paiml

Generates comprehensive, LLM-optimized codebase context using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Starting work on unfamiliar codebases - Onboarding to new projects or repositories - Need quick understanding of project…

Analyzes polyglot codebases with multiple programming languages using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Working with projects containing multiple programming languages - Assessing cross-language integration patterns and…

Analyzes code quality, complexity, and technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - User mentions "code quality", "complexity", "technical debt", or "maintainability" - Reviewing code or conducting code review -…

Provides automated refactoring suggestions and complexity reduction strategies using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - User requests code refactoring, optimization, or improvement - Complexity analysis reveals high-complexity…

Tracks and manages technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - User asks about technical debt, TODO comments, or code quality issues - Planning sprint work and need to prioritize debt repayment - Conducting code…

Adversarial PR review that must show HOW it knows — five consultations (one of them a reviewing agent from a different vendor), a three-state availability encoding no prose can fake, and a signed in-toto receipt whose own guard can reject it

Dogfood the aprender release surface — derive every interface from the built binaries, measure gate coverage against the surface ledger, exercise the covered set, and emit a go/no-go receipt

Sovereign-stack PRE-RELEASE protocol. Run this BEFORE generating a GitHub or crates.io release of any Rust crate in the fleet (copia, forjar, pmat, trueno, aprender, …). It runs every local release gate (fmt, clippy, tests, ≥95% coverage, cargo-deny, provable…

Pre-release QA for apr-cli — runs all gates that prevent crates.io publish breakage

Find which provable-contracts YAML contracts a Hugging Face model needs, create missing contracts, generate Rust artifacts, and implement all stubs. Triggers on: "find contracts", "contract coverage", "what contracts does X need", "which contracts for", HF…

Implementation blueprint from spike experiments — SEP-2640 Skills support AND the schema-server toolkit lift (config-driven MCP servers for SQL / GraphQL / OpenAPI backends). Requirements, proven patterns, multi-dialect SQL connector trait, two-axis Skills…

Help a developer design a config.toml for a PMCP schema-server toolkit deployment, applying the Pareto principle to curated tools and code-mode policy.

Generate validated GraphQL queries against this server's schema

Demonstrates the simplest possible MCP skill

Process customer refund requests per company policy

Systematic coverage gap analysis and test writing for the APR Model QA Playbook. Uses pmat query --coverage-gaps for highest-ROI targets, provides test patterns for each crate (proptest for gen, Evidence assertions for runner, MQS scoring for report), handles…

Diagnoses and fixes G0-G4 gateway failures in model qualification runs. Interprets MQS zero-scores, evidence JSON, and stderr output. Covers LAYOUT-002 violations, config.json mismatches, garbage detection, crash analysis, and all 5 contract invariants (I-1…

Guides end-to-end HuggingFace model certification: playbook creation from templates, running qualification at any tier (Smoke/MVP/Quick/Standard/Deep), collecting evidence, computing MQS scores with G0-G4 gateways, updating models.csv, and syncing the README…

Safely transposes an image, mirroring it across the top-left/bottom-right diagonal.

Remove the star and its shadow from a pyramid still and transpose the result, in one step, using ImageMagick and bash. Use when asked to clean up, transpose, flip, reorient, or run the full pipeline on one of this project's pyramid images. Runs…

The gate every bashrs lint-rule change passes before a PR is opened. Two halves — an ADVERSARIAL review that tries to break the fix by hunting the false negative it may have introduced, and a CRUX competitive analysis that checks the fix against how…

Dogfood forjar — rebuild, install, exercise every command, prove the C1–C10 claims and contracts against a sandboxed stack, check quality, file bugs

QA the installed apr CLI binary — pull a model, test every subcommand, hunt for bugs, file GitHub issues. Use when asked to QA apr, test apr, or check apr-cli.