Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Spec First · archive228 | DecimalAI

agent toolingby archive228

Spec First

archive228/spec-first

Source archive228/loopkit ↗License MIT

Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.

SkillScore55Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 10 of 18 test cases with the skill, and 6 of 18 without it.

Without skill32%

With skill55%

Checks it passed that the model alone missed

Specifies that PROMPT.md is re-read every iteration.
Includes test regression rules in the Stop if section.
Includes file change thresholds in the Stop if section.

and 6 more in the full report

7 fixed5 passed either way8 still failing2 broke

Pass-rate lift: +23 pp
Tokens: -25%
Agent turns: 0%
Response time: -34%

Model gemini-3.6-flashMeasured 8/16/2026v112 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/archive228-spec-first/SKILL.md https://app.decimal.ai/s/archive228-spec-first/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-spec-first, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/archive228-spec-first/ and pins it in .decimal/skills.lock

decimalai skills add archive228-spec-first

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-spec-first/SKILL.md https://app.decimal.ai/s/archive228-spec-first/SKILL.md

Raw file: /s/archive228-spec-first/SKILL.md ↗ · machine-readable summary at /s/archive228-spec-first.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Draft the PROMPT.md file for updating our Dockerfile to use multi-stage builds. Set the goal to: 'We need to reduce image size. Our current image is 1.2GB. The target is under 300MB.'

What was checked, without and with the skill
Checked	Without skill	With skill
Consolidates the goal statement into a single sentence in the Goal section.	Missed	Passed

case-21 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md8 linessingle file

Spec First

Without an external contract, the agent drifts after ~3 iterations — and the failure looks like progress (code written, tests pass, wrong goal solved). Write PROMPT.md BEFORE acting:

Goal — one sentence.
Done when — concrete, checkable conditions. "Test suite green: ".
Never touch — files/areas off-limits.
Stop if — more than N files outside scope change; a passing test starts failing. The agent re-reads this file every iteration. State (what's done) goes in a separate IMPLEMENTATION_PLAN.md it updates in place. If you can't write "done when" concretely, the task isn't ready — clarify before coding.

Track record

Benchmark

10 / 18

test cases passed, vs 6 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/spec-first/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Spec First

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills