effort-estimation
Calibrate engineering effort estimates for git commits using a 5-tier rubric. Use whenever you need to translate a diff into an hours estimate for a senior engineer working with or without an AI coding assistant.
rune-diff
Compare a RUNE specification against its implementation to detect drift. Use when verifying that code still matches its spec after modifications, or when auditing existing implementations against their contracts.
aws-cdk
Provides AWS CDK TypeScript patterns for defining, validating, and deploying AWS infrastructure as code. Use when creating CDK apps, stacks, and reusable constructs, modeling serverless or VPC-based architectures, applying IAM and encryption defaults, or testing and reviewing `cdk synth`, `cdk diff`, and `cdk deploy` changes. Triggers include "aws cdk typescript", "create cdk app", "cdk stack", "cdk construct", "cdk deploy", and "cdk test".
codex-implementation-loop
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex to write code, mentions handing off / delegating implementation to Codex, asks to work through a plan or spec unit-by-unit with Codex doing the coding, or wants a review-and-merge loop wrapped around Codex output â and also when resuming such a loop ("keep going", "next unit", "继ç»ä¸ä¸ä¸ª"). It encodes constraints that are expensive to rediscover: Codex runs in the real environment with effectively read-only git, must not be pointed at a full test suite by default, accepts only specific --effort values, and its self-report is a claim rather than evidence.
pr-describe
Write a pull-request title and body from the current branch's commits and diff against the base branch. Invoke when the user asks to open a PR, draft a PR description, or summarize a branch.
Diffgrab
Web page change tracking with structured diffs. markgrab + snapgrab integration.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Aider, Cursor, OpenCode, Oh My Pi, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.
Changed files on this branch vs its base
git diff --name-status $(git merge-base HEAD main)..HEAD
intent
Extract the underlying intent behind a request, issue, PR, or diff. Focus on problem and desired outcome; do not propose implementation, testing strategy, or rollout plans.
transform
Use this to author and change a dbt project: bootstrap a new dbt project in a repo that has none (`transform init`), write or refactor dbt model SQL from staging to marts, add tests and docs in schema.yml, manage dependencies, and define or update the semantic layer (dbt semantic models / MetricFlow: entities, dimensions, measures, metrics). Trigger it for requests like "set up a dbt project in this repo", "build a staging model for this table", "refactor this model", "add tests to this model", "create a mart for X", "define a revenue metric", or "add a dimension to this entity". Every change is a reviewable diff to the dbt project; any warehouse build is dev-target only, gated, and cost-surfaced first. Do not use it to explore or profile a warehouse (use explore) or to detect drift and reconcile a project that has fallen out of sync (use maintain).
changelog-analyzer
Analyze git commits in a range by examining actual code diffs (not commit titles) and produce a ranked list of improvements and optimizations. Use when the user wants a changelog, wants to summarize recent changes, asks what changed since a commit, or wants to review project progress.
coverage
Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.
antigravity-review
Get a second opinion from Google Antigravity (agy) on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when the user asks to "review with Antigravity", "Antigravity code review", or "ask agy to check my code".
implement-figma-design
Implement a UI component from a Figma design by iterating with visual diff feedback. Use when the user provides a Figma design reference and asks you to build or match it in code.
claude-a11y-audit
Use when reviewing UI diffs, accessibility audits, or flaky UI tests to catch a11y regressions, semantic issues, keyboard/focus problems, and to recommend minimal fixes plus role-based test selectors.
api-diff
Generate an API comparison report between two .NET versions using the RunApiDiff.ps1 script. Invoke when the user asks to run, create, or generate an API diff.
change-walkthrough
Create detailed markdown walkthroughs of code changes. Use when the user asks to "create a walkthrough", "explain the changes", "review recent commits", "document what changed", "walk me through the diff", "summarize my changes", or similar requests for change documentation.
pdf-diff
Visual PDF regression test comparing current Beamer output against a baseline branch. Use when checking if slide changes introduced visual regressions.
release
Run the Harnss release workflow â review staged diff, bump version, commit, tag, push, and create a GitHub release. Use when releasing, bumping version, tagging, or creating a release. Argument: major, minor, or patch.
