Ready to supercharge your AI agents?

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

Get Started Free →

Fix Schema · d-kimuson | DecimalAI

codingby d-kimuson

Fix Schema

d-kimuson/fix-schema

Source d-kimuson/claude-code-viewer ↗License MIT

Fix session log schema parse errors and create a pull request

SkillScore64Maintained

Automatic

Coding pack

Last verified 8/13/2026

What it changes

Passed 11 of 18 test cases with the skill, and 7 of 18 without it.

Without skill36%

With skill64%

Checks it passed that the model alone missed

Creates a draft PR summarizing schema changes
Selects creating a draft PR as the publication method
Runs pnpm typecheck and pnpm test during the verification phase

and 7 more in the full report

6 fixed8 passed either way8 still failing0 broke

Pass-rate lift: +27 pp
Tokens: -41%
Agent turns: 0%
Response time: -51%

Model gemini-3.6-flashMeasured 8/13/2026v114 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/d-kimuson-fix-schema/SKILL.md https://app.decimal.ai/s/d-kimuson-fix-schema/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add d-kimuson-fix-schema, 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/d-kimuson-fix-schema/ and pins it in .decimal/skills.lock

decimalai skills add d-kimuson-fix-schema

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

curl -fsSL --create-dirs -o .claude/skills/d-kimuson-fix-schema/SKILL.md https://app.decimal.ai/s/d-kimuson-fix-schema/SKILL.md

Raw file: /s/d-kimuson-fix-schema/SKILL.md ↗ · machine-readable summary at /s/d-kimuson-fix-schema.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Session logs show validation failures for `{"type": "model_response", "tokensUsed": 350, "finishReason": "stop"}`. In which directory path should we find the schema corresponding to this type?

What was checked, without and with the skill
Checked	Without skill	With skill
Points to src/lib/conversation-schema/ for the schema file location	Missed	Passed

case-11 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

2. Fix type errors:

Update affected components to handle new schema types
Follow project type safety rules (no as casting)

3. Add tests:

Create or update test files for modified schemas
Verify both old and new formats parse successfully

4. Verify and commit:

Run pnpm typecheck (must pass)
Run pnpm test (must pass)
Run pnpm fix
Commit changes

5. Create PR:

Push branch
Create draft PR with summary of schema changes

Track record

Benchmark

11 / 18

test cases passed, vs 7 / 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

d-kimuson / claude-code-viewer

.agents/skills/fix-schema/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.