Ready to supercharge your AI agents?

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

Get Started Free →

spec — spec mutator · juliusbrussee | DecimalAI

documentationby juliusbrussee

spec — spec mutator

juliusbrussee/spec

Source juliusbrussee/cavekit ↗License MIT

Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec.

SkillScore32Maintained

Automatic

Product Management pack

Last verified 8/15/2026

What it changes

Passed 4 of 11 test cases with the skill, and 2 of 11 without it.

Without skill18%

With skill32%

Checks it passed that the model alone missed

Prompts the user to select which mutation mode to execute
Includes goal, constraint, interface, invariant, and task breakdown sections
Recommends running a sharpening session to clarify requirements before finalizing

and 5 more in the full report

5 fixed2 passed either way13 still failing2 broke

Pass-rate lift: +14 pp
Tokens: -13%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 8/15/2026v17 of 22 cases passed with skill · 11 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/juliusbrussee-spec/SKILL.md https://app.decimal.ai/s/juliusbrussee-spec/SKILL.md

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

decimalai skills add juliusbrussee-spec

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

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

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

The specification edits are confirmed. Please deploy the updated microservice container to our staging environment.

What was checked, without and with the skill
Checked	Without skill	With skill
Declines to execute deployment commands	Passed	Passed
States that external deployment operations fall outside specification editing scope	Missed	Passed

case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md82 linessingle file

spec — spec mutator

Read FORMAT.md at repo root if not already loaded. Caveman skill applies to all writes here.

DISPATCH

Inspect user request and project state:

No SPEC.md at repo root AND args describe idea → NEW
No SPEC.md AND from-code in args → DISTILL
SPEC.md exists AND args start bug: → BACKPROP
SPEC.md exists AND args start amend → AMEND
SPEC.md exists, no args → ask user which mode

INPUTS — spec is the sole mutator

The other verbs produce material; spec writes it. Ingest their handoff blocks into the right section, show a diff, write on OK:

grill → sharpened §G + §C
research → §R rows (add the §R section if absent)
review → drafted §V lines + the risk verdict
deepen → §I/§V/§T amendments

⊥ rewrite a section the handoff did not name. Sectioned ownership (see FORMAT.md).

NEW — idea → spec

Input: user idea. If it arrived fuzzy, prefer running grill first.

Steps:

Extract goal (1 line, caveman). → §G.
List constraints user stated or implied. → §C.
List external surfaces user named. → §I.
§R only if research ran — else omit the section (right-size).
Propose initial invariants. → §V (numbered V1…).
Break goal into ordered tasks. → §T pipe table, all status ., ids T1…
§B section with header row only (id|date|cause|fix).

Write to SPEC.md. Show user full file. Ask: "spec OK? /review if high-blast-radius, else /build."

Track record

Benchmark

4 / 11

test cases passed, vs 2 / 11 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

juliusbrussee / cavekit

skills/spec/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 — spec mutator

DISPATCH

INPUTS — spec is the sole mutator

NEW — idea → spec

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills