Instructional ADLC skills from Dean Peters’ ProductCamp RTP 2026 talk: shape, secure, and ship AI agents with humans at the helm.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin adlc in deanpeters/ADLC-Skills-ProductCampRTP26. Commands read from the repo's manifest — 5 days ago.
adlc-step1-frame-intentFrame an agent idea as a clear intent brief with autonomy, success, non-goals, and stop boundaries before design begins.
adlc-step2-design-agent-systemMap an approved agent intent into actors, tools, context, memory, permissions, handoffs, and control boundaries.
adlc-step3-generate-agent-harnessConvert an approved system map into an inspectable agent harness plan with prompts, tools, traces, fixtures, and review surfaces.
adlc-step4-validate-agent-behaviorTurn a harness into behavioral evals, failure probes, evidence thresholds, and a validation decision before deployment.
adlc-step5-deploy-with-governancePrepare a governed deployment plan with launch gates, oversight, rollback, incident response, and authority to stop.
adlc-step6-observe-and-improveReview live agent traces, incidents, feedback, drift, and outcomes to decide whether to continue, change, rollback, or retire.
adlc-util-agent-strategy-canvasSum up an agent intent as nine boxes, three each for problem, solution, and value, then decide pivot, punt, or pursue before system design.
adlc-util-decay-checkCheck a live agent for the five signs of constraint decay against what was approved, rate each one, and decide continue, tighten, reframe, restrict, or review.
adlc-util-minimum-viable-narrativeTell one person's journey per prototype variant as a short story in labelled action and response turns, and turn each into a portable prompt for any design, low-code, or coding builder, then decide pivot, punt, or pursue before the bake-off.
adlc-util-plc-checkAsk whether the product's lifecycle stage has changed since an agent was approved, and whether the agent's job, autonomy, measures, and exit should change with it.
adlc-util-solution-hypothesisTurn an approved system design into a falsifiable If/Then bet with two tiny acts of discovery and two measures, then decide pivot, punt, or pursue before building a harness.
Problems found in this repo's manifests
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "AAS AI Product & Evaluation Ops" workflow plugin from Agentic Awesome Skills.
13 skills
Build, train, evaluate, and use open source AI models, datasets, and spaces.
26 skills · 1 MCP server
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
Price bonds, analyze yield curves, evaluate FX carry trades, value options, and build macro dashboards using LSEG financial data and analytics.
8 skills · 8 commands · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.