Ready to supercharge your AI agents?

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

Analyze and Plan · optim-agent | DecimalAI

codingby optim-agent

Analyze and Plan

optim-agent/analyze-and-plan

Source optim-agent/optim-plans ↗License MIT

MUST USE when investigating a bug, CI failure, test failure, regression, incident, broken behavior, root cause, RCA, or debug-why problem before deciding whether to create an optim-plans solution plan; do not use for ordinary feature ideas, vague product planning, direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.

SkillScore45Maintained

Automatic

Coding pack

Last verified 8/24/2026

What it changes

Passed 5 of 12 test cases with the skill, and 4 of 12 without it.

Without skill32%

With skill45%

Checks it passed that the model alone missed

The second-to-last choice is explicitly Other.
The request passes the PROBLEM_ANALYSIS.md artifact intent.
The 5 Whys breakdown terminates at unknown due to missing crash logs.

and 6 more in the full report

6 fixed4 passed either way9 still failing3 broke

Pass-rate lift: +14 pp
Tokens: +7%
Agent turns: 0%
Response time: -30%

Model gemini-3.6-flashMeasured 8/24/2026v110 of 22 cases passed with skill · 12 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/optim-agent-analyze-and-plan/SKILL.md https://app.decimal.ai/s/optim-agent-analyze-and-plan/SKILL.md

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

decimalai skills add optim-agent-analyze-and-plan

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

curl -fsSL --create-dirs -o .claude/skills/optim-agent-analyze-and-plan/SKILL.md https://app.decimal.ai/s/optim-agent-analyze-and-plan/SKILL.md

Raw file: /s/optim-agent-analyze-and-plan/SKILL.md ↗ · machine-readable summary at /s/optim-agent-analyze-and-plan.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

After inspecting the database connection timeout issue in `config/database.yml`, we decided to opt in to generating a plan. What is the required sequence for writing `PROBLEM_ANALYSIS.md` relative to `PLAN_v1.md`?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies writing PROBLEM_ANALYSIS.md before PLAN_v1.md in the artifact directory.	Passed	Passed
The response mentions recording the first controller-backed planning question before creating PROBLEM_ANALYSIS.md.	Missed	Passed

case-14 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md34 linessingle file

Analyze and Plan

Use this skill for problem/failure inputs that need diagnosis before planning. Do not use it for ordinary feature planning, direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.

Workflow

Inspect available evidence first: repo files, logs, tests, command output, or user-provided symptoms.
Produce an in-message RCA summary before asking whether to plan. Use at most 5 Whys. Stop with unknown when evidence is insufficient; do not invent a cause.
Ask one choice prompt that includes the RCA summary. The choices are: recommended first to call optim-plans, second to review the summary only without a plan, Other second-last, and Auto-complete last.
On opt-out, stop after the summary. Do not write PROBLEM_ANALYSIS.md on opt-out.
On opt-in or Auto-complete choosing the recommendation, select the smallest fitting planning level, read and follow ../{selected-level}/SKILL.md, and preserve that skill's first-turn contract.
Pass the original problem, RCA summary, evidence, and PROBLEM_ANALYSIS.md artifact intent as the planning request. The selected planning skill must initialize controller state and present and record its first controller-backed planning question before PROBLEM_ANALYSIS.md is written.
After opt-in, selected planning skill first controller-backed planning question recording, and selected run artifact_dir availability, write PROBLEM_ANALYSIS.md in that artifact_dir before PLAN_v1.md.

Level Selection

mini-plan: single-file, low-risk, clear root cause, obvious fix.
small-plan: a few local files or behavior checks, limited risk.
plan: normal multi-file fix with several decisions.
big-plan: architecture boundary, external API/dependency, compatibility, or websearch risk.
huge-plan: open-ended or cross-system issue where the RCA points to redesign.

PROBLEM_ANALYSIS.md

Include:

Original problem
Evidence inspected
RCA summary
5 Whys, ending early with unknown when evidence stops
Suspected root cause
Planning level selected and why

Auto-complete may opt into planning, but Auto-complete cannot approve execution.

Track record

Benchmark

5 / 12

test cases passed, vs 4 / 12 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

optim-agent / optim-plans

skills/analyze-and-plan/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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

optim-agent/diagnose-before-planDiagnose failures before creating a Prime Agent plan. MUST USE for bugs, CI failures, test failures, regressions, incidents, broken behavior, root cause, RCA, or debug-why requests before deciding whether to plan; preserve language, reviewer, and criticizer settings in .git/optim-plans; exclude ordinary feature planning, direct implementation-only, factual/explanation, trivial command-only, or explicit no-plan requests.Close match+45 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

Analyze and Plan

Workflow

Level Selection

PROBLEM_ANALYSIS.md

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills