Claude skills and agent skills

LesaniSkill

design-an-interface

Lesani/skills/skills/deprecated/design-an-interface/SKILL.md

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Often used withdecision-mapping·ubiquitous-language·batch-grill-me

LesaniSkill

qa

Lesani/skills/skills/deprecated/qa/SKILL.md

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

LesaniSkill

request-refactor-plan

Lesani/skills/skills/deprecated/request-refactor-plan/SKILL.md

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

Often used withubiquitous-language·batch-grill-me·prd-to-plan

LesaniSkill

ubiquitous-language

Lesani/skills/skills/deprecated/ubiquitous-language/SKILL.md

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

Often used withrequest-refactor-plan·prd-to-plan·scaffold-exercises

LesaniSkill

astra

Lesani/skills/skills/engineering/astra/SKILL.md

Coordinate complex work with Astra designing and reviewing, and Sol agents planning and implementing whole feature slices that are tested as they are built.

LesaniSkill

codebase-design

Lesani/skills/skills/engineering/codebase-design/SKILL.md

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Often used withdecision-mapping·setup-ts-deep-modules·loop-me

LesaniSkill

code-review

Lesani/skills/skills/engineering/code-review/SKILL.md

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Often used withadd-new-model

LesaniSkill

diagnose

Lesani/skills/skills/engineering/diagnose/SKILL.md

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Often used withzoom-out·to-issues·write-a-skill

LesaniSkill

domain-modeling

Lesani/skills/skills/engineering/domain-modeling/SKILL.md

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Often used withdecision-mapping·setup-ts-deep-modules·loop-me

LesaniSkill

fable-hybrid

Lesani/skills/skills/engineering/fable-hybrid/SKILL.md

Fable with a second model family - the Claude main session designs, Claude subagents plan and implement, GPT Sol reviews every plan and every slice diff and writes the user-facing text. Use when the user invokes /fable-hybrid or asks for Claude implementation with Sol review.

LesaniSkill

fable

Lesani/skills/skills/engineering/fable/SKILL.md

Tiered delegation workflow that reserves the top model for decisions - the main session designs and records binding decisions, opus subagents do fine planning, opus/sonnet subagents implement. Use when implementing a non-trivial feature or change, or when the user invokes /fable or asks to "plan with opus and implement with opus/sonnet".

LesaniSkill

from-issues

Lesani/skills/skills/engineering/from-issues/SKILL.md

Execute issue-tracker-resident issues end-to-end via subagents — picks the next ready issue (blockers closed, triage clear), runs implementer + spec-review + code-quality-review per SDD, opens a PR, and posts review summaries back to the issue. Use when the user says "work the next issue", "do issue #N", "execute the issues", or wants AFK execution of a triaged backlog. Skip for issues that haven't been triaged or whose blockers aren't closed.

LesaniSkill

grill-with-docs

Lesani/skills/skills/engineering/grill-with-docs/SKILL.md

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Often used withdecision-mapping·setup-matt-pocock-skills·setup-ts-deep-modules

LesaniSkill

implement

Lesani/skills/skills/engineering/implement/SKILL.md

Implement a piece of work based on a PRD or set of issues.

Often used withsetup-ts-deep-modules·ask-matt·to-questionnaire

LesaniSkill

improve-codebase-architecture

Lesani/skills/skills/engineering/improve-codebase-architecture/SKILL.md

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, make a codebase more testable and AI-navigable, or plan and execute a large architectural rework.

Often used withdecision-mapping·migrate-to-shoehorn·setup-ts-deep-modules

LesaniDeletes or force-pushesSkill

merge-down

Lesani/skills/skills/engineering/merge-down/SKILL.md

Merge multiple feature branches and worktrees down into a single integration branch, resolve the conflicts that always show up (sln files, formatting, modify/delete), then clean up merged worktrees, branches, and stashes. Use when the user says "merge everything down", "consolidate branches", "clean up worktrees", or wants to unify divergent topic branches into dev/main.

LesaniSkill

prototype

Lesani/skills/skills/engineering/prototype/SKILL.md

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Often used withsoak-test·playtest-report·team-live-ops

LesaniSkill

red-team

Lesani/skills/skills/engineering/red-team/SKILL.md

Take apart any target — an app, a feature, a plan, a document, a decision — with parallel adversarial agents. A blue-team rebuttal pass then kills the weak findings, and only the survivors reach the user. Use when the user says "red team this", "attack this", "tear this apart", "stress-test this", or asks for an adversarial review of anything.

LesaniSkill

research

Lesani/skills/skills/engineering/research/SKILL.md

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Often used withdaily-arxiv·Problem-Solving Techniques·setup-ts-deep-modules

LesaniReads credentialsSkill

setup-foundry-claude

Lesani/skills/skills/engineering/setup-foundry-claude/SKILL.md

Set up a shell wrapper that launches Claude Code against Azure AI Foundry without leaking provider config into the rest of the shell session, pin the model aliases to current models, and add a ccstatusline badge showing when an override endpoint is active. Covers PowerShell (Windows) and bash/zsh (Linux/macOS), plus an optional LiteLLM proxy so the same wrapper can run non-Anthropic models (GPT etc.) hosted on the Foundry resource, and a desktop launcher entry. Use when Claude Code should run against Foundry, when `opus`/`sonnet` resolve to older models than expected, or when a provider wrapper contaminates later `claude` runs in the same terminal.