weak-signal-synthesizer

43

OneWave-AI

Identify EMERGING trends by connecting dots across unrelated sources. Monitor niche communities, academic research, GitHub, patents, funding, regulatory changes. Predict what will trend in 3-6 months based on weak signals.

update-docs

35

knowsuchagency

Update documentation files (README.md, CLAUDE.md, assistant-knowledge.ts) based on code changes since they were last committed. Stops if git status is dirty.

plan-refiner

33

ddobrin

Expertise in refining architectural plans based on user feedback or new requirements. Use when the user asks to "update the plan", "change the plan", or "refine the strategy".

consult-spec

33

blockscout

TRIGGER CONDITIONS - invoke this skill when ANY of these apply: User-triggered (explicit request): - User mentions "specification", "SPEC", "SPEC.md", "spec requirements" - User asks to "verify with spec", "confirm with specification", "check requirements" - User requests "authoritative requirements" or "source of truth" Agent self-triggered (during reasoning): - Before implementing any feature or making code changes - When verifying technical requirements or constraints - When making architectural or design decisions - When you need unbiased guidance not influenced by current implementation - When encountering conflicting information and need ground truth PURPOSE: Consults SPEC.md through an isolated subagent that ONLY reads the specification, never implementation code. This ensures guidance is based on authoritative requirements, not potentially incorrect existing code.

validate

31

Gricha Perry Validate

Run validation checks - determines whether to use fast (validate) or full (validate:full) based on changed files

Gemini Checkpoint Management

31

melodic-software

Central authority for Gemini CLI checkpointing. Covers git-based file snapshots, automatic state saving, the /restore command, and rollback. Use when enabling checkpointing, restoring previous states, undoing changes, or planning experimental workflows with Gemini. Delegates 100% to gemini-cli-docs for official documentation.

smart-test

28

rysweet

Intelligent test selection based on code changes. Maps source files to tests via import analysis, implements tiered testing (fast < 1 min, impacted < 5 min, full suite), and tracks test reliability. Use when running tests after code changes to optimize feedback loops and CI time.

changelogs

27

TiendaNube

Update CHANGELOG.md files based on changes made in the current branch. Use when the user asks to update changelogs, document changes, or prepare release notes.

plan-builder

27

majesticlabs-dev

Write implementation plans with appropriate templates based on complexity. Use when planning features or changes. Provides minimal, standard, and full templates for different scope levels.

benchmark-advisor

26

wildcard

Suggests which benchmarks to run based on code changes

review-to-merge

26

jamesjlundin

Structured implementer-verifier-reviewer pipeline for high-quality code. Artifact-based handoffs between roles. Use when needing rigorous review process, handoff between roles, or review pipeline for critical changes.

threat-modelling

22

willvelida

Analyse repositories and deployed cloud infrastructure to produce STRIDE-based threat model documents with Mermaid architecture diagrams, prioritised threats, and recommendations. Use when a user asks to create a threat model, identify threats, assess attack surfaces, review an existing threat model, or update a threat model after system changes.

grey-haven-plugin-audit

20

greyhaven-ai

Comprehensive Claude Code plugin auditing skill for validating structure, detecting deprecated patterns, and recommending best practices based on the latest changelog. Use when auditing plugins, checking for deprecations, validating plugin structure, preparing plugins for release, or ensuring compatibility with recent Claude Code versions. Triggers: 'audit plugin', 'check plugin health', 'validate skill', 'plugin deprecation', 'changelog compatibility', 'plugin best practices'.

pw-danger-gemini-web

20

plugins-world

Text and image generation using a reverse-engineered Gemini Web API. Core capabilities: - Text generation: Generate text responses using Gemini models - Image generation: Generate images from text prompts and save them locally - Visual input: Support reference images for image-to-image or vision-guided text generation - Multi-turn conversation: Maintain conversational context via sessionId When to use: - When you need to generate high-quality AI images (cover art, in-article images, illustrations, etc.) - When you need text generation using Gemini models - When you need to generate variants or descriptions based on reference images - As an image generation backend for other skills (pw-cover-image, pw-redbook-image) Not suitable for: - Production environments that require official API support and guaranteed stability - Critical business processes sensitive to API changes - High-volume or high-frequency batch calls (may trigger rate limiting) Important reminders: - First use requires the user to accept a disclaimer - Google account authentication is required (automatically opens the browser to sign in) - Access from mainland China requires configuring a proxy - This is an unofficial API and may stop working at any time

strategic-influence-characters

19

samarv

Select a communication "character" and influence speed based on neurobiological triggers to drive alignment. Use this when pitching a vision that stakeholders find "inconceivable," when unblocking a stalled decision, or when you need to accelerate team change without triggering the "safety system" (fight/flight).

