agentleFS
Sign inStart free
ChristopherAlphonseChristopherAlphonse/calphonse-skills/lets-talk-about-it/SKILL.md

lets-talk-about-it

Skill1 starsChanged 10 days agoMITView on GitHub

One-pass interrogation and coding guardrails. Use to stress-test a plan, design, code change, or domain term against local code/docs while enforcing explicit assumptions, simplicity, surgical edits, and verifiable success criteria.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask at most one question at a time, only when the answer changes scope, architecture, risk, terminology, or verification.

    line 13
  2. Distinctive:

    Prefer the simplest viable option.

    line 15
  3. Distinctive:

    Keep edits surgical: touch only requested files/behavior, match local style, and clean up only unused code introduced by your own changes.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lets Talk About It

Stress-test before committing. Optimize for one useful pass, not exhaustive questioning.

Operating Contract

  • Inspect local evidence first: CONTEXT.md, CONTEXT-MAP.md, ADRs, specs, plans, task lists, configs, tests, and nearby source.
  • Ask at most one question at a time, only when the answer changes scope, architecture, risk, terminology, or verification.
  • State assumptions, contradictions, tradeoffs, and unresolved decisions explicitly.
  • Prefer the simplest viable option. Do not add speculative features, abstractions, configurability, or future-proofing.
  • Keep edits surgical: touch only requested files/behavior, match local style, and clean up only unused code introduced by your own changes.
  • Define success criteria before implementation, then verify with the narrowest meaningful check.

One-Pass Flow

  1. Frame: Restate the goal, known context, assumptions, and non-goals.
  2. Check evidence: Compare the plan or claim against local docs and code. Cite files for important findings.
  3. Interrogate: Walk only the relevant branches: problem, users, requirements, terminology, architecture, data/API flow, security, performance, reliability, tests, deployment.
  4. Decide: Recommend the simplest defensible path and name rejected alternatives.
  5. Verify: List concrete checks: tests, commands, browser steps, metrics, or review criteria.

Output

Return only what the task needs:

  • Recommendation
  • Assumptions / open questions
  • Scope and non-goals
  • Risks / tradeoffs
  • Verification checklist
  • CONTEXT.md or ADR updates, only when a durable domain term or hard-to-reverse decision was actually resolved

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free