Results for “update skill”

Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read the skilld.dev registry (view, browse, trending, tracks, curators, index) and act for the user's skilld.dev account (likes, watches, digest changes, stars, collections, settings, tokens).

The English summary is being prepared. Showing the original description.

Use when creating a new skill or updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Activates on "create a new skill", "add a skill to plugin", or "update existing skill".

The English summary is being prepared. Showing the original description.

This skill synchronizes plugin skills (plugins/synapse-a2a/skills/) with the current implementation, README.md, and guides folder. Use this skill when implementation changes have been made, new features added, or documentation updated, to ensure plugin skills stay up-to-date. Triggered by /sync-plugin-skills command or when significant code changes are detected.

The English summary is being prepared. Showing the original description.

Update a product spec from a meeting transcript — extract decisions, open questions, spec changes, and flowchart updates. Use this skill when: - A meeting discussed changes to a product spec and you need to update the local .md + wiki page - The user shares a meeting URL or transcript ID and says "update the spec" - The user says "what needs to change in the spec from this meeting" - After processing a meeting, when decisions affect a spec's content (not just action items) Trigger phrases: "update spec from meeting", "what changed in the spec", "meeting to spec", "sync meeting decisions to spec", "add meeting decisions to spec"

The English summary is being prepared. Showing the original description.

Use when the user says "write my investor update", "monthly update for investors", "quarterly investor email", "investor communication", "LP update", "board update", "shareholder update", "what do I tell my investors this month", "how do I write a good investor update", or wants to communicate progress, metrics, and needs to existing investors or board members on a recurring basis.

The English summary is being prepared. Showing the original description.

Check Spring Boot skill content freshness against latest research and flag skills needing updates. Use when running /spring-refresh, or when user mentions "refresh spring skills", "spring boot update check", "skill freshness", "stale spring content", "update spring boot skills".

The English summary is being prepared. Showing the original description.

CLAUDE.md / AGENTS.md・skills・context・rules 等の指示ファイルの静的監査。指示ファイルの「レビューして」「監査して」「スリム化して」等の依頼時、/instructions-audit 実行時に使用。rubric で削除候補・hook/deny 移管・skill 化/Read-when 化・description 強化・system prompt との衝突の分類ごとに指摘を修正案付きで出す。user-level と project-level 両対応。境界: 指摘の適用や個別追記は update-inst、セッション知見の反映は update-inst の retro モード、コードの監査は codebase-review。

The English summary is being prepared. Showing the original description.

Guide for creating and editing Claude Code skills. Use when user wants to create a new skill, create a new slash command (skills are the unified primitive - commands live in skills/ now), update an existing skill, or needs help structuring a SKILL.md file.

The English summary is being prepared. Showing the original description.

Audit a project's verification skill and maps of features and agent access against source code and live behavior. Correct documented procedures and references, while clearly identifying untested operations, access gaps, and missing prerequisites.

• Update verification procedures after app changes
• Reconcile feature coverage with permitted agent access
• Separate source review from executed verification evidence

Assess skills CLI pull requests for focused bug fixes using visible patches and regression tests. Surface well-supported candidates with a label and brief maintainer comment, while keeping uncertain findings out of public updates.

• Identify well-supported bug-fix pull requests
• Check regression tests and effects on other supported agents
• Suggest possible matching issues from available board findings

Update CRM opportunity fields such as stage, close date, amount, and next steps. See the exact before-and-after values, apply only requested or accepted changes, and verify the saved record through a link.

• Advance an opportunity to another stage
• Change a close date or deal amount
• Update next steps or forecast category

Build or update Figma screens from code or descriptions using an existing design system, a shared set of components and visual rules. Assemble sections with reusable components, colors, spacing, and styles, then check their appearance.

• Recreate an application page in Figma
• Build a landing page with shared components
• Update a Figma screen to match code

Manage OpenKruise in KubeSphere, from extension installation to troubleshooting. Generate SidecarSet configuration for adding helper containers and CloneSet configuration for application updates, including in-place changes and staged rollouts, with commands to apply and verify each configuration.

