until the end of the month) to build the data this skill needs.

Then stop.

Step 2 — Synthesize Talking Points

Analyze the selected monthly summaries and produce the following sections. Deduplicate items that appear in multiple months. Where applicable, note month-over-month changes.

A. Key Accomplishments
  • Prefer structured impact_summaries across all selected months. Fall back to accomplishments for older memory files that do not contain impact summaries.
  • Deduplicate: if the same item appears in multiple months, keep it once (in the month it was first completed).
  • Group by theme (e.g., "Infrastructure", "Team/Process", "Product/Feature").
  • Maximum 10 items total.
  • Format each item as an outcome-led statement using its action, result, and impact. Include source context where available.

Read the full file on GitHub · 166 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 166 lines · 27 tokens per session scan A 443c51038ecf

Subscribe to this mod's changes

Review Prep is a skill published in the GitHub repository YuiZhou/dayarc-agent (2 stars, last pushed 14d ago), licensed MIT. It adds 27 tokens to every session and 1,581 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.