prd-update-progress

18

wiggitywhitney

Update PRD progress based on git commits and code changes, enhanced by conversation context

prd-update-decisions

18

wiggitywhitney

Update PRD based on design decisions and strategic changes made during conversations

changelog-last-tag

18

Memcrab

Generate GitHub release notes or changelog text from git commits since the latest tag (or a specified tag). Use when asked to draft a "What's Changed" section or release notes based on commit history since the last tagged release.

doc-updater

17

Till-Crazy-Tears-Us-Apart

Update core documentation based on code changes referenced in CLAUDE.md

architecture-analysis

16

front-depiction

Architectural dependency analysis and impact assessment. Use for: (1) Blast radius - who depends on a service, what breaks if I change it; (2) Dependency tree - what does a service depend on (ancestors/upstream); (3) Root cause analysis - find shared dependencies when multiple services fail; (4) Architecture metrics - coupling (density), depth (diameter), connectivity; (5) Domain discovery - identify module boundaries via cut vertices; (6) Hot services - critical infrastructure with many dependents; (7) Impact assessment before changes; (8) Debugging cascading failures; (9) Identifying god services, tight coupling, deep hierarchies. Provides graph-based analysis via CLI commands: analyze, blast-radius, ancestors, common-ancestors, metrics, domains, hot-services. All agents can use this for architectural questions.

Write App Change Log

15

AnySoftKeyboard

Generates and updates the latest app changelog based on git history since the last version tag.

create-review-checklist

14

HomericIntelligence

Generate review checklists for different change types. Use to customize review focus based on what was changed.

responsive-adaptive

12

dylantarre

Use when building context-dependent animations - duration that changes based on device, distance, user preference, or interaction context

git-workflow

12

samhvw8

Git workflow management with atomic commit principles. Capabilities: commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits. Actions: commit, push, pull, merge, rebase, branch, stage, stash git operations. Keywords: git commit, git push, git pull, git merge, git rebase, git branch, git stash, atomic commit, commit message, conventional commits, branching strategy, GitFlow, trunk-based, PR, pull request, code review, git history, cherry-pick, squash, amend, interactive rebase, staged changes. Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes.

condition-based-waiting

12

hamr0

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

GitHub Release Workflow

12

SSujitX

Complete GitHub Actions workflow for automated releases with CHANGELOG-based versioning

iterate-plan

11

mhylle

Update existing implementation plans through user feedback with thorough research and validation. Also migrates old checkbox-based plans to the new Task tools system. This skill should be used when iterating on implementation plans, updating plans based on new requirements, refining technical approaches in existing plans, migrating old plans to Task tools, or when the user wants to modify a previously created plan file. Triggers on requests like "update the plan", "change the implementation approach", "iterate on this plan", "migrate to new system", or when feedback is provided about an existing plan document.

State Design Pattern

10

krzysztofsurdy

Behavioral pattern that allows objects to change behavior when their internal state changes. The object appears to change its class. Use when an object's behavior depends on state and must change at runtime based on that state.

test-tier-selection

10

laurigates

Automatic selection of appropriate test tiers based on change scope. Guides unit tests for small changes, full suite for larger changes. Use when running tests, discussing testing strategy, or after code modifications.

git-commit-workflow

10

laurigates

Commit message conventions, staging practices, and commit best practices. Covers conventional commits, explicit staging workflow, logical change grouping, humble fact-based communication style, and automatic issue detection. Use when user mentions committing changes, writing commit messages, git add, git commit, staging files, or conventional commit format.

changelog-review

10

laurigates

Analyze Claude Code changelog for changes that impact plugin development. Use when checking for new features, breaking changes, or opportunities to improve plugins based on Claude Code updates.

documenting-code

10

alexei-led

Update project documentation based on recent changes. Use when user says "update docs", "document", "add documentation", "update readme", "write docs", or wants to improve documentation.

change-type

9

nozomi-koborinai

Classify a change set as behavior vs structure, then recommend the correct PR label (change:behavior or change:structure) and the appropriate local/CI checks. Use when the user asks whether a change is a behavior change or a structure change, what label to apply, or how CI/testing should differ based on change type.

commit

9

agoodway

Generate a professional git commit message based on changes

update-docs

9

Wizard1209

Updates CLAUDE.md and other project docs based on recent changes. Use when user says "update docs", "add to CLAUDE.md", "document this", or runs /update-docs command.

update-changelog

9

Wizard1209

Updates notes/changelog.md based on git history. Use when user says "update changelog", "changelog entry", "release version", "release X.Y.Z", or runs /update-changelog.

build

9

gpshead

Use this skill when you need to compile CPython, run tests, verify your changes work, check if a fix is correct, or debug test failures. Covers building from source with ./configure and make, ccache for faster rebuilds, Argument Clinic regeneration, and the unittest-based test system (NOT pytest). Essential for any task that requires running code or tests.

reflection

8

ruska-ai

Meta-improvement skill that analyzes conversation context and uncommitted git changes to propose improvements to the AI agent ecosystem itself (agents, skills, commands). Use when the user asks to reflect on the conversation, improve the agent ecosystem, or optimize workflows based on patterns observed. This skill ALWAYS acts as supervisor first, producing an initial analysis report, then spawns specialized builder agents based on user-approved plan. Always requires user approval before making changes.

refactor-planner

8

sjmyuan

Analyze refactoring needs and generate detailed, step-by-step TDD-based refactoring plans. Handles code cleanup, architecture improvements, technical debt, and code quality enhancements. Use when users request refactoring, code improvements, structural changes, or cleanup tasks. This skill produces a plan but does not execute changes—pair with plan-executor for implementation.

git-flow

8

YuniorGlez

Senior Workflow Architect. Master of Trunk-Based Development, Stacked Changes, and 2026 Branching Strategies.

threat-model-generation

8

Factory-AI

Generate a STRIDE-based security threat model for a repository. Use when setting up security monitoring, after architecture changes, or for security audits.

bug-fix-planner

8

sjmyuan

Diagnose bug root causes and generate detailed, step-by-step TDD-based bug fix plans. Use this skill when users report bugs, unexpected behavior, or defects. This skill produces a plan but does not execute changes—pair with plan-executor for implementation.

feature-implementation-planner

8

sjmyuan

Clarify feature requirements and generate detailed, step-by-step TDD-based implementation plans for new functionality. Breaks down requirements into testable tasks with validation steps. Use when users request new features, enhancements, or functionality additions. This skill produces a plan but does not execute changes—pair with plan-executor for implementation.

code-review

7

samhvw8

Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.

tmp-filesystem-watcher

7

plurigrid

Real-time filesystem watcher for /tmp using Babashka fs. Monitors file creation, modification, and deletion events. Emits topological events based on filesystem changes. Part of music-topos consciousness bootstrap.

branch-comparison

7

CongDon1207

Use when the user asks to compare branches, analyze git diffs, review changes between branches, update specifications based on code changes, or analyze what changed. Triggers on keywords like "compare branches", "git diff", "what changed", "branch comparison", "code changes", "spec update".

git-commit

7

XuNeo

Commit changes with NuttX checkpatch.sh validation, automatic sign-off, component-based message format, and JIRA linking. Use when the user asks to create a git commit (for example: commit, git commit, commit diff, commit current, commit changes, submit code, submit changes, /commit, /git-commit).

code-review

6

joaquimscosta

Conduct comprehensive code reviews using the Pragmatic Quality framework with confidence-based filtering, hierarchical analysis (architecture, security, maintainability, testing, performance), and PR-level risk assessment. Use when user runs /code-review, /review:code-review, requests a "code review", "review my changes", "PR review", or mentions "review diff", "review branch".