product-boot

SkillDocs & knowledge

Lets your agent load past product decision records at the start of product work and capture new decisions as they emerge.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the product-boot skill

About this skill

Use when product or feature work starts, or a PDR-worthy decision (scope, persona, monetization) emerges, injects the PDR index (.adlc/memory/pdr/) as session context and pairs the decision with capture via /product-specify; invoked from team-boot's Class Boots catalog.

What this skill tells your AI

The instructions your AI receives, as published by tikalk/adlc-team-skills in skills/product/product-boot/SKILL.md and read by ahel’s review.

Overview

One of the five class boots surfaced by team-boot's Class Boots catalog. team-boot injects the always-relevant team context (constitution, CDR index, skills registry) at session start; this skill loads the product decision layer on demand — the Accepted PDR index from project memory — and pairs it with decision capture so new product choices are recorded (/product-specify) rather than evaporating.

Reading decisions and recording decisions are one loop: existing PDRs inform the work; decisions made during the work flow back into the same record system.

When to Use

Invoke when:

  • Starting product work (PRD generation, feature definition, roadmap planning, GTM decisions).
  • The session turns product-shaped mid-flight: feature scope, persona definition, monetization, pricing, or target-market choices emerge.
  • Reviewing an existing product's decision backdrop (/product-analyze, /product-roadmap benefit from the loaded index).

Core Process

Step 1: Locate the PDR Index

From the current working directory (do NOT walk up parent directories):

  1. Primary: .adlc/memory/pdr/pdr.md (generated by /product-implement; rows start with | PDR)
  2. Fallback: .adlc/memory/pdr.md

If neither exists but .adlc/memory/pdr/PDR-*.md files do, synthesize a lean table from each file (ID from filename; Feature-Area/Status/Title from frontmatter or first heading). If the directory is empty or absent, report 0 PDRs — never fabricate rows.

Step 1b: Read the PDR Drafts Index

Check .adlc/drafts/pdr/ for PDR-*.md files with status: proposed in frontmatter. These are draft PDRs pending clarification. Collect ID / Title / Type / Status / Date from each file. If the directory is empty or absent, report 0 pending drafts.

Step 2: Inject PDR Context (Output Contract)

Emit before the task answer:

## PDR Context

| ID | Feature-Area | Status | Title |
|--|--|--|--|
| PDR-048 | triage | Accepted | AI triage scoring |

_Searched N PDRs, K matched._

## Drafts Pending Review

| ID | Title | Type | Status | Date |
|----|-------|------|--------|------|
| (from .adlc/drafts/pdr/) |

_N pending drafts — run /product-clarify to review._
  • Render ID / Feature-Area / Status / Title from the index (the full index also carries Category, Date, Owner — read the individual PDR-*.md when a task matches a row).
  • N = total index rows; K = rows relevant to the current task. K MUST equal the table rows shown — 0 matched → empty table, never inflate.

Step 3: Capture Product Decisions

TriggerAction
Feature scope change, in/out decisionsPDR → direct write to .adlc/drafts/pdr/
Persona definition or revisionPDR → direct write to .adlc/drafts/pdr/
Monetization, pricing, target-market choicePDR → direct write to .adlc/drafts/pdr/
PDR-class decision already in the ledgerverify capture happened; if not, re-surface

Add/refresh rows in the Session Decision Ledger (Decision | Type | Captured? | Skill) for every PDR-class decision detected this session — including ones from before this boot was invoked. At session end, prompt to run /product-clarify for any unrecorded PDR drafts in .adlc/drafts/pdr/.

Failure Handling

  • Missing index + missing records → emit the empty table with _Searched 0 PDRs, 0 matched._ and continue the user's task; never block.
  • Unparseable index rows → skip malformed rows, note the skip count.

Red Flags

  • Fabricating PDR rows or inflating K beyond the table shown.
  • Injecting the index but ignoring capture — the pairing is the point.
  • Walking up parent directories to find .adlc/.

Verification

  • PDR Context table emitted with _Searched N PDRs, K matched._ (K = table rows).
  • Session Decision Ledger updated with detected PDR-class decisions.

Signals

GitHub stars
137
Forks
1
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
product-boot
Source
github.com/tikalk/adlc-team-skills