Ready to supercharge your AI agents?

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

Get Started Free →

perf-investigation-logger · composio-community | DecimalAI

documentationby composio-community

perf-investigation-logger

composio-community/perf-investigation-logger

Source composio-community/awesome-claude-plugins ↗License Not recorded

Use when appending structured perf investigation notes and evidence.

SkillScore73Maintained

Automatic

Knowledge Management pack

Last verified 8/12/2026

What it changes

Passed 15 of 20 test cases with the skill, and 3 of 20 without it.

Without skill14%

With skill73%

Checks it passed that the model alone missed

Includes **Summary** list item section
Formats decision under **Decision** label
Contains phase header with phase name and date

and 22 more in the full report

14 fixed2 passed either way5 still failing1 broke

Pass-rate lift: +59 pp
Tokens: +65%
Agent turns: 0%
Response time: +56%

Model gemini-3.6-flashMeasured 8/12/2026v116 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/composio-community-perf-investigation-logger/SKILL.md https://app.decimal.ai/s/composio-community-perf-investigation-logger/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add composio-community-perf-investigation-logger, 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/composio-community-perf-investigation-logger/ and pins it in .decimal/skills.lock

decimalai skills add composio-community-perf-investigation-logger

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

curl -fsSL --create-dirs -o .claude/skills/composio-community-perf-investigation-logger/SKILL.md https://app.decimal.ai/s/composio-community-perf-investigation-logger/SKILL.md

Raw file: /s/composio-community-perf-investigation-logger/SKILL.md ↗ · machine-readable summary at /s/composio-community-perf-investigation-logger.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

Save our findings regarding disk performance for ID `disk-io-bottleneck-11`. Quote from analysis: 'Write operations saturate IOPS limits during midnight WAL flushes.' Command run was `iostat -xz 1 10` and file analyzed was `config/storage.yaml:14`. Action item decided was moving WAL to NVMe storage.

What was checked, without and with the skill
Checked	Without skill	With skill
Target file path is .claude/perf/investigations/disk-io-bottleneck-11.md	Missed	Passed
Includes exact quote 'Write operations saturate IOPS limits during midnight WAL flushes.'	Passed	Passed
Evidence section includes line reference file config/storage.yaml:14	Passed	Passed

case-12 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md35 linessingle file

perf-investigation-logger

Append structured investigation notes to {state-dir}/perf/investigations/<id>.md.

Follow docs/perf-requirements.md as the canonical contract.

Required Content

Exact user quotes (verbatim)
Phase summary
Decisions and rationale
Evidence pointers (files, metrics, commands)

Output Format

## <Phase Name> - <YYYY-MM-DD>

**User Quote:** "<exact quote>"

**Summary**
- ...

**Evidence**
- Command: `...`
- File: `path:line`

**Decision**
- ...

Constraints

Use AI_STATE_DIR for state path (default .claude).
Do not paraphrase user quotes.

Track record

Benchmark

15 / 20

test cases passed, vs 3 / 20 without

Adoption

Users: 2
Times used: 5

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

composio-community / awesome-claude-plugins

perf/skills/investigation-logger/SKILL.md

View on GitHub ↗

Imported 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

perf-investigation-logger

Required Content

Output Format

Constraints

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills