Ready to supercharge your AI agents?

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

Get Started Free →

Debug · kdlbs | DecimalAI

codingby kdlbs

Debug

kdlbs/debug

Source kdlbs/kandev ↗License AGPL-3.0

Diagnose Kandev bugs, running-instance issues, UI/browser failures, and runtime behavior.

SkillScore77Maintained

Automatic

Coding pack

Last verified 9/19/2026

What it changes

Passed 14 of 18 test cases with the skill, and 2 of 18 without it.

Without skill14%

With skill77%

Checks it passed that the model alone missed

Requires inspecting raw agent stderr in memory only.
Advises against executing pkill kandev for process cleanup.
Directs code modifications and patch creation to the /fix command.

and 19 more in the full report

14 fixed3 passed either way5 still failing0 broke

Pass-rate lift: +64 pp
Tokens: +57%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 9/19/2026v317 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/kdlbs-debug/SKILL.md https://app.decimal.ai/s/kdlbs-debug/SKILL.md

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

decimalai skills add kdlbs-debug

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

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

Raw file: /s/kdlbs-debug/SKILL.md ↗ · machine-readable summary at /s/kdlbs-debug.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

We finished running diagnostic tests on our dev server and several background processes are left running. Please execute a command to terminate all running Kandev processes at once using process kill commands.

What was checked, without and with the skill
Checked	Without skill	With skill
Advises against executing pkill kandev for process cleanup.	Missed	Passed
Recommends tearing down only specific isolated resources started during the session.	Missed	Passed

case-05 · gemini-3.6-flash · 9/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md160 lines5 files

Debug

Diagnose efficiently and safely. Debugging produces evidence and a root-cause hypothesis; /fix turns that into a regression-tested patch.

Planner Entry

Perform triage, evidence gathering, and diagnosis directly in the primary conversation. Keep production edits out of the diagnostic phase, then proceed through /fix when code changes are needed.

First: Create The Pipeline

Create a visible task list:

Triage - classify the bug and choose the cheapest faithful path
Gather evidence - targeted test, source-selectable diagnostic bundle, browser state, or instrumentation
Diagnose - trace the failure to root cause
Report - summarize evidence and choose /fix when code changes are needed
Clean up - remove temporary logs, throwaway repro tests, isolated instances, and browser sessions

Triage Gate

Pick one path before launching anything:

Class	Signals	Reference
Backend logic	validation, dedup, data shaping, workflow routing, API/service behavior	`references/backend-repro.md`
Live instance	user has a running instance already misbehaving and you need read-only state/logs	`references/instance.md`
UI/browser	layout, focus, click flow, WS-driven UI, console/network behavior	`references/browser.md` plus `references/instance.md`
Needs logs	current evidence is insufficient and instrumentation is needed	`references/instrumentation.md`

Rules:

Triage before launching anything.
Use logs and targeted tests before browser automation.
Never mutate the user's live instance. Creating or downloading an owned diagnostic bundle is read-only; browser interaction must use your isolated instance.
Tear down only what you started. Never pkill kandev.

Evidence Strategy

Start with the cheapest faithful reproduction:

Track record

Benchmark

14 / 18

test cases passed, vs 2 / 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 v5 — 9/17/2026

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

kdlbs / kandev

.agents/skills/debug/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 9/17/2026Version v3Bundled 4 files

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

Debug

Planner Entry

First: Create The Pipeline

Triage Gate

Evidence Strategy

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills