AgentStack
atelier-fashion avatar

atelier-fashion

17 listings · 0 installs

Open-source publisher. Listings imported from github.com/atelier-fashion — credited to the original author with their license.

↗ github.com/atelier-fashion
17 results
Self-run
SKILL

Validate

Validate any ADLC phase output before advancing

0
15
Free
Self-run
SKILL

Analyze

Codebase health audit — identify technical debt, quality issues, and improvement opportunities

0
10
Free
Self-run
SKILL

Wrapup

Close out a completed feature — update ADLC artifacts, log knowledge, and summarize

0
9
Free
Self-run
SKILL

Init

Bootstrap .adlc/ structure in a new repo or subdirectory

0
9
Free
Self-run
SKILL

Reflect

Post-implementation self-review — catch issues before /review

0
8
Free
Self-run
SKILL

Manifest

Remote-derived view of all in-flight ADLC work — open PRs and pushed feat/REQ-* branches across every session — with a coarse component/domain overlap report. Read-only and advisory.

0
13
Free
Self-run
SKILL

Optimize

API cost & performance scanner — identify expensive operations and optimization opportunities

0
14
Free
Self-run
SKILL

Canary

Canary deployment with smoke tests — deploy to a zero-traffic revision, run health checks, and promote on success. Use when the user says "canary deploy", "deploy with canary", "smoke test the deploy", or wants deployment confidence before going live.

0
18
Free
Self-run
SKILL

Proceed

End-to-end ADLC pipeline that takes a requirement from spec through to deployed. Takes a REQ number as argument and runs validate → fix → architect → fix → implement → verify (reflect + review) → create PR → wrapup (merge, deploy, knowledge capture). Use when the user says "proceed", "proceed with REQ-xxx", "run the pipeline", "take REQ-xxx to completion", "implement REQ-xxx end to end", or wants…

0
13
Free
Self-run
SKILL

Review

Multi-agent code review covering correctness, quality, architecture, test coverage, and security

0
19
Free
Self-run
SKILL

Spec

Write requirement specs from feature requests

0
13
Free
Self-run
SKILL

Adversary

Adversarial review of any artifact — a spec, architecture doc, task breakdown, diff/PR, plan, README, or plain prose claim. Assumes the artifact is wrong, broken, or incomplete, tries to prove it, and reports only the findings that survive its own refutation attempts. Read-only and artifact-agnostic. Use when the user says "attack this", "adversary", "red-team this spec/plan/PR", "try to break th…

0
12
Free
Self-run
SKILL

Status

Show current state of all ADLC work across the project

0
17
Free
Self-run
SKILL

Architect

Design architecture and break requirement into tasks

0
15
Free
Self-run
SKILL

Bugfix

End-to-end bug fix workflow — report, analyze, fix, verify, ship (PR + merge + deploy + knowledge capture)

0
14
Free
Self-run
SKILL

Sprint

Parallel pipeline orchestrator — launch multiple /proceed sessions concurrently across REQs, monitor progress, and report status. Use when the user says "sprint", "run these REQs in parallel", "proceed with all approved REQs", "launch a sprint", or wants to advance multiple requirements simultaneously.

0
12
Free
Self-run
SKILL

Template Drift

Detect drift across ALL the sync surfaces `/init` vendors into a project — `.adlc/templates/*.md`, `.adlc/partials/*.sh`, `.adlc/ETHOS.md`, and the workflow runtime (`.adlc/workflows/adlc-sprint.workflow.js` + `README.md`) — against the canonical copies in `~/.claude/skills/`. Use when the user says "check template drift", "template drift", "are my templates out of date", or wants to know whether…

0
16
Free
You've reached the end · 17 loaded