Address repeated instructions or recurring corrections by turning rules into automated checks, metadata flags, or scripts. When a rule requires human judgment, make the instruction more prominent and add an example showing the failure to avoid.
中文简介正在准备中。当前显示英语简介。
- Turning repeated corrections into automated checks
- Encoding rules in metadata flags
- Handling recurring issues with runtime checks or scripts
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Collect review feedback and discussion comments from the pull request for the current branch. Get a grouped summary, a prioritized action list, and unresolved questions that need clarification before you proceed.
中文简介正在准备中。当前显示英语简介。
- Prioritizing changes requested in a pull request
- Reviewing feedback scattered across comment threads
- Identifying questions to clarify before making changes
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Revisit an existing design as though a new requirement had been present from the start. Examine affected files, plan the overall redesign, and carry changes through types, documentation, examples, and design rationale in incremental steps.
中文简介正在准备中。当前显示英语简介。
- Integrating a new requirement into an existing design
- Rethinking structure before adding another workaround
- Updating types, documentation, and examples together
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Reviews the current conversation from three perspectives to find reusable lessons and propose concrete skill improvements. It separates findings into accepted, rejected, and backlog items, with user approval required before applying accepted edits.
中文简介正在准备中。当前显示英语简介。
- Reviewing lessons from a completed agent session
- Turning repeated mistakes into skill improvements
- Separating skill edits from structural fixes
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Review code comments in selected files or changes with a dedicated agent, remove accepted findings, and fix underlying problems. It also proposes ways to enforce documented constraints through types, runtime checks, tests, or automated checks.
中文简介正在准备中。当前显示英语简介。
- Reviewing comments in a code change
- Fixing workarounds explained by comments
- Turning documented constraints into automated checks
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Generate several candidate solutions in parallel, compare them against concrete criteria, and choose a base. Combine useful parts from other candidates, then verify the final artifact and document why each major choice was made.
中文简介正在准备中。当前显示英语简介。
- Compare multiple designs before choosing a direction
- Explore different implementations of the same task
- Combine useful elements from competing drafts
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Use repeated failed fixes to question their shared assumption. This principle asks agents to state that assumption, test it with a repeatable check, and follow the evidence before attempting another fix based on it.
中文简介正在准备中。当前显示英语简介。
- Reassess an assumption after repeated failed fixes
- Design a repeatable check for a suspected premise
- Investigate patterns across failures
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Configure which AI models pstack uses for each role, along with reasoning effort, the level of reasoning applied. Detects available models, writes settings for the current environment, and controls the session startup hook where supported.
中文简介正在准备中。当前显示英语简介。
- Assigning AI models to pstack roles
- Updating settings to match available models
- Setting default and per-role reasoning effort
michael-denyer/pstack-claude☆ 33722026年10月23日 更新
Explore a codebase with SocratiCode to locate features, functions, and types. Search by meaning, inspect how files depend on each other, and find relevant database schemas or API specifications before reading selected files.
中文简介正在准备中。当前显示英语简介。
- Locate the code behind a feature
- Understand file dependencies and circular references
- Find database schemas and API specifications
giancarloerra/SocratiCode☆ 33542026年10月24日 更新
Set up and maintain SocratiCode indexes, which prepare project files for search. Manage file watching, refresh changed content, rebuild dependency graphs, and check infrastructure health when indexing or search results need attention.
中文简介正在准备中。当前显示英语简介。
- Prepare a project for code search
- Configure automatic or manual index updates
- Investigate interrupted indexing or stale results
giancarloerra/SocratiCode☆ 33542026年10月24日 更新
Turn a completed workflow or conversation into a reusable agent skill. Clarify inputs, outputs, dependencies, and error handling, then produce an approved design, written instructions or helper scripts, and validation based on the original process.
中文简介正在准备中。当前显示英语简介。
- Packaging a completed workflow as a reusable skill
- Standardizing recurring tasks and error handling
- Combining existing skills into a shared procedure
google-deepmind/science-skills☆ 33272026年10月23日 更新
Prepare the Python package manager uv for skills that depend on it. This skill checks for an existing installation, installs uv if needed, and configures the command search path so uv commands are available.
中文简介正在准备中。当前显示英语简介。
- Preparing to run a skill that requires uv
- Installing uv when it is missing
- Making an installed uv command available
google-deepmind/science-skills☆ 33272026年10月23日 更新
Check maintainer documentation locally before automated CI checks run. Find missing metadata, outdated review dates, nonexistent paths in the architecture manifest, and completed plans that still contain unfinished tasks, with guidance for correcting common failures.
