Perform small, quick coding tasks directly without creating project plans or subagents.

Install

mkdir -p .claude/skills/gsd-fast-esteban-marketing && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15801" && unzip -o skill.zip -d .claude/skills/gsd-fast-esteban-marketing && rm skill.zip

Installs to .claude/skills/gsd-fast-esteban-marketing

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Execute a trivial task inline — no subagents, no planning overhead
66 charsno explicit “when” trigger
Beginner

Key capabilities

  • Fix typos in documents or code
  • Make small configuration file changes
  • Apply minor code refactors
  • Add forgotten commits to a repository
  • Execute simple additions to files

How it works

The skill executes a predefined fast workflow end-to-end without spawning subagents or generating planning files.

Inputs & outputs

You give it
a trivial task described in one sentence
You get back
the trivial task executed directly in the current context

When to use gsd-fast

  • Fix a typo in code
  • Update a small configuration file
  • Apply a minor refactor
  • Add a forgotten commit

About this skill

<objective> Execute a trivial task directly in the current context without spawning subagents or generating PLAN.md files. For tasks too small to justify planning overhead: typo fixes, config changes, small refactors, forgotten commits, simple additions.

This is NOT a replacement for /gsd-quick — use /gsd-quick for anything that needs research, multi-step planning, or verification. /gsd-fast is for tasks you could describe in one sentence and execute in under 2 minutes. </objective>

<execution_context> @.agent/get-shit-done/workflows/fast.md </execution_context>

<process> Execute the fast workflow from @.agent/get-shit-done/workflows/fast.md end-to-end. </process>

<success_criteria>

  • The core objective stated in the context or workflow was perfectly achieved.
  • Required output files or state updates are correctly written to disk.
  • Operations are atomic and accurately logged. </success_criteria>

<failure_modes>

  • Required input files (context, state, plans) may be missing or empty.
  • Tools may fail due to incorrect parameters or unexpected system states.
  • Agent may hallucinate completion without verifying final file contents. </failure_modes>

When not to use it

  • When the task requires research or multi-step planning
  • When verification of the task is needed
  • When the task cannot be described in one sentence

Limitations

  • It is for tasks executable in under 2 minutes
  • It does not replace tasks requiring research
  • It does not replace tasks requiring multi-step planning

How it compares

This skill directly executes trivial tasks without planning overhead, unlike workflows that involve research, multi-step planning, or verification.

Compared to similar skills

gsd-fast side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gsd-fast (this skill)04moNo flagsBeginner
cursor-local-dev-loop329dReviewBeginner
codex-worker16moReviewAdvanced
agent-challenges16moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry