Ready to supercharge your AI agents?

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

Get Started Free →

plan-interrogate · rohitg00 | DecimalAI

productivityby rohitg00

plan-interrogate

rohitg00/plan-interrogate

Source rohitg00/pro-workflow ↗License Not recorded

Stress-test a plan by walking its decision tree one question at a time.

SkillScore77Maintained

Automatic

Product Management pack

Last verified 8/13/2026

What it changes

Passed 16 of 21 test cases with the skill, and 11 of 21 without it.

Without skill55%

With skill77%

Checks it passed that the model alone missed

The file path proposed or written is CONTEXT.md.
The entries follow the term definition format term - definition.
The response addresses Node A before posing questions about Node B.

and 8 more in the full report

7 fixed10 passed either way3 still failing2 broke

Pass-rate lift: +23 pp
Tokens: -5%
Agent turns: 0%
Response time: -50%

Model gemini-3.6-flashMeasured 8/13/2026v117 of 22 cases passed with skill · 21 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/rohitg00-plan-interrogate/SKILL.md https://app.decimal.ai/s/rohitg00-plan-interrogate/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rohitg00-plan-interrogate, 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/rohitg00-plan-interrogate/ and pins it in .decimal/skills.lock

decimalai skills add rohitg00-plan-interrogate

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

curl -fsSL --create-dirs -o .claude/skills/rohitg00-plan-interrogate/SKILL.md https://app.decimal.ai/s/rohitg00-plan-interrogate/SKILL.md

Raw file: /s/rohitg00-plan-interrogate/SKILL.md ↗ · machine-readable summary at /s/rohitg00-plan-interrogate.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Here is a draft proposal to add an asynchronous background job queue for processing large file exports. Please interrogate this proposal before we jump into development. Identify all dependent choices and work through open questions sequentially—ask me just one question at a time paired with your proposed answer and short justification. Check existing project docs and commits so you skip questions already resolved by the codebase. Finally, provide the complete ledger of finalized choices that I can copy straight into the design document, strictly without conversational summaries.

What was checked, without and with the skill
Checked	Without skill	With skill
The response restates the background job queue plan in one paragraph.	Missed	Passed
The response requests confirmation from the user on the restatement before posing questions or interrogating decisions.	Missed	Passed

case-02 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md66 linessingle file

plan-interrogate

Drive a plan from sketch to commitment by resolving every open decision before any code is written.

Method

Restate the plan in one paragraph. Confirm with the user that this is the plan being interrogated. Do not proceed on a mis-restatement.
Extract the decision tree. Every branch point becomes a node. Mark each node as open (undecided) or resolved. A resolved node carries a source tag: user (the user answered), inferred (the codebase or an existing constraint settled it).
Resolve in dependency order. A node is ready when every node it depends on is resolved.
For each ready open node, ask exactly one question. Keep the question tight and binary or small-multiple-choice when possible.
Pair every question with a recommended answer and one sentence of reasoning. The user can confirm, pick a different option, or push back.
Before asking, check whether the answer already lives in the codebase, prior commits, or an existing doc. If so, skip the question and mark the node resolved with source inferred: <path>.
Exit only when zero nodes are open. Print the resolved tree as a flat list: Decision - Choice - Source (user | inferred: <path>).

Anti-patterns

Asking multiple questions at once. The user loses context and you lose the ability to react to each answer individually.
Asking before exploring. If a fifteen-second read would answer the question, read first.
Asking without a recommendation. A question without a stance is a survey; it offloads design onto the user.
Rolling past an unresolved node. If a dependency is not pinned, the downstream question is premature.

Outputs

The interrogation produces three artifacts, not just answers. Offer to write each; do not force it.

Track record

Benchmark

16 / 21

test cases passed, vs 11 / 21 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

rohitg00 / pro-workflow

skills/plan-interrogate/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

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

plan-interrogate

Method

Anti-patterns

Outputs

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills