context-engineering skills

2,017 tagged context-engineering, measured the same way as everything else here.

Browse within: spec-driven-development 203meta-prompting 168agent-memory 148knowledge-graph 143apex 130salesforce 130agentic-coding 128codex-cli 114context-management 111coding-agents 79bi-temporal 76chroma 76deterministic-ai 76engineering 76

rpce-merge-pr-batch

25

repoprompt/repoprompt-ce

Skill Claude CodeCodex

Safely process an explicitly ordered batch of RepoPrompt CE pull requests end to end: preserve a dirty original checkout, isolate each PR in an external disposable worktree, use window- and context-scoped CE rpce-cli Agent Mode review, repair and validate, require exact-head hosted checks, merge with merge commits…

not rated 889 4d ago A 128 tokens original Apache-2.0

rpce-test-quality

26

repoprompt/repoprompt-ce

Skill Claude CodeCodex

Select, design, review, consolidate, or remove RepoPrompt CE tests, diagnostic harnesses, and smoke checks by regression value and maintenance cost. Use when the task centers on test, diagnostic, or smoke coverage, including whether a single regression test is worth committing. Do not use for feature or bug-fix work…

not rated 889 4d ago A 83 tokens original Apache-2.0

tura

27

Tura-AI/tura

Skill Claude CodeCodex

Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.

not rated 609 +3 14d ago A 46 tokens AGPL-3.0

drawio-chart

28

Snailclimb/AIGuide

Skill Claude CodeCodex

A tool for creating and exporting Draw.io diagrams. Draw.io, also called diagrams.net, is a visual editor for flowcharts, architecture diagrams and other technical drawings.

not rated 581 +7 1mo ago A 97 tokens

Snailclimb/AIGuide

Skill Claude CodeCodex

A set of conventions for writing, reviewing, refactoring and explaining Java and Spring Boot code. It covers common application layers such as controllers, services and data-access code, while allowing repository-specific rules to take priority.

not rated 581 +7 1mo ago A 144 tokens

codex-fable5

30

baskduf/FableCodex

Skill Claude CodeCodex

Apply a Claude Fable 5 inspired operating style inside Codex. Use when the user asks to make Codex act like Fable, Fable5, fablize, or Value-for-Fable/VFF; convert Anthropic or Claude system-prompt/tool instructions to Codex; set up a Fable-style tool-first workflow with goal gates, investigation, verification…

not rated 437 +1 1mo ago A 123 tokens AGPL-3.0

atomicmemory-cli

31

atomicstrata/atomicmemory

Skill Claude CodeCodex

Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.

not rated 428 yesterday A 26 tokens

git-branch-cleanup

32

gotalab/skillport

Skill Claude CodeCodex

Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.

not rated 409 2mo ago A 66 tokens original MIT

opus-4-5-migration

33

gotalab/skillport

Skill Claude CodeCodex

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

not rated 409 2mo ago A 97 tokens original MIT

skill-evaluator

34

gotalab/skillport

Skill Claude CodeCodex

Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.

not rated 409 2mo ago A 61 tokens original MIT

tilth

35

jahala/tilth

Skill Claude CodeCodex

Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…

not rated 333 4d ago A 95 tokens original MIT

static

36

Fergana-Labs/stash

Skill Claude CodeCodex

Stash is your personal home for agent work. Everything you create is scoped to your account — it is yours alone, with nothing to pick or set up first. Your Stash has three primary surfaces.

not rated 327 5d ago A 0 tokens original MIT

brief

37

Fergana-Labs/stash

Skill Claude CodeCodex

Brief the user on what they saved in a period — the thread running through it, not a list.

not rated 327 5d ago A 23 tokens original MIT

slides

38

Fergana-Labs/stash

Skill Claude CodeCodex

How to build presentation slide decks as HTML pages. Covers the slide format, canvas dimensions, and recommended libraries.

not rated 327 5d ago A 24 tokens original MIT

exchange-recovery

39

openbkn-ai/bkn-foundry

Skill Claude CodeCodex

A recovery workflow for Exchange servers, which are systems used for organisational email and calendars. It covers planning a restoration from backups, creating a recovery job, and checking whether the service works afterward.

not rated 322 4d ago A 0 tokens

k8s-network

40

openbkn-ai/bkn-foundry

Skill Claude CodeCodex

A knowledge network describing the main resource relationships in a Kubernetes cluster. Kubernetes is a system for running and managing containerised applications across machines.

not rated 322 4d ago A 0 tokens

supplychain-hd

41

openbkn-ai/bkn-foundry

Skill Claude CodeCodex

A knowledge guide for tracing a product supply process from demand estimates through suppliers.

not rated 322 4d ago A 0 tokens

PackmindHub/packmind

Skill Claude CodeCodex

Guide for writing and running new Playwright end-to-end tests in the apps/e2e-tests/ directory of the Packmind monorepo. Use this skill whenever you add or modify a spec that drives the real frontend and API — for example testing a user flow, a new page/route, a feature behind a flag, or a UI behavior end-to-end.…

not rated 308 today A 175 tokens original Apache-2.0

feature-flags-audit

43

PackmindHub/packmind

Skill Claude CodeCodex

Audit and inventory all feature flags declared in the Packmind codebase. Use when the user asks to list, audit, review, or inventory feature flags, asks which flags are active, wants to know what a flag gates, or asks which flags are opened to a given domain/user. Produces a synthetic markdown table with each flag…

not rated 308 today A 93 tokens original Apache-2.0

PackmindHub/packmind

Skill Claude CodeCodex

Guide for creating coding standards via the Packmind CLI. This skill should be used when users want to create a new coding standard (or add rules to an existing standard) that captures team conventions, best practices, or coding guidelines for distribution to GitLab Duo.

not rated 308 today A 57 tokens original Apache-2.0

pr-reviewer

45

Fu-Jie/openwebui-extensions

Skill Claude CodeCodex

Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.

not rated 302 +1 1mo ago A 41 tokens original MIT

release-finalizer

46

Fu-Jie/openwebui-extensions

Skill Claude CodeCodex

Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.

not rated 302 +1 1mo ago A 42 tokens original MIT

Fu-Jie/openwebui-extensions

Skill Claude CodeCodex

Use when inspecting UI bugs in OpenWebUI plugins, taking screenshots of plugin output, capturing console errors, testing Action/Filter/Pipe plugins in the chat interface, or verifying plugin installation in the Admin panel. Triggered by: plugin UI bug, Action HTML output, screenshot, console error, plugin not working…

not rated 302 +1 1mo ago A 80 tokens original MIT

git-commit

48

adongwanai/learn-workbuddy

Skill Claude CodeCodex

A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.

not rated 255 4d ago A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: