agentleFS
oeveryoevery/rsp/skills/rsp-shape/SKILL.md

rsp-shape

Skill1 starsChanged 8 days agoMITView on GitHub

Resolve bounded design questions read-only or clarify material choices and plan authorized work as one executable Change or justified shallow Group. Not decision approval, implementation or final-record cleanup.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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 one to three related material questions ordinarily, one DecisionOwner question per turn for deep clarification.

    line 40
  2. Distinctive:

    Read external issue input only when a Change declares an issue relationship or the request asks to shape from an issue URL.

    line 44
  3. Distinctive:

    Never invent a product decision.

    line 46
  4. Distinctive:

    Read complex shaping when authorized planning involves multiple material decisions or independently acceptable outcomes with …

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

RSP Shape

For tracked work, read the shared work model when its identity and ownership definitions are missing from the current context. Use logical WorkRefs in commands and reports; cite file locations separately. Direct invocation needs no prior Core execution.

Choose the branch before loading detail: bounded design advice is read-only and may have no Change; explicit planning-artifact work shapes or refines a Change/Group. Neither branch implements product behavior.

Shape clarifies decisions and writes planning artifacts, including Markdown. The authorized DecisionOwner approves material choices. Doc may word settled decisions and reconcile final work records. Return unresolved material choices to Shape; prose cleanup cannot settle them.

Responses follow explicit instruction, personal instructions, then conversation language. Preserve existing artifact language and canonical identifiers, commands and values. For new artifacts, use explicit instruction, effective configuration, scoped project instructions, then conversation language.

Resolve needed RSP settings, including defaults and inheritance, through the selected CLI's successful rsp config --json summary; refresh on relevant drift or recovery. Raw YAML is diagnostic only. Projection failure blocks dependent choices, not independent authorized work; return material conflicts to the owner.

Establish the boundary

Read the request, authority, nearest project context, Change and Brief when selected, then only decisive evidence. A direct design question without a Change does not require one. A design question inside a tracked Change retains that WorkRef, but defaults to report-only; only explicit artifact authority permits updating its Design.

For structural or responsibility decisions, use architecture knowledge to inspect any existing model and distinguish current facts from proposed design.

A request to shape, create, or refine a Change grants artifact authority unless no-edit; advice does not. If creation focuses it, preserve the exact prior focus and restore it immediately unless selection was requested. Shaping grants no other authority; preserve unrelated work.

Route concrete or ready work to implementation only when authorized and no design/planning question remains. An explicit read-only design request still ends with its report. Do not rewrite settled work for style or completeness.

Resolve material ambiguity

Inspect the repository before asking. Ask for unresolved owner decisions affecting behavior, data, interfaces, compatibility, safety, ownership, migration or acceptance. Reuse settled answers until evidence invalidates them. Ordinary implementation choices within that contract need no new decision or planning pass. Write only authorized answers.

Derive requirements and acceptance checks from settled authority. Do not make a preferred implementation or unsettled public behavior, failure contract, default or compatibility choice mandatory. Keep replaceable internal choices in Design, label material alternatives as proposals and put readiness-blocking decisions in Blockers.

Choose permitted methods within the branch. Recover a diagnosed read/search fault against unchanged goal, scope, authority, baseline and evidence. Inspect artifact/focus effects before replaying planning mutations; unknown effects or unsafe replay stop that action. Required RSP commands/checks cannot be replaced by prose or tool status.

Ask one to three related material questions ordinarily, one DecisionOwner question per turn for deep clarification. Resume unresolved decisions from fresh facts and return the ready owner to Core; a method change alone restarts no workflow.

For a bounded design question, load only the relevant domain modeling, module and seam design, or reversible exploration method. Read deep clarification only for explicit rigorous challenge or dependent high-risk decisions. Advice does not create or modify an artifact, authorize a disposable code probe, or turn a recommendation into product authority.

Read external issue input only when a Change declares an issue relationship or the request asks to shape from an issue URL.

Never invent a product decision. When a material choice or mutation authority remains unresolved, leave the work open and report the single highest-impact blocker.

Choose the owner

For authorized planning-artifact work, read planning and readiness before choosing or naming an owner, writing a Change/Group, or updating the selected Design. Read-only design advice needs none of those artifact procedures.

Read complex shaping when authorized planning involves multiple material decisions or independently acceptable outcomes with dependencies/integration. Work shape does not enable agent delegation.

Apply the Shape Ready gate

For planning, apply the complete Shape Ready gate, then run the focused RSP check after authorized mutation. On pass, return the ready Change WorkRef or Group reference, artifacts and decisive evidence for Core to continue the authorized objective without another user request.

For read-only design, lead with the recommendation and decisive evidence. Include credible tradeoffs, owner decisions and a next action only when relevant to the current question; do not restate settled context or force a planning report. Create or mutate no plan automatically.

When a material decision prevents readiness, stop with decisive evidence, the DecisionOwner and required answer; resume from fresh relevant evidence after that answer. For other blockers, state the actual missing input, next owner and safe resume condition. Use canonical machine fields such as StopDisposition only when a real consumer requires them. Do not report unresolved material decisions as ready work.

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.