task-management
Helps organize tasks, create action plans, manage schedules, and track progress
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-17 00:07
53,894 results
Helps organize tasks, create action plans, manage schedules, and track progress
Use when you have a written implementation plan and execute it in a separate session with review checkpoints
Use when starting feature work that needs isolation from the current workspace or before executing an implementation plan - creates an isolated git worktree through smart directory selection and safety verification
Use at the start of any conversation - determine how to find and use skills, requiring the skill tool to be invoked before any response (including clarifying questions)
Before submitting or creating a PR, when reporting work as complete, fixed, or about to be used - the validation command must be run and output confirmed before making any successful report; evidence always precedes assertion
General-purpose web search and content extraction skill. Multi-source parallel search (WebSearch, MCP search tools, ctx7, agent-browser), web page body extraction (crwl), and structured article analysis. Use when the user needs to search for information, research a topic, find materials, obtain web page content, read articles, or analyze web pages. Trigger scenarios include: search, research, investigation, fetch, look it up, help me find, read this link, analyze this…
Turn resumes, LinkedIn profiles, PDF-extracted resume text, personal bios, avatars, portfolio links, project assets, and style preferences into premium…
Use when you are about to start Discover on a brownfield project, but you are not yet clear about "which entry points can serve as evidence (run/test/ci/contract/ops)" and "which modules should be done first (P0/P1/P2)", and you are worried that uncontrolled scope will make it unmaintainable.
Use when on the spec branch of dlc-dev you need to complete the requirement clarification for R1 (raw→solution), but pressure signals appear such as urging you to skip clarification/skip gates, demanding to "ask everything at once," or demanding that you directly give the next-step routing conclusion.
Use when you need to run the AI DLC (Spec Pack) process in the dlc-dev repository, select/chain requirement-side (raw/solution/prd/prototype/demo) and implementation-side (plan/execute/finishing) skills, and use gates to avoid context drift, writing to the wrong directory, or skipping key steps under pressure.
Search the web via the Zhipu CodePlan MCP web-search-prime server. Use when you need fast web discovery (titles/URLs/snippets) without a browser. Triggers:…
Search, lint, and rewrite code structurally with ast-grep (sg). Use for any syntax-aware task — outlining a file or directory, finding code by AST structure,…
Apply The Lean Startup practices (Eric Ries). Covers Vision (Ch 1-4: Start, Define, Learn, Experiment — validated learning, Build-Measure-Learn loop), Steer…
FileBrowser Quantum all-in-one CLI. It includes two types of operations: 1) File management: browse (info/list-dir), read/write (update), create directory (mkdir), delete (delete), …
Should be used after solving a non-trivial problem—for example, pitfall fixes, architectural decisions, performance tuning, integration debugging, and similar scenarios. Distill the solution into a structured learning file so that subsequent sessions can retrieve and reuse it. It can also be used at the start of a new session to retrieve existing learnings.
Applies to tasks like "starting a new project," "creating a new repo," "building the first prototype first," "setting up the minimal skeleton first," or "proving the direction is viable first." It should be used whenever the user wants to converge a vague new idea into a minimal viable starting point.
Uniformly advancing cross-stage tasks and software design decisions that require project context: clarify goals, inspect existing or reference projects, choose the smallest verifiable slice, determine module/interface/state boundaries, split dependencies and decide whether to delegate, and create or update SPARK.md when there is long-term value. Applicable to "what should the project do next", "plan changes after comparing reference projects", "how to split modules/interfaces", "how to weigh refactoring options", "how to advance in stages", "how to write or update…
Extracts activity information from WeChat article feeds, lets the model judge whether each article is truly an activity by reading the article semantics,…
Use when the user requests formatting markdown documents, fixing syntax errors, optimizing layout, intelligent paragraphing, cleaning up redundant content, or checking document quality.
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md…
Date, time, timezone, and epoch timestamp manipulation from the command line. Use when user mentions "date command", "timestamp", "epoch", "unix timestamp",…
Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance,…
Use when computing quantitative text complexity metrics from a corpus, measuring readability scores (Flesch-Kincaid, Coleman-Liau, Gunning Fog, SMOG, ARI),…
Classify GitHub issues into the factory's live label queue and write an auditable snapshot. Use for backlog triage or a scheduled triage run.