Ready to supercharge your AI agents?

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

Get Started Free →

Dev Trace · evolution-foundation | DecimalAI

codingby evolution-foundation

Dev Trace

evolution-foundation/dev-trace

Source evolution-foundation/evo-nexus ↗License NOASSERTION

Evidence-driven causal tracing with competing hypotheses.

SkillScore86Maintained

Automatic

Coding pack

Last verified 8/19/2026

What it changes

Passed 17 of 20 test cases with the skill, and 5 of 20 without it.

Without skill23%

With skill86%

Checks it passed that the model alone missed

The probe step must identify the critical unknown
The FRAME phase must define the exact why question
The path must be inside workspace/development/debug/

and 13 more in the full report

14 fixed5 passed either way3 still failing0 broke

Pass-rate lift: +64 pp
Tokens: -22%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/19/2026v119 of 22 cases passed with skill · 20 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/evolution-foundation-dev-trace/SKILL.md https://app.decimal.ai/s/evolution-foundation-dev-trace/SKILL.md

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

decimalai skills add evolution-foundation-dev-trace

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

curl -fsSL --create-dirs -o .claude/skills/evolution-foundation-dev-trace/SKILL.md https://app.decimal.ai/s/evolution-foundation-dev-trace/SKILL.md

Raw file: /s/evolution-foundation-dev-trace/SKILL.md ↗ · machine-readable summary at /s/evolution-foundation-dev-trace.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

What two explicit elements must be produced in the final PROBE step of a multi-hypothesis trace into data sync drift?

What was checked, without and with the skill
Checked	Without skill	With skill
The probe step must identify the critical unknown	Missed	Passed
The probe step must specify a discriminating experiment	Missed	Passed

case-15 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md37 linessingle file

Dev Trace

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.

Causal investigation with multi-hypothesis discipline. Generate at least 2 explanations, collect evidence FOR and AGAINST, rank by strength, end with a discriminating probe.

Use When

Observation has multiple plausible causes
"Why did this happen?" — and you don't want to jump to the first answer
Multi-causal problem (intermittent bugs, regional anomalies, performance puzzles)
Need to preserve uncertainty rather than collapse to one answer prematurely

Do Not Use When

Cause is obvious → just fix it via @hawk-debugger
Single-cause bug with clear stack trace → @hawk-debugger
Just needs codebase search → @scout-explorer

Workflow

Delegate to @trail-tracer:

OBSERVE — restate the observation precisely, no interpretation
FRAME — define the exact "why" question
HYPOTHESIZE — generate 2+ competing explanations
GATHER EVIDENCE — for each, collect evidence FOR and AGAINST in parallel
APPLY LENSES — systems / premortem / science
REBUT — strongest alternative challenges the leader
RANK — down-rank contradicted, weak-assumption, failed-prediction explanations
SYNTHESIZE — best explanation, explicitly provisional if needed
PROBE — name the critical unknown and the discriminating next experiment

Output

Saved to workspace/development/debug/[C]trace-{topic}-{date}.md using the dev-trace-report.md template.

Pairs With

@trail-tracer (the executor)
@hawk-debugger (when trace converges to a clear bug)
@apex-architect (when trace reveals architectural issues)

Track record

Benchmark

17 / 20

test cases passed, vs 5 / 20 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

evolution-foundation / evo-nexus

.claude/skills/dev-trace/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

yeachan-heo/traceEvidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team modeClose match+18 pp pass-rate lift

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

Dev Trace

Use When

Do Not Use When

Workflow

Output

Pairs With

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills