abvx-agent-skills 0.10.0

Small, reviewable, validation-gated agent skills for Codex-style project work.

ABVX Agent Skills

Small, reviewable, validation-gated agent skills for Codex-style project work.

This repository publishes opinionated ABVX skillpacks: compact SKILL.md workflows with clear triggers, attribution, risk notes, and validation. These are not prompt dumps. They are portable, versioned agent capabilities meant to be loaded on demand through the Agent Skills progressive-disclosure model.

The newer bet in this pack is LoopOps: useful skills should not compete with stronger base models by restating generic advice. They should capture repo-specific context, tool adapters, verification gates, and supervisor contracts that can promote repeated work into scripts, workflows, and cost-bounded agent loops.

Start Here

• Need to save tokens? Start with rtk-assisted-shell, shell-output-compaction, token-efficient-execution, and lean-context-layout. Add compaction-survival if your sessions run long enough to forget their own state.
• Need to debug a repo? Start with diagnose, repo-debugging-ledger, and graph-guided-code-reading.
• Need to build frontend? Start with frontend-product-builder, designmd-brand-kit, and browser-verification.
• Need a standalone HTML artifact? Start with html-diagram-artifact for SVG-first architecture explainers, or html-brief-artifact for plans, summaries, reports, and research notes.
• Need stronger UI taste or design setup? Start with design-register-bootstrap, frontend-taste-layer, and design-critique-polish.
• Need long-session continuity? Start with handoff, compaction-survival, and token-usage-audit.
• Need to onboard a new repo? Start with project-context-bootstrap and follow with durable-context-maintenance.
• Need discovery or product shaping? Start with rapid-grilling, doc-grounded-grilling, and spec-to-prd.
• Need to turn plans into execution? Start with plan-to-issues, repo-issue-triage, and test-driven-execution.
• Need safer long delivery runs? Start with delivery-preflight-gate, phase-spec-execution, recovery-loop-3strike, and delivery-baseline-audit.
• Need a full multi-track workflow? Start with dynamic-workflow-packets.
• Need to turn repeated prompts into loops? Start with loopops-protocol, then use skillopt-evolve-skills to capture durable lessons.
• Need to build reusable assistant packs? Start with role-skill-pack-design, workflow-policy-layering, brief-first-execution, and private-vs-publishable-skill-audit.

Skills

These skills are grouped by the job they do. The token-economy layer is intentionally visible first: for many teams, the easiest win is not “a smarter prompt”, but less wasted context.

Token Economy & Context Control

Skill	What It Does	Status	Origin
rtk-assisted-shell	Routes noisy shell workflows through RTK-style filtering. On shell-heavy tasks this can cut command-output tokens dramatically, often in the same range as RTK's reported 60-90% savings on common dev commands.	experimental	ABVX adapted
shell-output-compaction	Shrinks logs, diffs, and repo search output into counts, slices, and error-first excerpts. Usually the fastest way to turn multi-screen stdout into a small, usable artifact.	experimental	ABVX adapted
graph-guided-code-reading	Replaces broad repo reading with entrypoints, symbols, dependencies, and blast radius. On large codebases this can turn “read everything” into a much smaller focus set.	experimental	ABVX adapted
token-efficient-execution	Cuts waste from repeated reads, broad rewrites, and low-value narration. Best for long coding sessions where the loop, not the final answer, is burning the budget.	experimental	ABVX adapted
token-frugal-mode	Compresses final answers without dropping the decisive technical signal. Useful when the session is tight and you want shorter replies without caveman-style degradation.	experimental	ABVX adapted
lean-context-layout	Shrinks always-loaded agent docs into a compact startup core and pushes the rest on demand. Best for bloated AGENTS.md, CLAUDE.md, and repo runbooks.	experimental	ABVX adapted
compaction-survival	Preserves the high-value working state before long sessions collapse into compaction. Saves the turns you would otherwise spend reconstructing “what were we doing?”.	experimental	ABVX adapted
token-usage-audit	Diagnoses where the budget is really going: startup bloat, shell noise, repeated reads, oversized summaries, or compaction loss. Use this before over-optimizing the wrong layer.	experimental	ABVX adapted

Coding, Debugging & Architecture

Skill	What It Does	Status	Origin
diagnose	Runs a disciplined debugging loop around one reproducible signal, ranked hypotheses, and narrow verification.	experimental	ABVX adapted
repo-debugging-ledger	Keeps a checked-location ledger so debugging does not keep reopening the same code and repeating the same dead ends.	experimental	ABVX original
complexity-optimizer	Finds safe complexity and performance simplifications without turning the codebase into a refactor festival.	experimental	ABVX adapted
architecture-deepening-review	Reviews deeper module seams, coupling, change surfaces, and testability, not just top-level architecture slogans.	experimental	ABVX adapted
test-driven-execution	Builds features and fixes through one-behavior-at-a-time red-green-refactor loops instead of broad speculative implementation.	experimental	ABVX adapted
system-zoom-out	Pulls a local code area back into its wider system map so you can reason about callers, modules, boundaries, and blast radius.	experimental	ABVX adapted
agents-best-practices	Hardens agent harnesses around permissions, context shape, safety, and evaluation discipline.	experimental	ABVX adapted
skillopt-evolve-skills	Improves agent instructions and skills from real task evidence rather than from theory alone.	experimental	ABVX adapted

Frontend, UX & Product Surfaces

Skill	What It Does	Status	Origin
design-register-bootstrap	Establishes compact design context before implementation: brand vs product register, audience, anti-references, color strategy, and PRODUCT.md / DESIGN.md direction.	experimental	ABVX adapted
frontend-taste-layer	Adds a stronger anti-slop design layer to frontend work so outputs stop looking templated, generic, or visually under-committed.	experimental	ABVX adapted
design-critique-polish	Runs a focused critique-and-polish pass to rank frontend issues, identify ship blockers, and tighten hierarchy, typography, color, and states.	experimental	ABVX adapted
frontend-product-builder	Builds usable frontends, landing pages, pitch pages, dashboards, and prototypes with a product-first interaction model.	experimental	ABVX adapted
designmd-brand-kit	Turns a website or brand surface into an agent-usable design system: structure, identity, and reusable UI cues.	experimental	ABVX adapted
browser-verification	Verifies real browser rendering, responsive layout, and interaction behavior instead of trusting static code inspection.	experimental	ABVX adapted
web-quality-audit	Audits accessibility, performance, UX, privacy, and browser security as one practical web quality pass.	experimental	ABVX adapted
prototype-lab	Rapid throwaway builds for testing interaction, logic, and product direction before committing to heavier implementation.	experimental	ABVX adapted

HTML Artifacts & Visual Deliverables

Skill	What It Does	Status	Origin
html-diagram-artifact	Creates standalone HTML/SVG diagrams for architecture, request paths, component relationships, and system explainers with minimal prose and browser-verifiable dark mode.	experimental	ABVX adapted
html-brief-artifact	Creates standalone HTML briefs for plans, status updates, PR summaries, incident notes, and research explainers without drifting into a full frontend build.	experimental	ABVX adapted

Project Context & Onboarding

Skill	What It Does	Status	Origin
design-register-bootstrap	Detects whether a surface is brand or product, then writes the compact design context needed to keep later frontend work coherent.	experimental	ABVX adapted
project-context-bootstrap	Detects the stack, asks the right project questions, and turns a weakly documented repo into a compact, agent-usable context surface.	experimental	ABVX adapted
durable-context-maintenance	Keeps repo-local context current after architecture, workflow, and test-flow changes so agents stop rediscovering the same facts.	experimental	ABVX adapted

Discovery, Planning & Delivery

Skill	What It Does	Status	Origin
rapid-grilling	Quickly sharpens vague ideas through one-question-at-a-time alignment before heavier planning starts.	experimental	ABVX adapted
doc-grounded-grilling	Stress-tests a plan against repo docs, ADRs, design assets, and domain language so discovery stays grounded in reality.	experimental	ABVX adapted
spec-to-prd	Turns clarified context into a durable PRD for product, client, and internal roadmap work.	experimental	ABVX adapted
plan-to-issues	Breaks PRDs and plans into thin end-to-end slices that agents or humans can actually pick up.	experimental	ABVX adapted
repo-issue-triage	Moves bugs and enhancements through a compact state machine so backlog items become actionable instead of vague.	experimental	ABVX adapted

Research, Knowledge & Reusable Methods

Skill	What It Does	Status	Origin
evidence-ledger-research	Keeps claims, sources, calculations, and open questions in a disciplined evidence ledger.	experimental	ABVX original
loopops-protocol	Chooses when repeated agent work should stay a prompt or be promoted into a skill, checklist, script, workflow, or cost-bounded loop.	experimental	ABVX original
book-to-skill	Converts books, papers, and long documents into reusable, progressive-disclosure agent skills.	experimental	ABVX adapted
role-skill-pack-design	Designs compact role/workflow skill packs with base layers, difference layers, boundaries, and rollout order.	experimental	ABVX original
workflow-policy-layering	Separates workflow from authority, escalation, forbidden actions, and validation so assistant specs stop contradicting themselves.	experimental	ABVX original
brief-first-execution	Starts non-trivial work with one live brief for scope, non-goals, risks, verification, and done criteria.	experimental	ABVX original
private-vs-publishable-skill-audit	Audits private skill packs before publication and extracts only the reusable layer.	experimental	ABVX original

