Template
Universal, agent-agnostic skills for coding agents. Measure first, fix the real constraint, never delete without approval.
npx -y skills add surendranb/loadout --skill templateAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 24 days oldThe repository was created 24 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
One sentence on WHAT this skill does, then WHEN to use it (situations and trigger phrases). Both halves matter — the description is how the agent decides to invoke the skill. Keep it a single concrete line. No angle brackets and no YAML folded scalars in frontmatter (it enters the system prompt).
SKILL.md
1.4 KB, 233 tokens by cl100k_base, as published. Nobody here has run it
Your Skill Name
State the outcome this skill produces and the method it follows — in one paragraph. A skill is a drilled capability, not a prompt: same disciplined behavior every run.
Method
- Measure first. Gather the real state before deciding anything.
- Find the constraint. Diagnose the one binding bottleneck; ignore symptoms.
- Rank fixes by impact divided by (cost plus risk). Cheapest reversible win first.
- Propose, get approval, act. Never take a destructive step without a shown, approved list.
- Re-measure and stop when the objective is met.
Thresholds / rules
List the concrete numbers or rules the agent applies, and why each is the threshold (rationale, not just the rule).
Safety contract
- Read-only by default; name exactly what (if anything) changes state.
- No deletion/uninstall/reconfig without the user approving a specific list.
- Never touch the user's own work or managed configuration without explicit confirmation.
- Make changes reversible where possible; report outcomes faithfully.
Gives 0 of the 12 instructions most prompt engineering skills give in 233 tokens
Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06
- ask at most three clarifying questionsin 22 of 563, across 15 files
- respond in the user input languagein 14 of 563, across 9 files
- preserve the original intentin 13 of 563, across 11 files
- Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
- Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
- Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
- Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
- validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
- generate quantitative baseline performance reportsin 12 of 563, across 2 files
- create representative test scenariosin 12 of 563, across 2 files
- treat prompts as codein 12 of 563, across 5 files
- test prompts on diverse inputsin 12 of 563, across 8 files
Said here and by no other author read
- gather real state before deciding anything
- diagnose the binding bottleneck
- ignore symptoms
- rank fixes by impact divided by cost plus risk
- choose the cheapest reversible win first
- propose a shown list and get approval
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.