Claude Skills by OutlineDriven

Automated contract verification, detection, and remediation across multiple languages using formal preconditions, postconditions, and invariants. This skill provides both reference documentation AND execution capabilities for the full PLAN -> CREATE -> VERIFY -> REMEDIATE workflow.

Use when property-based testing, theorem proving, or formal proof tactics require zero unproven properties. Produces passing proofs and tests, sufficient coverage, and regression tests for every counterexample. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the work is modeling a domain, encoding a state machine, hardening an API boundary, making invalid states unrepresentable, or parsing instead of validating. Not for TypeScript-specific doctrine — use typescript-best-practices; not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to run AST-based structural search, lint, or rewrite of code when regex is too fragile. Pattern is validated, blast radius reviewed, and rewrite landed at the correct scope. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when the user describes an AI workflow gap or uses an ambiguous cross-session reference such as ''the PR Bob mentioned''. Resolves each to a stable handle and surfaces collaboration anti-patterns when reached. Don''t use for tasks that require source or remote-system changes.

Use when a task is ambiguous, maximum clarification is needed before planning, or the user requests exhaustive, collaborative, or adversarial askme mode. Runs Verbalized Sampling, fires batched clarifying questions, and confirms intent before planning proceeds. Not for source or remote-system changes; not for a single fork — use decide.

Use when the user requests axiom, axiom-mode, axiom-compact, formal-logic, or compact form. Switches responses to compact formal-logic English with predicate claims and ASCII keywords, then restores the register after clarity exceptions. Not for changing code or remote state.

Use when dependency upgrades need tiered batches for CVEs, a major release, forced compatibility, scheduled hygiene, a pre-release lockfile audit, or a cadence-driven or vulnerability-triggered sweep. Classifies each update on a risk ladder, verifies it, or defers it with a reason. Not for PR queue triage; use github-backlog-triage.

Use when starting UI work, defining palettes or design tokens, or fixing AI-generic, vibe-coded, or default-framework UI. Also handles TUI, CLI, and desktop surfaces when the runtime is named. Not for persisted design systems; use design-consultation. Not for live-URL audits; use web-design-review. No irreversible changes.

Use when the user invokes /duet, says pair on this, or faces aesthetic, architectural, or irreversible decisions. Surfaces every genuine fork as a user pick at the moment of decision so no review-bottleneck diff is produced. Not for one-shot fork resolution — use decide.

Use when asked to explore the codebase to map structure, symbols, and dependencies. Produces a structured orientation report with architecture, pattern, tooling, dependency, and critical-file sections.

Use when asked to generate a personal taste skill from local evidence. Produces a <name>-taste skill with 5 evidence-derived anchors and a two-sided charter. Not for applying an existing taste register: use spine. Local writes only.

Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms and a publish gate. Not for plain-git workflows in repos without branchless; the skill stays inert there. Human-only.

Use when a button click, dashboard check, or human verdict sits inside an iteration loop. Replaces it with an autonomous gate or moves non-automatable work outside the loop. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when a human asks to audit memory or find stale or duplicate memories. Also handles tidy''s ICM-state audit when the user says tidy and the target is stale memory entries. Not for writing new memories — use memory-update.

Use when the user asks to sanitize memory for sharing, redact PII, or scan memory for credentials. Scans for Tier-1 credentials first and stops before generating any copy if found; otherwise produces redacted copies with a diff for human review. Not for auditing memory — use memory-clean.

Use when the user explicitly says to save something to memory or scan this session for memories. Derives evidence-backed proposals, confirms each with the user, and writes validated memory files with read-back. Not for auditing memory — use memory-clean.

Use when work splits into independent sub-tasks or cross-domain research. Runs concurrent agents and returns one reviewed composition or an exact gap. Not for durable scope ownership with per-scope review — use partition-scopes-to-subagents.

Use when a user commits to a direction and asks to plan, brief, research, or operationalize it. Classifies type and tier, researches read-only, and writes to plans/ after acknowledgment. Not for scoring — use planning; not for codebase audit — use plan-review.

Use when researching a named library, framework, SDK, API, or service, or finding a migration guide. Produces a cited Markdown artifact written to disk with source-cited claims, confidence labels, and open questions. A primary-source-only mode restricts the ladder to official docs, API refs, and source code. Not for codebase-internal research — use scout.

Use when addressing review feedback or analyzing whether a comment is valid. Classifies each comment VALID ISSUE / NOT AN ISSUE / NEEDS CLARIFICATION with evidence and a recommended solution. Not for GitHub PR review threads — use resolve-pr-feedback.

Use when asked to review a pull request, examine code changes, find bugs, or audit a branch. Standard mode produces a severity-graded validated-findings report with concrete fixes; depth mode fans out parallel bug/security and quality reviewers and synthesizes a unified verdict. Not for an iterative review-and-fix loop — use audit-project.

Use when changes touch auth, input parsing, dependencies, network I/O, or pre-release of a public-facing service. Runs a STRIDE walk, OWASP Top 10 walkthrough, and supply-chain scan, and blocks merge on critical or high findings. Not for adding security controls during construction — use security-hardening; not for verifying one named finding — use security-finding-verification.

Use when the user says set up gitignore, fix gitignore, or untracked files keep appearing. Writes or merges .gitignore under stable section anchors and proves reruns produce no diff. Not for remote, credential, publish, deploy, or irreversible changes.

