proposal
Skill2 starsChanged 5 days agoMITView on GitHub
- Turn a task or problem into a reviewable proposal before implementation. - Refine a hand-edited or external proposal before planning or implementation. - Hand any downstream reader, human or agent, a proposal whose every claim merits building or proving. - Settle design, decisions, and limits from confirmed findings; leave no open question. - Write the target proposal, present it for review, and change nothing else: - Draft: a new ./<slug>-proposal.md. - Refine: the supplied proposal, in place. - Draft:…
17 other projects use a version of this.
Adopted by
Most recently taken up by
- meslva/claude-skillstheir own version, first seen Nov 8, 2026
- aya-taleb/biz-boost-skillstheir own version, first seen Nov 1, 2026
- ChuluuMGL/proposal-skilltheir own version, first seen Oct 25, 2026
- adeerkhan/vitruviustheir own version, first seen Oct 20, 2026
- zubair-trabzada/ai-proposal-claudetheir own version, first seen Oct 17, 2026
- chriswestt/claude-skillstheir own version, first seen Oct 9, 2026
Used with
Projects with it also use audit.
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.
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- ajsahni/agents-office★ 601same name
- AlpacaLabsLLC/skills-for-architects★ 420same name
- zubair-trabzada/ai-proposal-claude★ 39same name
- GTMify/aigtm★ 25same name
- alejopijuan/Claude-Code-Agency-Co-Founder★ 19same name
- adeerkhan/vitruvius★ 10same name
- ChuluuMGL/proposal-ppt-skill★ 3same name
- ChuluuMGL/proposal-skill★ 3same name
- kurenn/claude-skill-proposal★ 2same name
- youdcode/open-company★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- auto-commitSkill
- cleanSkill
- code-reviewSkill
- coverageSkill
- documentSkill
- purifySkill
- puritySkill
- refactorSkill
- spae-buildSkill
- spae-checkSkill
- spae-fixSkill
- spae-inspectSkill
- spae-orchestrateSkill
- spae-planSkill
- spae-prepareSkill
- spae-spawnSkill
- spae-specSkill
- spae-verifySkill
- structureSkill
- testSkill
- tipSkill
- troubleshootSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
21 rules. 0 are common, 16 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
16
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
- Distinctive: line 29
Write the target proposal, present it for review, and change nothing else:
- Distinctive: line 63
Every file except the target stays unmodified.
- Distinctive: line 64
Read project instruction and architecture docs in full when present.
- Distinctive: line 76
Read codebase sections narrowly.
- Distinctive: line 77
Run planned experiments per Constraints.
- Distinctive: line 101
Never reference conversation context, prior runs, or paths absent from the repository, such as deleted experiment directories.
- Distinctive: line 119
Codebase fit: prefer existing patterns over new design.
- Distinctive: line 129
Never prescribe rigs, recipes, pixel coordinates, key sequences, or tooling provisioning.
- Very specific: line 136
Never emit Unverified, open-question, TODO, or follow-up sections.
- Distinctive: line 142
Write scope: write only the target; never edit any other file.
- Distinctive: line 144
Run one only when source and docs can't settle a decision.
- Very specific: line 145
Keep each minimal, unattended, timeout-bounded, and confined to a mktemp -d directory outside the repository.
- Distinctive: line 148
Use installed tooling only.
- Distinctive: line 152
Autonomy: never ask the user for input mid-execution.
- Distinctive: line 155
Version control and release: never propose or run git mutations, package publishing, or deployments.
- Very specific: line 157
No further changes: after REPORT, stop; never implement the proposal.
- Very specific: line 175
Every claim names something to build, preserve, decide, reject, or accept.
- Very specific: line 178
Every Design claim passes the references/outcome-guide.md substitution test.
- Distinctive: line 189
No experiment directory remains.
- Distinctive: line 196
Keep prose terse while ensuring clarity.
- Distinctive: line 199
Use lists and sub-lists for long sentences and dense paragraphs.
