agentic-design-session

Solid

Turn a framed feature into an append-only decision log: every design fork made explicit, with the reasoning and the alternatives that were rejected and why. Use after agentic-feature-framing has produced a charter, and before any implementation starts. Also use when an implementation reveals an earlier decision was wrong and needs superseding. Produces .claude/features/<slug>/decisions.md, and closes by sizing the feature into the Size and sessions section of the charter — the call on whether the orchestrator runs it in one pass or several. No code, no other file edits. This is phase 1b of the agentic development pipeline.

AI & Automation 314 stars 20 forks Updated yesterday Apache-2.0

Install

View on GitHub

Quality Score: 86/100

Stars 20%
83
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Design session You are settling **how**, and recording it so it survives. The main output is `.claude/features/<slug>/decisions.md`, from `.claude/pipeline/decision-log.template.md`. Read the charter first. You also close by filling one section of the charter — `Size and sessions` — and that is the only edit you may make outside the decision log. It is the last step of this skill, described at the bottom. ## Why the rejected alternatives matter more than the decisions An orchestrator will re-encounter every fork you settle here when it writes specs, weeks of context later. Given only the decision, it does one of two things: re-opens the question, or contradicts it without noticing. Given the decision plus *why the obvious alternative was rejected*, it recognises the fork and moves on. So a `Rejected` bullet with no reason is worth nothing. "We rejected polling" is not a record; "we rejected polling because the p99 gap has to stay under a second and the poll interval that allows would cost more than the socket" is. The same applies when you turn out to be wrong. A superseded decision keeps its reasoning in the file, because the reason it looked right is exactly what stops someone re-proposing it in three weeks. ## Hard rules - **Write no code.** Types, signatures and schemas are decisions, and you may quote a signature in a decision. You may not implement one. - **Edit no file but the decision log**, and the charter's `Size and sessions` section at the close. Not...

Details

Author
PackmindHub
Repository
PackmindHub/packmind
Created
1 years ago
Last Updated
yesterday
Language
TypeScript
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

agentic-feature-framing

Frame a piece of work before any design or implementation: what is in scope, what is explicitly not, and the acceptance criteria that will judge it. Use at the very start of a new feature, when the user says "I want to build X", "we need a way to Y", or hands over a ticket or a rough idea. Produces .claude/features/<slug>/charter.md and nothing else — no code, no design decisions, no file edits. This is phase 1a of the agentic development pipeline; agentic-design-session is 1b and agentic-orchestrator is phase 2.

314 Updated yesterday
PackmindHub
AI & Automation Solid

agentic-orchestrator

Run the implementation loop for a framed and decided feature: pick the next unit, retrieve just enough context, write an inline spec, dispatch one subagent, gate the result, route on which gate stage failed, and record it. Use after agentic-feature-framing and agentic-design-session have produced a charter and a decision log, when the user says "start building", "implement the feature", "run the next unit", or resumes work on an existing .claude/features/<slug>/. This is phase 2 of the agentic development pipeline. It never edits code itself.

314 Updated yesterday
PackmindHub
AI & Automation Listed

decision-log

Record significant architectural or design decisions to .memory/decisions/ in a consistent, ADR-style format, capturing the alternatives considered and why they were rejected — not just the choice made. Use whenever a non-trivial design or architectural decision is made, especially one with real alternatives that were seriously considered and rejected.

1 Updated 1 months ago
NITISH-R-G