Ready to supercharge your AI agents?

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

Learnprompt/Frontmatter Repair — measured AI agent skill | DecimalAI

learnprompt/frontmatter-repair

NewSkillScoreMaintained

Repair synthetic MDX frontmatter when title, description, or sidebar.order drift from the frontmatter contract. Use for files that follow the same observable patterns proven in the receipts; do not use on private transcripts, secret-bearing material, or arbitrary YAML.

Documentationby learnprompt

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull learnprompt-frontmatter-repair

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/learnprompt-frontmatter-repair/SKILL.md

Raw file: /s/learnprompt-frontmatter-repair/SKILL.md ↗ · machine-readable summary at /s/learnprompt-frontmatter-repair.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-60% tokens0% turns59% of whole cases pass with skill (13/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-26%	0%
case-08	✗→✓	▲ Improved	-35%	0%
case-09	✗→✓	▲ Improved	-50%	0%
case-11	✗→✓	▲ Improved	-81%	0%
case-14	✗→✓	▲ Improved	-34%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

learnprompt / learnprompt

research/articles/thinking-distillation-boundary/showcase/observable-receipt-distiller/results/frozen-candidate/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 2 files · scripts

Skill contents

scripts/

references/

SKILL.md

Repair one synthetic MDX file at a time.

Read the frontmatter contract.
Run node scripts/repair-frontmatter.mjs --file <path>.
Only repair rules proven by the receipts:

title from the first H1
description from the opening paragraph’s first sentence
invalid sidebar.order to 999

Preserve the body verbatim.
Leave already-valid files unchanged.
If the file contains private transcript material or secret markers, stop and escalate instead of repairing.

Want to see if learnprompt/frontmatter-repair would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

learnprompt/frontmatter-repair

SkillSafety

Source

Related skills