“Common” is measured: kept by at least 6 in 10 of the 15 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.
Files
Proposal
When to use
- Turn a task or problem into a reviewable proposal before implementation.
- Refine a hand-edited or external proposal before planning or implementation.
- Hand any downstream reader, human or agent, a proposal whose every claim merits building or proving.
Goal
- Settle design, decisions, and limits from confirmed findings; leave no open question.
- Write the target proposal, present it for review, and change nothing
else:
Draft: a new./<slug>-proposal.md.Refine: the supplied proposal, in place.
Input
Draft: task statement from the argument, the conversation, or a task-only file.Refine: path to an existing proposal file.- Project instruction and architecture docs, when present—for example
AGENTS.md,CONTRIBUTING.md,README.md. - Codebase sections the proposal touches.
references/PROPOSAL.md: section template.references/prose-protocol.md,references/outcome-guide.md,references/verification-guide.md.
Workflow
Select path by argument:
Refine: argument names an existing file holding a proposal.Draft: otherwise; a file holding only a task statement supplies the task.
- GATE—Make no writes:
- Select
DraftorRefine; set the target:Draft: derive a kebab-case<slug>from the task; target./<slug>-proposal.md; confirm it doesn't exist.Refine: target the supplied file; read it in full.
- Inside a git repository, record
git --no-pager status --porcelainas baseline. - Halt on any Halt conditions entry.
- Select
- ORIENT—State goal and path in one sentence:
- Every file except the target stays unmodified.
- Read project instruction and architecture docs in full when present.
- PLAN—Declare the work:
Refine: build a claim ledger—every claim in the target, with its rationale and section.- List investigation questions:
Draft: the task's unknowns.Refine: open questions and claims needing source confirmation.
- Name the codebase sections each question needs.
- Name an experiment only for a question source and docs can't settle; state the decision it informs.
- ACT—Investigate, draft, refine:
- Read codebase sections narrowly; widen only on uncertainty.
- Run planned experiments per Constraints; delete their temporary directories afterward.
Draft: draft perreferences/PROPOSAL.mdand Directives.Refine: restructure the target perreferences/PROPOSAL.mdand Directives.- Refine with confirmed findings; resolve every open question per Directives.
- VERIFY—Loop over Verification criteria:
- For each failure: return to
ACT, fix, then re-enterVERIFY. - Exit only when every criterion passes.
- For each failure: return to
- PERSIST—Write the target—
Draft: create;Refine: overwrite in place; re-read it to confirm the content. - REPORT—Emit result following result directives and using result template; then stop.
Directives
- Optimize for agent, token, and context efficiency.
- Consult
references/prose-protocol.mdandreferences/outcome-guide.mdbefore drafting. - Self-contained: readers, often agents, use the proposal for varied
purposes, with no memory of this run or conversation; keep it
self-contained, explicit, and token-dense:
- Define non-standard terms on first use.
- Never reference conversation context, prior runs, or paths absent from the repository, such as deleted experiment directories.
- Claims become scope: downstream readers turn every claim into a
requirement, test, or exclusion; write only what merits building,
preserving, or proving. State
Designas components, interfaces, and contracts; bind an internal choice throughDecisionswith its rationale, else omit it. - Condense, never drop (
Refine): tighten wording; keep every claim and its rationale; move a discarded claim toRejectedorAccepted limitswith a one-line rationale, never silently. - Evidence versus verification:
Evidence: how findings surfaced; downstream readers treat it as assumptions, never obligations.Verification: outcomes the implementation must prove, each paired with its cheapest proving evidence.
- YAGNI: discard unrequested scope, speculative design, and
theoretical complexity; log each discard under
Rejectedwith a one-line rationale. - Codebase fit: prefer existing patterns over new design.
- Size: scale detail to task size; write
Noneunder a section without content; keep headers intact. - Proportional verification, per
references/verification-guide.md:- Pair each outcome with the lowest evidence-ladder rung proving it, or prose with reading.
- Require only tooling the repository already declares or installs.
