code-intelligence skills

tyler-mitchell/type-atlas

Skill Claude CodeCodex

Record and release Type Atlas package changes through the repository's local Bumpy workflow.

tyler-mitchell/type-atlas

Skill Claude CodeCodex

How to develop Type Atlas. You build the instrument you perceive through, so the work is driven by your own genuine need to understand something — and the instrument's failures to answer you are the design input.

RSafargalin/sextant

Skill Claude CodeCodex

Part of sextant

Use when navigating or changing Swift, Objective-C, C or C++ code — finding where a symbol is defined, who calls it, what implements a protocol, what a change would break, what a package or type exposes, or what changed between revisions. Says when to ask the sextant MCP server instead of running Grep, Glob or reading…

Attemainio/dotnet-toolkit

Skill Claude CodeCodex

Part of dotnet-toolkit

Use when auditing this plugin's own docs, skills, agents, rules, hooks, CLAUDE.md and README.md — three axes at once. (1) Do they match the actual MCP tool implementation under src/DotnetToolkit.McpServer? Run after adding, removing, renaming, or changing the signature/return shape/[Description] of a tool, or after…

Attemainio/dotnet-toolkit

Skill Claude CodeCodex

Part of dotnet-toolkit

Use when asked what dotnet-toolkit actually costs compared to doing the same work with plain tools — "is this plugin worth it", "benchmark the toolkit against grep", "how much does searchindex really save over Grep/Read", "measure the MCP tools against cat/ls/find", "does this pay for itself on Windows/PowerShell"…

Attemainio/dotnet-toolkit

Skill Claude CodeCodex

Part of dotnet-toolkit

Use when reading or navigating C#/.NET code — find or search for a class, interface, method, property or field; read a symbol's source; look up who calls something or what implements it; trace a call tree or a path between two functions; see what is callable at a line; inspect a base chain or project references; find…

lagrahhn/codeGraph-branch

Skill Claude CodeCodex

Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.

lagrahhn/codeGraph-branch

Skill Claude CodeCodex

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.

srobinson/fmm

Skill Claude CodeCodex

MCP-first code navigation for this codebase. Use before any symbol lookup, file search, dependency trace, impact analysis, or codebase evaluation — replaces grep/glob/read with O(1) fmm tool calls. Trigger when: starting any task involving unfamiliar code, navigating code structure, finding where a symbol is defined…

vcth4nh/idesense

Skill Claude CodeCodex

Guide for using JetBrains IdeSense tools for code navigation and analysis (plus the retained rename/move refactorings). TRIGGER: When ANY of these MCP tools are available in the current session: idefindusages, idefinddefinition, idefindclass, idefindfile, idesearchtext, idediagnostics, ideexplainsymbol…

IronAdamant/Chisel

Skill Claude CodeCodex

Run Chisel test-impact analysis on any git project — which tests to run after a change, what's risky, what's untested. Use when the user asks to run chisel, find impacted tests, check risk or coverage gaps, or after a batch of code edits in a project with a .chisel/ DB (or to bootstrap one with chisel analyze).

naranor/code-intelligence-skill

Skill Claude CodeCodex

Universal, safe, and professional code modification and refactoring environment for 50+ languages. Use when editing source files to prevent syntax breakage, perform project-wide type-aware renames (LSP), or distill large command output to save context window tokens.

esneiderbravo/speclaw

Skill Claude CodeCodex

Finalize a completed change — sync its specs into canonical, then move it to the archive. Use when a change is done and merged-ready: "archive the change", "finalize X", "close out the change". Part of speclaw's lawbook module (draft → build → sync → archive). Archiving belongs in the same PR that implements the…

esneiderbravo/speclaw

Skill Claude CodeCodex

Draft a new spec-driven change — propose a ceremony level, then write only the artifacts that level needs — before writing any code. Use when the user wants to start, plan, or propose a new feature, fix, or refactor: "draft a change for X", "propose X", "let's plan X", "spec out X", "new change". Part of speclaw's…

esneiderbravo/speclaw

Skill Claude CodeCodex

Enter explore mode — a thinking partner for investigating an idea, a problem, or the codebase before or during a change. Use when the user wants to think something through, understand how something works, or clarify requirements before committing to a spec: "help me think through X", "how does X work", "explore X"…

lenhonbp/codex-memory-intelligence

Skill Claude CodeCodex

Apply the CMI Agent Operating System contract for substantive work: orient with explicit goal, scope and authorization boundaries; observe before editing; capture typed evidence; diagnose before symptom fixes; prioritize explicitly; implement the smallest coherent change; verify the original journey or contract…

lenhonbp/codex-memory-intelligence

Skill Claude CodeCodex

Resume known unfinished project work from durable CMI session handoff evidence, current open findings, current active Changes, and a fresh repository baseline re-check. Use when the user asks to continue, resume, pick up previous work, làm tiếp, or identify what unfinished CMI-tracked work remains. Strictly read-only…

lenhonbp/codex-memory-intelligence

Skill Claude CodeCodex

Provide a concise read-only assessment of whether CMI project evidence is currently usable, stale, missing, degraded, or blocked before relying on it. Use when the user asks if CMI is healthy, whether intelligence/evidence is current, why CMI is blocked, if the graph/index is stale, or to check evidence health before…

Nolane-x/Nolane-habitat

Skill Claude CodeCodex

Maintain, debug, test, document, package, or release the Nolane Habitat repository. Trigger when work changes Habitat workspace lifecycle, storage, semantic providers, mutation safety, MCP, Observatory, tests, Codex integration, or release artifacts.

Nolane-x/Nolane-habitat

Skill Claude CodeCodex

Use Nolane Habitat to orient, inspect, change, verify, or checkpoint work in a software project through its MCP workspace. Trigger when a user asks for semantic project context, governed code changes, task checkpoints, or Nolane Habitat MCP tools.

The-Code-Registry/mcp-server

Skill Claude CodeCodex

Use The Code Registry MCP server to create accounts, create code vaults, run LOCALAGENT analysis, poll completion correctly, and present business-focused code intelligence for any purpose including due diligence, security, and tech debt workflows.

HelloThisWorld/open-mind

Skill Claude CodeCodex

Enrich an Open Mind project's glossary with standard term definitions from Wikipedia. For each already-extracted term, look up its authoritative Wikipedia definition, tidy it, and write it back to the glossary as a separate, attributed field; terms with no confident match keep their verbatim in-project definition. Use…

HelloThisWorld/open-mind

Skill Claude CodeCodex

Route a request to exactly one Open Mind capability (glossary / structure / search). A local model may decide when ready, but its choice is validated against the known capability set and falls back to a deterministic if-else floor — the model never invents or overrides a capability unchecked.

HelloThisWorld/open-mind

Skill Claude CodeCodex

Extract a project's term/acronym definitions VERBATIM from its own authoritative sources, each with file:line provenance and a grounded usage profile; resolve a term deterministically or return an honest "not found" — never generated.