中文简介正在准备中。当前显示英语简介。
- Check required metadata after updating standards
- Find outdated review dates
- Verify paths listed in the architecture manifest
liaohch3/claude-tap☆ 33082026年10月24日 更新
Fill missing interface translations in a viewer JSON file using English and Chinese source strings. Preview missing entries, translate into six languages through OpenRouter, and validate the updated file with JSON checks and tests.
中文简介正在准备中。当前显示英语简介。
- Adding six-language translations for new interface text
- Previewing missing translation keys before editing
- Retranslating selected entries after source changes
liaohch3/claude-tap☆ 33082026年10月24日 更新
Check whether a pull request is ready to merge by combining local lint, formatting, and tests with GitHub Actions status and PR description requirements. Returns a readiness verdict with specific reasons for any failed checks.
中文简介正在准备中。当前显示英语简介。
- Running local checks before opening a pull request
- Reviewing an existing pull request’s merge readiness
- Finding failing or pending GitHub Actions checks
liaohch3/claude-tap☆ 33082026年10月24日 更新
Process GitHub issues from selection through code fixes and pull requests, which propose changes for review. Parallel agents implement and test fixes, while review monitoring handles follow-up comments. Filters, fork support, and recurring checks help organize the work.
中文简介正在准备中。当前显示英语简介。
- Fixing a batch of issues labeled as bugs
- Submitting fixes from a fork
- Handling review comments on fix pull requests
nexu-io/nexu☆ 32802026年4月26日 更新
Compare project documentation with code to find outdated descriptions, missing details, and inconsistent references. Review recent changes, audit all documentation, or focus on one area, then apply approved fixes while preserving the existing language and style.
中文简介正在准备中。当前显示英语简介。
- Review documentation affected by code changes
- Audit all documentation against the current code
- Check API or database documentation
nexu-io/nexu☆ 32802026年4月26日 更新
Delegate feature development, code refactoring, and pull request reviews to Codex, Claude Code, Pi, or OpenCode. It guides background execution, progress monitoring, and parallel work in separate working directories.
中文简介正在准备中。当前显示英语简介。
- Delegating new feature or app development
- Reviewing pull requests in a separate working directory
- Refactoring a large codebase
nexu-io/nexu☆ 32802026年4月26日 更新
Use the ClawHub command-line tool to find and install agent skills, update them to the latest or a specified version, list installed skills, and publish skill folders with version numbers and change notes.
中文简介正在准备中。当前显示英语简介。
- Find and install a skill for a task
- Install or update a skill to a specific version
- Update all installed skills
nexu-io/nexu☆ 32802026年4月26日 更新
Collect, list, and count actionable comments from CodeRabbit and Codex on GitHub pull requests. Separate comments attached to code from review summaries, check Codex status signals, and manage CodeRabbit review conversations.
中文简介正在准备中。当前显示英语简介。
- List actionable comments on a pull request
- Count CodeRabbit comments without minor suggestions
- Check whether Codex is still reviewing
nexu-io/nexu☆ 32802026年4月26日 更新
Extract skill ideas from recent Claude Code session logs using repeated actions, errors, and automation requests as signals. Remove duplicates, score novelty, feasibility, and trading value, then maintain a prioritized backlog for skill generation.
中文简介正在准备中。当前显示英语简介。
- Find skill ideas in the past week’s coding sessions
- Identify automation opportunities from repeated actions and errors
- Deduplicate and prioritize skill ideas
tradermonty/claude-trading-skills☆ 32522026年10月24日 更新
Generate a Claude CLI prompt from a structured JSON skill idea. The prompt guides creation of a complete skill directory, including SKILL.md, reference documents, helper scripts, and test scaffolding that follows repository conventions.
中文简介正在准备中。当前显示英语简介。
- Turn a JSON skill idea into a creation prompt
- Prepare prompts for an automated skill generation pipeline
- Include repository structure and quality criteria in skill design
tradermonty/claude-trading-skills☆ 32522026年10月24日 更新
Implement work described in a specification or task tickets, using test-driven development where possible. Check types and individual tests during development, run the full test suite at the end, review the changes, and commit to the current branch.
中文简介正在准备中。当前显示英语简介。
- Implement a feature from a specification
- Complete coding work described in tickets
- Develop with type checks and tests
rpamis/comet☆ 32292026年10月25日 更新
Turn a plan, specification, or conversation into small development tickets that each deliver a verifiable feature. Identify prerequisite tickets, review the breakdown with the user, and publish approved tickets as local files or tracker issues.
中文简介正在准备中。当前显示英语简介。
- Turn a specification into actionable development tickets
- Clarify ticket dependencies and execution order
- Plan a staged refactor across a codebase
rpamis/comet☆ 32292026年10月25日 更新