deepsec
Drive the `oma-deepsec` skill end-to-end. Installs `.deepsec/`, calibrates cost, runs the right scan/process/triage/revalidate/export pass, gates PRs with `process --diff`, writes custom matchers, and routes findings to follow-up specialists.
android-build
Build, test, debug, and preview Android apps inside a ShipIt session. Load when a task touches an Android/Gradle project (Kotlin/Java, build.gradle(.kts), AndroidManifest.xml, res/ layouts, Compose UI). Covers the baked toolchain (JDK/SDK/Gradle), the build â lint â snapshot-test loop, reading snapshot PNG diffs, on-demand SDK installs, and the emulator-as-Compose-service for a live device over adb.
BACH CodeCommander
17 tools for code analysis, JSON repair, encoding fix, format conversion, diff, and regex.
changeset-validation
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.
sourcesage-cli
Generate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run `sage` or `sourcesage` to create `.SourceSageAssets/Repository_summary.md`, analyze the current repository or another local repository, switch the output language between English and Japanese, use `--lite` to keep the summary small, change the output directory, or optionally create a deprecated tag-diff release report with `--diff`.
translation-diff-export
Export a JSON translation patch containing only untranslated or source-changed UniGetUI strings for a target language.
Io.Github.Rog0x/String
String analyzer, diff, templates for AI agents
Message de commit (FR, Conventional Commits)
Tu génères un message de commit Conventional Commits propre en français à partir du diff git.
revdiff
Review git diffs with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in tmux/kitty/wezterm, captures annotations, and addresses them. Activates on "revdiff", "review diff", "annotate diff", "git review with revdiff", "interactive diff review", "revdiff config", "revdiff themes", "revdiff keybindings", "how to configure revdiff", "what themes does revdiff have".
review-fix-pass
Review the current uncommitted diff against the latest review report, apply only high-confidence fixes, and return a structured result for iterative loops.
dotfiles
Review a GitHub pull request, examining the summary, linked resources, and diff
git-commit-creator
Creates properly formatted Git commits following conventional commit standards for the MCPSpy project. Use when asked to commit changes, stage files, or manage git workflows. Has access to git status, diff, checkout, add, and commit commands.
code-change-verification
Verify code changes by identifying correctness, regression, security, and performance risks from diffs or patches, then produce prioritized findings with file/line evidence and concrete fixes. Use when reviewing commits, PRs, and merged patches before/after release.
publish-release
Drive cutting a new testagent release end-to-end: analyze the surface diff against the bump table in RELEASING.md, propose a version, draft three-bucket release notes, tag, watch CI, then publish curated notes.
interactive-testing
Smoke-test the running Lightcode Electron app end-to-end via Chrome DevTools Protocol. Use when the user asks to "smoke test", "test the app", "verify the refactor in the UI", "open the app and click through", or otherwise wants Claude to drive the real running app instead of relying on unit tests. Boots dev server + Electron with CDP enabled, uses raw CDP or agent-browser as appropriate, walks the surfaces most relevant to the current diff (provider selector, ThreadDraftView, ChatPane, ThreadRuntimeRequestPanel, Browser panel), and reports findings with screenshots.
OpenTelemetry Instrumentation Extension
Extend OpenTelemetry instrumentation when new functionality is added to the MCP Gateway. Use when (1) new operations/functions are added, (2) reviewing code for missing instrumentation, (3) user requests otel/telemetry additions, or (4) working with state-changing operations. Analyzes git diff, suggests instrumentation points following project standards in docs/telemetry/README.md, implements with approval, writes tests, updates documentation, and verifies with debug logging and docker logs.
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
repoprompt-tool-guidance-refresh
Update RepoPrompt tool guidance based on MCP/CLI changes across versions. Two-phase workflow - invoke BEFORE upgrading (--pre), then AFTER upgrading (--post). Uses `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh` to detect and diff changes (outputs to `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/`).
PageCrawl
Monitor web pages for changes with AI-powered change detection, diffs, and alerts.
ADD â the orchestration engine
You are the orchestrator. ADD keeps the AI fast *and* safe by fixing direction (spec, scenarios, contract, failing tests) **before** the build, and trusting the result through passing evidence rather than a plausible-looking diff.
check-config-diff
This skill should be used when the user asks to "check config diff", "compare upstream config", "diff rubocop config", "sync with Rails rubocop", or wants to see differences between the upstream Rails .rubocop.yml and this repository's config/rails.yml.
Adaptive context detection â same as code-review-simplify
DIFF_STAT=$(git diff HEAD --stat 2>/dev/null || echo "") if [ -n "$DIFF_STAT" ]; then REF="HEAD" # pre-commit: review uncommitted Builder changes else REF="HEAD~1" # standalone: review last committed change fi DIFF=$(git diff "$REF" --stat) CHANGED_FILES=$(git diff "$REF" --name-only) DIFF_FULL=
adr-drafter
Draft a new ExStruct ADR or propose an update to an existing ADR from an issue, PR, diff, tests, and specs. Use when an ADR is required or recommended and you need a structured draft with context, decision, consequences, and evidence.
pyroscope-dotnet
Summarize an upstream merge PR with diff overview and profiler-related commit log
cypilot
Invoke when user asks to do something with Cypilot, or wants to analyze/validate artifacts, or create/generate/implement anything using Cypilot workflows, or plan phased execution. Core capabilities: workflow routing (plan/analyze/generate/auto-config); deterministic validation (structure, cross-refs, traceability, TOC); codeâartifact traceability with @cpt-* markers; spec coverage measurement; ID search/navigation; init/bootstrap; adapter + registry discovery; auto-configuration of brownfield projects (scan conventions, generate rules); kit management (install/update with file-level diff); TOC generation; agent integrations (Windsurf, Cursor, Claude, Copilot, OpenAI). Kit sdlc: Artifacts: ADR, CODEBASE, DECOMPOSITION, DESIGN, FEATURE, PR-CODE-REVIEW-TEMPLATE, PR-REVIEW, PR-STATUS-REPORT-TEMPLATE, PRD; Workflows: migrate-openspec, pr-review, pr-status.
review-pyrefly-diff
Reviews a comma separated pyrefly diff according to the pyrefly review best practices.
openqodex
Code review for the current change, before it is pushed. One command runs the security, secret, dependency and lint scanners that fit the changed files, a separate reviewer that checks every scanner finding and is given every changed line, and prints the report. Use before every git push, when asked for a code review, a security scan, or to review changes, a diff or a pull request, and when a push was blocked or warned by OpenQodex.
render-topologies
Render all .mmd files to PNG, pixel-diff against main, and open only changed renders as BEFORE/AFTER pairs in Preview. Use after layout or rendering changes to check for visual regressions. Works in worktree mode (fix branch vs main) or standalone mode (current working tree vs main). Companion to the fix-issue skill, which delegates full regression checks here.
advanced-code-quality
Use when going beyond basic linting to enforce advanced Python code quality gates. Triggers on: cognitive complexity, code duplication detection, architectural enforcement, import boundaries, dependency hygiene, test quality beyond coverage, mutation testing, docstring coverage, type coverage, AI-generated code detection, AI slop detection, complexipy, jscpd, import-linter, deptry, diff-cover, mutmut, interrogate, sloppylint, refurb, pylint design checks, wily, radon maintainability, pytestarch, griffe, "bulletproof Python", "tighten quality gates", "advanced quality checks", "beyond ruff and mypy", "catch AI-generated code issues", "code duplication", "architectural boundaries", "dependency drift", "test effectiveness". Complements the code-quality skill (ruff, mypy, xenon, vulture, pre-commit) with 20+ additional tools.
fix-buildkite-ci
Triage and fix failing Buildkite CI checks for RisingWave pull requests by extracting concrete failing tests, diffs, and error messages from Buildkite build/job logs and artifacts, then applying focused code or test fixes. Use when users ask to diagnose red Buildkite checks, investigate flaky/failing CI jobs, understand why a Buildkite build failed, or provide Buildkite/GitHub check URLs and want a concrete fix.
Io.Github.Rog0x/Git
Git log, diff, blame, branch stats for AI agents