Ready to supercharge your AI agents?

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

Get Started Free →

Bottleneck Resolver · stijnman | DecimalAI

agent toolingby stijnman

Bottleneck Resolver

stijnman/bottleneck-resolver

Source stijnman/grok-custom-skills ↗License MIT

Identifies and resolves performance bottlenecks in agent workflows.

SkillScore82Maintained

Automatic

DevOps & SRE pack

Last verified 8/15/2026

What it changes

Passed 18 of 22 test cases with the skill, and 16 of 22 without it.

Without skill73%

With skill82%

Checks it passed that the model alone missed

Instruct the user to add timing logs to the next run.
Require re-measuring step durations after implementing the fix.
Recommend using predictive cache manager for repeated API lookups.

3 fixed15 passed either way3 still failing1 broke

Pass-rate lift: +9 pp
Tokens: -6%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 8/15/2026v218 of 22 cases passed with skill

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/stijnman-bottleneck-resolver/SKILL.md https://app.decimal.ai/s/stijnman-bottleneck-resolver/SKILL.md

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

decimalai skills add stijnman-bottleneck-resolver

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

curl -fsSL --create-dirs -o .claude/skills/stijnman-bottleneck-resolver/SKILL.md https://app.decimal.ai/s/stijnman-bottleneck-resolver/SKILL.md

Raw file: /s/stijnman-bottleneck-resolver/SKILL.md ↗ · machine-readable summary at /s/stijnman-bottleneck-resolver.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

After enabling parallel execution on our file validator service file-val-service, total execution time dropped. What final step must be performed to complete the optimization workflow?

What was checked, without and with the skill
Checked	Without skill	With skill
Require re-measuring step durations after implementing the fix.	Missed	Passed

case-08 · 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.md35 linessingle file

Bottleneck Resolver

When to Use

User says find bottleneck or task matches this capability
User says speed up or task matches this capability
User says why so slow or task matches this capability
User says optimize workflow or task matches this capability

Workflow

Profile step durations (tool calls, waits, retries).
Rank bottlenecks by impact.
Propose fixes: parallelize, cache, simplify, batch.
Implement highest-impact fix; re-measure.

Integrations

performance-optimizer
parallel-tool-orchestrator
predictive-cache-manager

Error Handling

Failure	Response
Cannot measure	Add timing logs to next run.

Gotchas

Measure before optimizing; avoid premature parallelization.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Track record

Benchmark

18 / 22

test cases passed, vs 16 / 22 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 — 8/15/2026

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

stijnman / grok-custom-skills

.grok/skills/bottleneck-resolver/SKILL.md

View on GitHub ↗

License MITImported 8/15/2026Version v2

Other skills for the same job

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

Bottleneck Resolver

When to Use

Workflow

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills