agentleFS
Sign inStart free
orbyn-devorbyn-dev/orbyn-fullstack-skills/skills/figure-it-out/SKILL.md

figure-it-out

Skill4 starsChanged 10 days agoMITView on GitHub

Execute an authorized large migration or cross-cutting change through to its measurable end state, tracking every unit. Use orbyn-plan when the deliverable is only a plan.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ketchup-video, principle-explain-the-number and 10 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.
  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 14 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 29 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 20 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • Xia-AtaraxiaSkill

    benchmark-checklist

    Vets performance measurements for the limiter, tuning, physical limits, errors, repeatability, relevance, and proof that timed work happened. It applies to 'check this benchmark', 'report this speedup', measured regressions, and choosing a library or configuration from numbers. It reports spread and gaps before drawing a conclusion. Not for general testing policy or choosing test oracles - use principle-testing.

    Also in 34 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 54 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow the consuming project's instructions and requested scope.

    line 8
  2. Distinctive:

    Use orbyn-plan to establish or revise the execution plan and stack ownership to place changes.

    line 10
  3. Distinctive:

    Define the end state: Write a checkable end state, exclusions and the largest unresolved risk.

    line 15
  4. Distinctive:

    Inventory the units from current source,: not an estimated file count, before planning.

    line 16
  5. Distinctive:

    Sequence by dependency and risk: Use coherent units that can be inspected without leaving ambiguous ownership, and take the riskiest …

    line 17
  6. Very specific:

    Follow the workflow lead contract.

    line 27
  7. Distinctive:

    Use show-me-your-work for decisions that matter later.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 54 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

Figure it out

Follow the consuming project's instructions and requested scope; use the portable defaults only where guidance is missing. Use orbyn-plan to establish or revise the execution plan and stack ownership to place changes.

Method

  1. Define the end state. Write a checkable end state, exclusions and the largest unresolved risk.
  2. Inventory the units from current source, not an estimated file count, before planning. Mark each as pending, active, verified, deferred by the user or blocked by a named dependency. Keep one task record rather than separate competing plans.
  3. Sequence by dependency and risk. Use coherent units that can be inspected without leaving ambiguous ownership, and take the riskiest complete path first.
  4. Set up each unit. Record its entry revision, expected artifact, authorized check, and reversible recovery point. Follow the user's verification scope. Use existing tools before building automation; create a small reusable helper when repetition or reliable checking justifies it.
  5. Execute each unit. The lead states the hypothesis and throughput checkpoint, delegates substantial investigation/implementation with owned files, inspects the actual artifact and diff, and performs authorized verification.
  6. Recover from failure. Preserve the failure and useful evidence, correct the disproven assumption and revise the hypothesis before retrying; repeat an unchanged failed attempt only with a new explanation. If a provider or operator step is unavailable, continue independent units and leave that step visibly unverified.
  7. Reconcile at the end. Check the full inventory against actual files and check receipts. Close only units whose artifacts exist and whose required evidence was obtained. Report verified, unverified and blocked parts, including remaining work in the requested end state even if the local implementation is complete. Never silently reduce the requested outcome.

A service or API extraction unit includes shared schema, consumers, routing, contract, persisted state, the old handler and its retirement condition. Close it when all of those are done; a new handler alone leaves it open. Keep unfinished operator/deployment work visible in the report instead of moving it to a future-work paragraph and calling the migration complete.

Delegation and records

Follow the workflow lead contract. Keep coupled contract/caller edits with one owner, isolate genuinely independent output paths, and stay within the resolved harness max_children. Route corrections to the same owner. A child executes its owned unit directly without delegation.

Use show-me-your-work for decisions that matter later.

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