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.zipInstalls 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 overheadKey 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
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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-fast (this skill) | 0 | 4mo | No flags | Beginner |
| cursor-local-dev-loop | 3 | 29d | Review | Beginner |
| codex-worker | 1 | 6mo | Review | Advanced |
| agent-challenges | 1 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by Esteban-Marketing
View all by Esteban-Marketing →You might also like
cursor-local-dev-loop
jeremylongshore
Optimize local development workflow with Cursor. Triggers on "cursor workflow", "cursor development loop", "cursor productivity", "cursor daily workflow". Use when working with cursor local dev loop functionality. Trigger with phrases like "cursor local dev loop", "cursor loop", "cursor".
codex-worker
MoonshotAI
Spawn and manage multiple Codex CLI agents via tmux to work on tasks in parallel. Use whenever a task can be decomposed into independent subtasks (e.g. batch triage, parallel fixes, multi-file refactors). When codex and tmux are available, prefer this over the built-in Task tool for parallelism.
agent-challenges
ruvnet
Agent skill for challenges - invoke with $agent-challenges
sensei
Azure
**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git co
workflow-update
nomadoor
Use when editing example_workflows JSON files or changing node schema in ways that affect sample workflows.
continue-work
papeete-consulting-lab
>