Generate, validate, and explicitly accept a canonical ContextDevKit ADR.
Maestra-Tech/ContextDevKit
SkillsMP has collected 80 skills from Maestra-Tech/ContextDevKit. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 80
- GitHub stars
- 3
- GitHub forks
- 0
Skills in this repository
Showing 40 of 80 collected skills.
Open a multi-agent deliberation — a council of specialist voices debate a hard question with tiered research, a synthesizer converges, the result feeds an ADR. (ADR-0035 / ADR-0070)
Start a mutation-focused session on one objective and keep its scope bounded.
Coordinate conditionally required parallel work over explicit, disjoint task scopes.
Manage tasks in one canonical ContextDevKit 4 JSON scope.
Deterministic QA gate for explicitly scoped canonical testing tasks.
Create, load, validate, render, and advance a canonical Workflow v2 package.
Read-only, six-lane improvement scan across architecture, product, security, UX, and growth.
Review the codebase against the best-practices rubric and propose INTELLIGENT refactors (not random splits).
One-pass health audit — runs doctor, a tech-debt sweep, and a QA status check; summarizes top actions.
Global read-only analysis across code, security, dependencies, and likely defects.
Read-only dependency and supply-chain audit with optional explicit report output.
Scaffold GitHub-native security and inspect alerts without creating hidden task state.
Audit the codebase against the constitution — deterministic scan + your interpretation.
Investigator mode — find root cause before writing any new feature code.
Domain Engineering diagnostic — optional CMIS/DAS/profile recommendations. Observation-only; never mutates or blocks.
Register the current session (creates a session file + updates CHANGELOG). Use at the end.
Manage Model Context Protocol (MCP) servers — discover, add (curated), health-check, audit, and sync host configs from the curated registry.
Rank canonical backlog tasks by explicit priority and dependency readiness.
Read-only learning review that proposes governance improvements from durable evidence.
L6 — autonomous feature pipeline. Drives the full squad: design → implement → review → test → log. Checkpoints can be manual or automatic.
Close the predicted-vs-actual loop from the current Git diff.
Bootstrap a brand-new (empty) project from zero — product idea, interactive questionnaire, stack suggestion, roadmap, best practices.
One-shot intelligent onboarding — inspects the project and self-configures ContextDevKit to it.
L5 pre-flight — map the blast radius of a change BEFORE editing high-risk paths.
Propose evidence-backed refinements to agent briefings without applying them.
Triage open GitHub issues into one explicit canonical task scope.
Create a git worktree + branch for a parallel session on the same machine.
Business-driven methodology entry point — classify (intake), create/advance an Operation or Business work context, and drive the intake → operation → nested-workflow flow. Host-neutral; dry-run by default.
Workflow Navigator — shows the current phase, deliverables, and next commands for an ADR-0057 workflow. Read-only; never mutates state.
QA — final verdict. Run the suite, check critical-path coverage vs target, write a PASS/NEEDS-WORK report.
Codex usage and autonomy insight from ContextDevKit receipts, without reading unstable private transcript formats.
Ensure every app/module has its own scoped AGENTS.md, then fill each with real local rules.
Manual Codex premium reasoning tier — run one explicitly requested task on the host-resolved reasoning model, then return to normal.
Quick summary of current project state (latest session + Unreleased + key rules)
Show or verify a stored Session Autonomy Receipt (token/autonomy/cost) for a session.
Context budget — guidance on WHICH context files to load per task type (always / on-demand / skip) to keep token cost low. Read-only advice. (ADR-0066)
Show/route/grow/audit the agent squads — the roster, playbooks, active routing, and onboarding config.
L5 — analyze recent sessions and propose refinements to AGENTS.md (writes a proposal, applies nothing).
QA — materialize tests for the given files, routing each slice to the right specialist.