Workflow, Handoffs & Multi-Track Work

Skill	What It Does	Status	Origin
dynamic-workflow-packets	Orchestrates large coding, research, audit, or client-search tracks without losing verification and risk gates.	experimental	ABVX adapted
handoff	Produces compact continuation briefs for long-running work, agent resumes, and human handoffs.	experimental	ABVX adapted

Long-Run Delivery Control

Skill	What It Does	Status	Origin
delivery-preflight-gate	Runs the minimum useful baseline checks before a long implementation loop starts, so pre-existing breakage does not poison later verification.	experimental	ABVX adapted
phase-spec-execution	Breaks larger delivery into explicit phases with acceptance criteria, verification commands, and lightweight state updates.	experimental	ABVX adapted
recovery-loop-3strike	Bounds execution failure handling to one evidence-bearing retry, one focused fix-spec, and then an honest blocker handoff.	experimental	ABVX adapted
delivery-baseline-audit	Re-checks declared deliverables and final verification against the starting baseline and full working tree before calling the task complete.	experimental	ABVX adapted

Structured Data & Spreadsheet Work

Skill	What It Does	Status	Origin
spreadsheet-workbook-forensics	Repairs and edits spreadsheets where workbook structure, formulas, and cell-level verification matter.	experimental	ABVX original

Install

Install one skill into Codex:

git clone https://github.com/markoblogo/abvx-agent-skills
cp -R abvx-agent-skills/skills/dynamic-workflow-packets ~/.codex/skills/

Install all skills:

git clone https://github.com/markoblogo/abvx-agent-skills
cp -R abvx-agent-skills/skills/* ~/.codex/skills/

Start a new agent session after installation so the skill descriptions are discovered.

Install via PyPI:

pip install abvx-agent-skills
abvx-skills list
abvx-skills install

Published package pages:

• PyPI: https://pypi.org/project/abvx-agent-skills/
• TestPyPI: https://test.pypi.org/project/abvx-agent-skills/

Install one packaged skill into Codex:

abvx-skills install dynamic-workflow-packets

Install to a custom destination:

abvx-skills install --destination ./tmp-skills

Smoke-test the published package from PyPI:

python -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install abvx-agent-skills
abvx-skills list
abvx-skills validate

Repository Profile

Each public skill includes:

• SKILL.md - executable agent instructions
• SKILL_CARD.md - intended use, attribution, risks, evaluation, and version
• agents/openai.yaml - Codex UI metadata

The project follows the open Agent Skills shape: SKILL.md plus optional scripts/, references/, and assets/. For Codex compatibility, top-level frontmatter is kept conservative: name, description, license, metadata, and supported fields only.

The HTML artifact skills intentionally keep their deliverables single-file and dependency-light. Use them for explainers and briefs, not as substitutes for production frontend implementation.

Validate

python scripts/validate.py

Or validate the packaged skills through the CLI:

abvx-skills validate

Run a static security audit with SkillSpector:

pip install git+https://github.com/NVIDIA/SkillSpector.git
abvx-skills audit-security ./skills --no-llm

Evaluate reports against the repo policy and baseline:

python scripts/evaluate_skillspector.py \
  --reports-dir artifacts/skillspector \
  --policy .abvx/skillspector-policy.yaml \
  --baseline .abvx/skillspector-baseline.json

Validate a local skills directory:

abvx-skills validate ~/.codex/skills

Structural validation and security audit are separate gates. The validator checks required files, frontmatter, directory/name alignment, TODO placeholders, cards, UI metadata, and basic secret patterns.

Release

Build and check the package locally:

python -m pip install --upgrade build twine
python -m build
python -m twine check dist/*

Publish flow:

• Run the publish GitHub Actions workflow with repository=testpypi for a dry run against TestPyPI.
• Create a GitHub release, or run the same workflow with repository=pypi, to publish to PyPI.
• Configure trusted publishing for both pypi and testpypi environments in the package index before the first release.
• Repository head is version 0.10.0, adding html-diagram-artifact and html-brief-artifact.
• The latest published package may lag behind repository head until the next PyPI/TestPyPI publish.

Philosophy

• Keep always-loaded context small.
• Prefer procedural rules over vague advice.
• Make skills easy to audit in diffs.
• Attribute upstream inspiration.
• Pair useful automation with risk gates and verification.

See docs/abvx-skillpack-profile.md for the repository standard.

Attribution

Several skills are inspired by public work from the broader agent tooling ecosystem. See ATTRIBUTION.md.

License

MIT. See LICENSE.