Use when installing or repairing one repository-local pre-commit hook using the project''s current gates, or when a repo needs package-manager-native commit-time checks. Extends existing hook tooling instead of duplicating it; JS uses Lefthook and Biome, Python/Rust/OCaml use prek. Not for remote or irreversible changes.

Use when the user says "simplify this diff" or asks for a compression pass over a change-set. Decomposes the diff into reuse, quality, and efficiency axes; applies validated findings as atomic issue-class commits; auto-reverts regressions. Not for dead-code sweeps — use deslop.

Use when a user invokes a strict-mode validation or verifiable-goals loop setup. Bootstraps strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Returns a per-anchor verdict table with ranked fixes in audit mode, or loads the judgment register in anchor mode. Don''t use for tasks that require source or remote-system changes.

Use when hardening error handling, validating boundary behavior, or hunting silent failures. Not for feature development — use tdd (offensive-first); not for test deletion — use tests-purge-unneeded; not for remote or irreversible changes.

Use when a legacy, slow, or duplicate test suite is being cleaned up, a post-refactor sweep is due, or the type system already covers an asserted contract. Not for tests superseded by a new harness — use test-migration-coverage-gate; not for untracked data or changes without VCS rollback.

Use when a completed session needs an agent-environment retrospective: a severity-ranked list of environment improvement candidates, each backed by session evidence. Not for an engineering retrospective from telemetry — use engineering-retrospective.

Use when the user asks to audit or repair agent surfaces — plugin configs, agent definitions, skills, CLAUDE.md/AGENTS.md, docs, prompts, commands, or hooks. Produces a certainty-graded breadth report and applies only HIGH auto-fixable findings with --apply. Not for deep one-skill improvement — use skill-improver.

Use when setting up a repo for agents, adding AGENTS.md, auditing CLAUDE.md, scoring instructions, or pruning long/stale files via a three-check gate. Also handles lean pointer-only AGENTS.md under 100 lines. Not for remote, credential, publish, deploy, or irreversible changes.

Use when loop scaffold files have drifted from their provenance-pinned templates. Converges exactly four auto-fixable files (STATE.md, gate.yaml, loop-budget.md, loop-run-log.md) to template content with pre-write backup and rollback, and reports other drift. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to create or refresh a personal mode skill and open a reviewable PR. Mines recent session history for a recurring manual workflow, drafts one self-contained skill file, and opens a PR with evidence. Not for shared repo skills or work that skips human approval.

Use when asked to audit an agent or AI feature for agentic-experience quality. Assesses target source or described behavior against Architecture and Agentic-experience rubrics, records findings with locators or logical bounds, and returns a severity-tiered report with a PASS/FAIL/INCOMPLETE verdict. Not for source or remote-system changes.

Use when the user names one book, course, paper, or source document and asks to distill it into a reusable skill. Classifies the source as procedure or reference, writes an attributed SKILL.md, and proves its routing. Not for a folder of sources — use map-corpus.

Use when prompt-doctrine is duplicated, drifted, or conflicting across output-style embeds and external harness AGENTS files. Strips duplicate directives from persona prefixes, repairs invariant-zone tail drift, classifies harness divergences, and records a divergence ledger before committing. Not for editing the canonical baseline itself.

Use when a human explicitly asks for a full repository agent-compatibility pass. Validates agent configuration surfaces, runs read-only startup and config loading, and returns a scored compatibility report with prioritized fixes. Not for tasks that require source or remote-system changes.

Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Inspects repository manifests to detect the tech stack and synthesizes a least-privilege command and domain allowlist that forbids state-modifying commands. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI — use control-cli.

Use when asked to create a local agent-plugin directory tree. Generates a valid scaffold with a host-specific manifest, entry point exporting the registration API, and standard directory layout, then validates the result. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to deduplicate skills or prompt directories, find repeated rules, or check a skill tree for contradictions. Produces a read-only ledger classifying every repetition cluster and conflict candidate with evidence and zero unclassified cells.

Use when someone outside Warp wants to wire a third-party coding agent (Claude Code, Codex, or Cursor) to a Warp Factory MCP endpoint. Provisions a 30-day bearer credential, writes a bearer-token MCP registration in the target harness, reloads it, and verifies protocol-level tool and resource discovery. Not for unattended runs; credential minting requires explicit human invocation.

Use when a repository needs a safety net against force-push, forced refspec, hard reset, forced clean, forced branch deletion, working-tree discard, stash drop/clear, reflog expire, or gc prune; installs a PreToolUse hook exiting 2 on them; plain git push allowed. Not for remote, credential, publish, deploy, or irreversible changes.

Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.

Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.

Use when the user asks to make the skills framework work in a new harness, IDE, or CLI; the run delivers a port whose bootstrap auto-injects every session and passes the captured acceptance transcript. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when the user wants to compile taste and "this feels wrong" signals into machine-consumable tokens, rules, forbidden combinations, and examples. Elicits concrete cases, classifies each into one of four buckets, and writes a structured rule/pattern document. Not for remote, credential, publish, deploy, or irreversible changes.

Use when onboarding to a repository, capturing costly conventions, constraints, or rationale, or improving AGENTS.md. Produce a grounded AGENTS.md containing only prescriptive, non-derivable rules. Don''t use for remote, credential, publish, deploy, or irreversible changes.