agentleFS
Sign inStart free
ParadevAIParadevAI/Paradev/.agents/skills/decide/SKILL.md

decide

Skill16k starsChanged 10 days agoMITView on GitHub

Walk the user through design or implementation decisions one at a time, or review completed code one change at a time. Use when the user says "walk me through each decision", "let's decide together", "help me work through these choices", "walk me through what you did", or "QA step by step". Present concise context, mutually exclusive options, log each answer, and finish with a summary.

51 other projects use a version of this; 1 new project in the last 4 weeks, against 0 the 4 before.

Adopted by

Surging: 1 new project took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 1 new project
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 1 in all, so this is a hint, not a trend.

Most recently taken up by

Who's talking about ParadevAI/Paradev

The biggest 5 of 64 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 64

Talked about on GitHub, the web, Bluesky and YouTube (64 times).

On GitHub · 50

45 more on GitHub

On the web · 11

6 more on the web

Used with

Projects with it also use weekly, experiment and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gaiaaiagentSkill

    weekly

    Generate a weekly digest rolling up dailies into higher-level pattern analysis

    Also in 3 projects that use this

  • SethGammonSkill

    experiment

    Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures with a metric command, keeps improvements, discards failures. Supports convergence detection and diminishing returns.

    Also in 3 projects that use this

  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 3 projects that use this

  • AnthropicSkill

    brief

    Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

    Also in 5 projects that use this

  • genomewalkerSkill

    health

    Soul system health check with remediation

    Also in 3 projects that use this

  • AWSSkill

    map

    Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before a design walkthrough, inspect the relevant code and record concrete bugs, inconsistencies, and decision points in …

    line 10
  2. Distinctive:

    Ask exactly one interactive question with two to four mutually exclusive options.

    line 21
  3. Very specific:

    Use ask_user when available.

    line 22
  4. Distinctive:

    Never substitute a plain-text question when repository instructions require an interactive overlay.

    line 23
  5. Distinctive:

    Keep labels to five words or fewer.

    line 24
  6. Very specific:

    Put the recommendation first and suffix its label with (Recommended).

    line 25
  7. Very specific:

    Do not add an Other option when the client adds one automatically.

    line 27
  8. Very specific:

    After the answer, write Logged: <decision>.

    line 28
  9. Distinctive:

    If the user acknowledges an issue without choosing, log the recommended choice and say they can correct the assumption.

    line 30
  10. Distinctive:

    Use this mode when the user wants to review existing code step by step.

    line 36
  11. Distinctive:

    Wait for the verdict before showing the next step.

    line 45
  12. Distinctive:

    If a step reveals a genuine design fork, pause the QA walkthrough and offer to switch to decision mode for that fork.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 49 edited versions of this file we could read. “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

Decide

Prepare

Before a design walkthrough, inspect the relevant code and record concrete bugs, inconsistencies, and decision points in plans/<YYYYMMDD>-<topic>.md or the appropriate app-scoped plans/ directory. Preserve existing edits; never discard speculative or user-authored work without explicit approval.

Order decisions by dependency and leverage, not document order.

Decision walkthrough

For each decision:

  1. Show ## Decision N: <title>.
  2. Give two to four sentences of context grounded in real files or functions.
  3. State the trade-off in one sentence.
  4. Ask exactly one interactive question with two to four mutually exclusive options.
    • Use ask_user when available. In Codex Plan mode, use request_user_input when that is the exposed interactive question tool.
    • Never substitute a plain-text question when repository instructions require an interactive overlay.
    • Keep labels to five words or fewer.
    • Put the recommendation first and suffix its label with (Recommended).
    • Explain each option and its trade-off in one sentence.
    • Do not add an Other option when the client adds one automatically.
  5. After the answer, write Logged: <decision>. and continue.

If the user acknowledges an issue without choosing, log the recommended choice and say they can correct the assumption.

At the end, provide a | # | Decision | Choice | table and offer to turn the audit into an implementation plan. Do not write implementation code during the decision walkthrough.

QA walkthrough

Use this mode when the user wants to review existing code step by step.

  1. Identify the review unit: a commit, staged diff, PR, or explicit file set.
  2. Break it into logical steps in dependency order.
  3. Show one step per turn with:
    • ## Step N: <title>
    • One or two sentences explaining what changed and why
    • A focused real-code excerpt with file and line references
    • One interactive verdict question: Looks good, next step (Recommended), Push back, change this, and, only for non-trivial code, Pause, explain more
  4. Wait for the verdict before showing the next step.
  5. Log approvals, collect requested changes, and finish with a | # | Step | Verdict | table.

If a step reveals a genuine design fork, pause the QA walkthrough and offer to switch to decision mode for that fork.

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