• Install OpenKruise and check its status
• Add and update helper containers with SidecarSet
• Stage application image updates with CloneSet

Find the replacement command for plain-language client correspondence. This deprecated reference directs routine letters to `/client-letter` and substantive status updates to `/status client`, helping users choose the appropriate workflow when moving from the older skill.

• Find the replacement for the deprecated letter skill
• Choose the command for appointment confirmations or document requests
• Choose the command for substantive client status updates

Search Zhihu articles by keyword and publication period through the BrowserAct API. Retrieve full article text, titles, authors, dates, cover image URLs, and source links as structured data for industry research, brand monitoring, or competitor updates.

• Research recent industry articles
• Track mentions of a brand or company
• Collect competitor product updates

Find GitHub projects using keywords, minimum stars, and update dates, then collect repository details and contributor profiles through BrowserAct. Results include project descriptions, contributor biographies, personal websites, and Twitter handles for research, recruiting, or collaboration scouting.

• Discover open-source projects in a specific field
• Collect developer profiles for recruiting
• Find potential collaborators and sponsors

Measure DOCA Flow rule update and disable rates when work runs on the device's DPA processor. Configure workloads, interpret repeated measurements in thousands of operations per second, and investigate zero-operation results or failed self-tests.

• Establish a DPA rule-update performance baseline
• Compare burst sizes, queue sizes, and worker counts
• Review iteration statistics and measurement conditions

Connect existing DOCA Flow processing rules and resources to BlueField’s DPA processor. The skill guides export sequencing, operation queues, counter access, and entry or memory updates, and helps diagnose failures between host setup and device-side access.

• Expose an existing DOCA Flow pipe to a DPA kernel
• Investigate exported entries that the kernel cannot see
• Check queues for counter access and entry updates

SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.

The English summary is being prepared. Showing the original description.

检查并更新花叔系 skills。用户说「检查skill更新」「更新花叔的skill」「skill是不是最新的」时触发。按各仓库的版本标签判断有没有新版本，只提示，是否更新由用户决定。

The English summary is being prepared. Showing the original description.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

The English summary is being prepared. Showing the original description.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

The English summary is being prepared. Showing the original description.

Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill, refresh the eval suite, keep the four manifests + all README translations + CHANGELOG + AGENTS/GEMINI in sync, audit trigger boundaries, and cut releases. Drives the five agents in .codex/agents/ (skill-author, eval-curator, consistency-qa, trigger-boundary-auditor, release-manager). Triggers when the maintainer asks to work ON brooks-lint itself: "add a new skill", "edit the brooks-debt guide", "update the eval suite", "fix the trigger descriptions", "make this change and validate it", "release brooks-lint", "bump and publish", and follow-ups: "re-run", "re-validate", "update that skill", "redo the audit", "do the X part again". Do NOT trigger for: USING the brooks-lint analysis skills on some target codebase (that's brooks-review / brooks-audit / brooks-debt / brooks-test / brooks-health / brooks-sweep); generic questions about brooks-lint that don't ask to change it; or maintenance of a different plugin.

The English summary is being prepared. Showing the original description.

Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill, refresh the eval suite, keep the four manifests + all README translations + CHANGELOG + AGENTS/GEMINI in sync, audit trigger boundaries, and cut releases. Drives the five agents in .claude/agents/ (skill-author, eval-curator, consistency-qa, trigger-boundary-auditor, release-manager). Triggers when the maintainer asks to work ON brooks-lint itself: "add a new skill", "edit the brooks-debt guide", "update the eval suite", "fix the trigger descriptions", "make this change and validate it", "release brooks-lint", "bump and publish", and follow-ups: "re-run", "re-validate", "update that skill", "redo the audit", "do the X part again". Do NOT trigger for: USING the brooks-lint analysis skills on some target codebase (that's brooks-review / brooks-audit / brooks-debt / brooks-test / brooks-health / brooks-sweep); generic questions about brooks-lint that don't ask to change it; or maintenance of a different plugin.

The English summary is being prepared. Showing the original description.