nklisch-skills

Markdown-based work-tracking substrate for AI-driven projects. Items as files in .work/, late-binding releases, gates that produce items, goal-backed autopilot queue runner.

32 skills · hooks

Software development workflow skills — design features, implement from plans, refactor codebases, extract patterns, design tests, and ship releases.

24 skills · 1 agent

Requirements-first delivery with adaptive opportunity scanning, optional release gates, weighted review, and grounded research.

11 skills · hooks

Standalone markdown-first code audit skills — deep code scan, bug scan, security scan, test scan, perf scout, bold refactor, and repo eval without requiring agile-workflow or .work.

7 skills

Standalone, project-agnostic utility skills with no workflow lock-in — plainspeak (plain-language re-explanation), agent-reflection (self-reflection on tool & skill usage), write-tool-skill + skill-auditor (skill authoring and quality auditing).

5 skills

Agentic Research Discipline (ARD) — grounded, verifiable AI research with a non-erodable anti-fabrication floor, selectable verification gates, and a .research/ substrate tier paralleling .work/. ARD is the plugin's internal, empirically-warranted discipline (ard-core/).

4 skills

Control a local Chromium browser and inspect transient behavior with source-linked temporal visual evidence.

2 skills · 1 MCP server

Standalone prose craftsmanship for human-facing docs — style-contract drafting (prose-draft), editorial lens review (prose-review), and a multi-model rewrite-and-weave cycle to publication quality (prose-refine).

3 skills

Calibrate agent working posture to the project and the person — calibrate-posture (adaptive interview that writes a risk-calibrated posture block into AGENTS.md), proportionality-check (a light self-interrupt for uninvited verification, security, and locking machinery), and overbuilder-review (an after-the-fact audit of docs or code for proof rituals, speculative seams, and configurability nobody uses, proposing the smallest mechanism that preserves each real guarantee).

3 skills

Operate Theatre's Stage and Director tools with portable Godot guidance and optional pending-feedback notices.

2 skills · hooks

Sparse cross-agent coordination ledger for shared repositories. Uses deliberate GitHub Discussion events for claims, handoffs, blockers, review summaries, and merge summaries without turning Discussions into chat.

1 skill

Claude Code-only every-turn writing guidance: simple, deeply informative technical language with explicit framing for codebase references and no invented shorthand.

hooks

Delegate arbitrary task work between local coding agents — any host (Claude Code, Codex, or Pi) can call any peer (Codex, Claude Code, Gemini through Antigravity, or Z.AI GLM 5.2 through Pi). Ships the peer skill.

1 skill

Personal control plane for Codex and Claude Code environments — adopt, reconcile, update, and bootstrap native plugins, complete skills, and shared instructions without marketplace discovery.

1 skill

Adaptive, interview-first UI/UX design. A concierge skill that aligns on goals, audience, usage, and visual direction through plain-language conversation, then produces whatever fits — mockups, journeys, token systems, component and motion showcases — capturing screenshots of its work as the committed visual record. Loosely integrates with agile-workflow.

1 skill