agentleFS
tikalktikalk/adlc-team-skills/skills/product/product-boot/SKILL.md

product-boot

Skill145 starsChanged 22 days agoMITView on GitHub

Use when product or feature work starts, or a PDR-worthy decision (scope, persona, monetization) emerges — injects the PDR index (docs/adlc/memory/pdr/, legacy .adlc/memory/pdr/ fallback) as session context and suggests the decision for capture via /product-specify (never writes drafts itself); invoked from team-boot's Class Boots catalog.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never defer to session end.

    line 26
  2. Very specific:

    If neither exists but docs/adlc/memory/pdr/PDR-*.md or legacy .adlc/memory/pdr/PDR-*.md files do, synthesize a lean table from each file …

    line 47
  3. Very specific:

    When no local memory index exists in the current working directory and the directory sits inside a workspace (detected via a .gitmodules …

    line 53
  4. Very specific:

    Check .adlc/drafts/pdr/ for PDR-*.md files with status: proposed in frontmatter.

    line 61
  5. Very specific:

    Never write a draft (or any file) yourself — /product-specify writes the .adlc/drafts/pdr/ draft when the user runs it, and …

    line 117
  6. Distinctive:

    Add/refresh rows in Team Context & Decisions (ID | Name | Type | Rel | Status | Clarify) for every PDR-class decision detected this session …

    line 121

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

product-boot

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 a capture suggestion so new product choices are routed to /product-specify rather than evaporating. The boot never writes files: it suggests the capture skill, and the user runs it.

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 through the capture skill.

When to Use

Invoke at the START of a matching task — before planning the todo list and before implementation — so the PDR context informs planning. Never defer to session end.

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: docs/adlc/memory/pdr/pdr.md (generated by /product-implement; rows start with | PDR)
  2. Fallback: .adlc/memory/pdr/pdr.md (legacy layout, legacy)

If neither exists but docs/adlc/memory/pdr/PDR-*.md or legacy .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.

When no local memory index exists in the current working directory and the directory sits inside a workspace (detected via a .gitmodules marker in an ancestor), read the workspace root's docs/adlc/memory/ index instead (the dual-read order applies: docs/adlc/memory first, legacy .adlc/memory fallback).

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.

Absent Context

If team-boot injected no team context this session (no Team Context & Decisions section in the first user message — unconfigured project or hook failure): say so in one line, emit the section heading with a 0 PDRs matched (no team context injected — run /team-setup) source line, and continue the task on the directly-read PDR index. Never treat a missing injection as an empty record set. Recovery: run /team-diagnose.

Step 2: Inject PDR Context (Output Contract)

Emit before the task answer:

## PDR Context

| ID | Feature-Area | Status | Title |
|--|--|--|--|
| AI triage | 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 rows matched → emit the section heading + the _Searched N PDRs, K matched._ line only — no table. A 0-row table header collapses into unrendered single-line markdown; never emit one. Emit the section as markdown blocks — heading, table rows, and counts line each on their own lines.

Step 3: Suggest Product Decision Capture

TriggerAction
Feature scope change, in/out decisionsPDR → suggest /product-specify
Persona definition or revisionPDR → suggest /product-specify
Monetization, pricing, target-market choicePDR → suggest /product-specify
PDR-class decision already in the ledgerverify the suggestion was surfaced; if not, re-surface

Emit one line per detected decision, in the visible response:

_Suggested capture: <decision name> → run /product-specify._

Never write a draft (or any file) yourself — /product-specify writes the .adlc/drafts/pdr/ draft when the user runs it, and /product-clarify gates it afterwards.

Add/refresh rows in Team Context & Decisions (ID | Name | Type | Rel | Status | Clarify) for every PDR-class decision detected this session — including ones from before this boot was invoked. Mirror each decision as a task-list todo (suggest /product-specify → matching clarify skill at session end for drafts that exist); after code-modifying tasks, add a trailing todo to sweep Team Context & Decisions until Unrecorded: 0 pending · Unclarified: 0 drafts (a draft leaves Unclarified only via its clarify skill or an explicit user handoff to a named clarify or execute skill). At session end, deliver the clarify prompt naming each uncaptured decision (ID + capture skill) and each captured PDR draft in .adlc/drafts/pdr/ (ID + clarify skill); if the user defers clarify, mark those rows handed off.

Failure Handling

  • Missing index + missing records → emit the section heading + _Searched 0 PDRs, 0 matched._ only — no table — 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 the capture suggestion — the pairing is the point.
  • Writing a draft (or any file) yourself — the boot only suggests; /product-specify writes.
  • Walking up parent directories to find .adlc/.

Verification

  • PDR Context table emitted with _Searched N PDRs, K matched._ (K = table rows).
  • Detected PDR-class decisions added as Team Context & Decisions rows.
  • No files written; each detected PDR-class decision carries a _Suggested capture: … → run /product-specify._ line.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.