- File outcomes only a real GUI, browser, or native input can prove
under
Accepted limits; require such evidence only when the task explicitly asks or the repository already declares the tooling. - Never prescribe rigs, recipes, pixel coordinates, key sequences, or tooling provisioning.
- Open questions: resolve each with prudent discretion—smallest
scope meeting the goal; the conservative option when evidence stays
insufficient:
- Settle each into
Design,Decisions,Accepted limits, orRejected. - Never emit
Unverified, open-question, TODO, or follow-up sections.
- Settle each into
- Plan boundary: omit delivery ordering, task decomposition, and implementation sequencing; leave them to whoever plans the work.
Constraints
- Write scope: write only the target; never edit any other file.
- Experiments:
- Run one only when source and docs can't settle a decision.
- Keep each minimal, unattended, timeout-bounded, and confined to a
mktemp -ddirectory outside the repository; delete it beforePERSIST. - Use installed tooling only; never provision tooling or build GUI or native-input rigs unless the task explicitly asks.
- Isolate from the user's desktop, input devices, browser profiles, accounts, and live services.
- Autonomy: never ask the user for input mid-execution; never propose steps requiring human execution, an attended terminal, or human presence.
- Version control and release: never propose or run git mutations, package publishing, or deployments.
- No further changes: after
REPORT, stop; never implement the proposal. - Halt conditions: halt without writing; report
Failedwith a diagnostic underFindings:Draft: no task supplied.Draft:./<slug>-proposal.mdalready exists.Refine: target unreadable or empty.
Verification
- The target exists, follows
references/PROPOSAL.mdsection order, and complies withreferences/prose-protocol.md. - The target stays self-contained: no reference to conversation context, prior runs, or paths absent from the repository; non-standard terms carry definitions.
Refine: every claim-ledger entry maps to a target section,RejectedandAccepted limitsincluded; no claim or rationale vanishes.- Every claim names something to build, preserve, decide, reject, or
accept; no open question,
Unverifieditem, TODO, or follow-up survives. - Every
Designclaim passes thereferences/outcome-guide.mdsubstitution test; every bound internal choice sits underDecisionswith its rationale. - Each
Verificationrow names existing repository tooling and its ladder rung, or reading for prose; no new tooling, rig, recipe, coordinate, or key sequence appears. - GUI-, browser-, or native-input-only outcomes sit under
Accepted limits, unless the task opted in. Evidenceimposes no obligation; no delivery ordering or task decomposition appears.- Section depth matches task size.
- No experiment directory remains.
git --no-pager status --porcelaindiffers from the GATE baseline only in the target's entry.
Result directives
- Minimum words. Maximum signal.
- Keep prose terse while ensuring clarity.
- Optimize prose for agent, token, and context efficiency.
- Split actions, findings, and summaries into terse bullet points.
- Use lists and sub-lists for long sentences and dense paragraphs.
- Result contract: orchestrating agents parse
Result; a missing, altered, or inconsistent result breaks orchestration. - End every run—completion, short-circuit, abort, or halt—with the result template as the final message; never end on progress narration.
- Set
Resultto exactly one template literal, verbatim; report an abort or halt lacking its own literal asFailed, with the reason underFindings. - Emit the result template as live markdown—never in a code fence.
- Output nothing outside the template.
Result template
<!-- prettier-ignore-start -->### Execution Summary
- **Actions**:
- [Terse list of actions taken]
- **Files**:
- [Proposal path]
- **Findings**:
- [Terse list of notable findings, risks, or halt diagnostics]
- **Summary**:
- **Decisions**: [Terse list of key decisions]
- **Accepted limits**: [Terse list of accepted limits and residual risks]
> **Proposal Status** • `[slug]`
> **Result**: [Drafted | Refined | Failed]
> **Impact**: [Terse impact statement]
> **Path**: `[target path]`
>
> _Review the proposal before planning or implementation._ _(unless failed)_<!-- prettier-ignore-end -->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
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.

