Automated summary
Designs and hardens the cheapest executable proof that discriminates settled intent from a realistic wrong implementation before building or promoting a candidate.
Strengths
- Requires discriminating proof with opposite-direction controls and realistic wrong-implementation analysis.
- Keeps proof mutation with one writer while read-only oracles return evidence, avoiding competing proof candidates.
- Provides explicit routes for weak proof, writer collisions, changed plans, and already-proven cases.
Limitations
- Relies on an issue plan, governing contract, and the spec-to-test, review-tests, and build-candidate skills.
- Does not implement the feature or write the proof itself; it orchestrates proof preparation and review.
- Assumes branch/worktree discipline and a single proof writer at a time.
Use when intent is settled and you need an executable proof before implementation or candidate promotion.
Avoid for open-ended exploration, trivial changes with no proof need, or when there is no executable proof subject.
Security analysis
SafeThis is a process-only skill describing proof/test preparation workflows, routes, and handoffs to other skills. It declares no tools, contains no shell commands, network calls, file mutations, secret handling, or obfuscated payloads, so there is no meaningful execution risk.
No concerns found
How this analysis is madeExamples
Use prepare-proof for issue #142: an expired token must return 401 without refreshing the session. Produce the cheapest executable proof, challenge it with a realistic wrong implementation, and route the result.Before promoting candidate auth-refresh-v2, prepare proof against the governing contract and current production path. Strengthen any weak proof and stop if the worktree is unsafe.The test for SPEC-88 passes, but I don't trust that it fails for the right reason. Use prepare-proof to review the observed execution and add opposite-direction controls before we build.name: prepare-proof description: Turn settled intent into the cheapest discriminating executable proof before implementation or candidate promotion. argument-hint: "[issue, spec, or candidate]"
Prepare proof
Use the issue plan, governing contract, current semantic owner, production path, existing tests, and independent external authority.
Proof design, independent oracle challenge, realistic wrong-implementation analysis, opposite-direction controls, production-path review, and proof economics may be investigated independently when useful.
When tests, fixtures, schemas, or proof receipts require mutation, use the selected claim's current branch/worktree and one proof writer at a time. Read-only adversaries and oracles return evidence to that writer; they do not create competing proof candidates. Do not inspect sibling worktrees or neighbouring PR overlap merely to reserve a proof surface.
Flow
- Resolve current inputs and establish or reuse the current proof candidate/writer when proof artifacts require mutation.
- Invoke
spec-to-testto materialize and execute the proof. - Invoke
review-testsagainst the observed execution and realistic wrong implementations. - Strengthen and re-execute the proof until adequate.
- Continue to
build-candidatewithout routine approval.
Routes
PROOF_READY→build-candidateWEAK_PROOF→spec-to-test, thenreview-testsWRITER_COLLISION/UNSAFE_WORKTREE→ preserve the same-candidate mutation hazardPLAN_CHANGED/MATERIAL_PREMISE_CHANGED→prepare-issueMORE_ORACLE_RESEARCH→ research, then repeatNO_EXECUTABLE_PROOF_SUBJECT→ return to the invoking public flow for proportional candidate/claim reviewALREADY_PROVEN→build-candidateNOT_PROVEN→ preserve the missing evidence
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/prepare-proof-ms71b33y/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/prepare-proof-ms71b33y' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/prepare-proof-ms71b33y/download' --output '.skill-downloads/prepare-proof-ms71b33y/SKILL.md.part' && mv '.skill-downloads/prepare-proof-ms71b33y/SKILL.md.part' '.skill-downloads/prepare-proof-ms71b33y/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/prepare-proof-ms71b33y/SKILL.md' && test -s '.skill-downloads/prepare-proof-ms71b33y/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/prepare-proof' && cp -R '.skill-downloads/prepare-proof-ms71b33y' '.claude/skills/prepare-proof'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/prepare-proof-ms71b33y'openskills read 'prepare-proof-ms71b33y'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/prepare-proof-ms71b33y/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.