Claude Skills by OutlineDriven

Use when the user wants to classify abstractions as useful, bad, or busy and keep one shallow level. Classifies each by whether its cooked form is easier than its raw form, and selects one shallow level. Don''t use for tasks that require source or remote-system changes.

Use when building or running native code under AddressSanitizer, or when interpreting an existing ASan report. Instruments C/C++ or Rust unsafe/FFI targets, sets ASAN_OPTIONS for fuzzer integration, and classifies each reported error with its faulting and allocation sites. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user needs to set up and run an AFL++ fuzzing campaign for a C/C++ target. Compiles with LTO, LLVM, or GCC instrumentation, runs single or multi-core campaigns, triages crashes, and minimizes the corpus. Requests explicit approval before system-level changes. Not for libFuzzer harness campaigns — use libfuzzer.

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 a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body with human approval and preview. Not for automated or model-initiated insertion without explicit human review.

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 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 user wants to enumerate plausible designs, configurations, scenarios, and paths and diagram the field before choosing. Produces an exhaustive enumerated field and a diagram before any choice. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when the user requests a deep dive, exploratory analysis, or data analysis on BigQuery. Produces a dated analyses dir with an approved plan, cohorts, linked SQL and visualization artifacts, and TLDR. Read-only BigQuery warehouse queries are within authority; not for credential, publish, deploy, or irreversible changes.

Use when asked to design or change a public API, route, CLI flag, or module boundary. It documents the contract with semantics and errors, then migrates every consumer so no legacy path remains. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when a completed agent run must be recorded as durable, queryable evidence. Appends one entry to the JSONL run log under an ISO date guard, prunes expired entries, and updates the last-run pointer. Don''t use for remote, credential, publish, deploy, or irreversible changes.

Use when non-trivial code needs designing before implementation, or an existing codebase needs its architecture improved: surveying for shallow modules, locating a seam, deepening a structure, hardening with guardrails, or making code testable. Also handles surveying for shallow modules, locating seams, deepening structures, hardening with guardrails, and making code testable. Not for architecture diagrams, deploy, remote, credential, or irreversible changes.

Use when the user asks to visualize an architecture as a self-contained HTML artifact with a hash-bound receipt. Also handles delta mode: comparing two snapshots, rendering what changed when both are supplied. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user knows what they mean but cannot express it completely or clearly. Turns a vague intended thought into a faithful, audience-ready statement, preserving scope and identity, surfacing unsupported choices, and inventing no goals or facts. Not for discovery, ideation, or style-only editing — use unslop for style.

Use when asked to run /artifact-arena to generate and judge competing artifact implementations. Produce one verified synthesis with provenance and rejection reasons. Don''t use for remote, credential, publish, deploy, or irreversible 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 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 a user needs coverage-guided fuzzing for Python code or a Python native extension using Atheris. Sets up an instrumented harness, configures sanitizer flags for native extensions, and reproduces saved crash artifacts. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don''t use for single-change pushes or uncommitted change-sets.

Use when a user wants adversarial stress-testing of a proposed architecture, structure, or shape. The agent attacks while the human defends, or the agent proposes while the human attacks, until the shape survives or breaks. Records the surviving shape as a decision. Not for tasks that require source or remote-system 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 the user says "audit my code", "find all the bugs", "review until clean", or "grill my changes". Runs an iterative multi-agent review that resolves every finding at or above a configurable severity floor to zero, or stops at a gate or cap. Not for remote, credential, or irreversible changes.

Use when a verified non-trivial fix lands. Automatically captures a durable learning doc to docs/solutions/ or a CONCEPTS.md entry, or determines nothing qualifies. Also handles refresh when solution docs may have drifted. Not for unverified fixes.

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 the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.

Use when a user wants a looser conceptual graph for exploratory work. Generates a freeform conceptual graph that the user can explore. Not for remote, credential, publish, deploy, or irreversible changes.

Use when a human has an approved delivery plan and wants the full chain run under phase gates. Delegates implementation to work, simplification to simplify, review to review, and finalization to review-and-ship. Not for planning, open-ended debugging, or single-step execution — use work directly.

Use when the user runs /autoplan on a plan or idea. Runs CEO, design, DX, and engineering review phases over the idea, amends the plan, derives deterministic task IDs into a task JSONL ledger, and waits at a final human approval gate. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user says release this, publish this package, or cut a release for a changesets-based npm package. Not for non-npm packages or releases without a changesets workflow.

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 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 asked to park an undecided idea without representing it as decided or active work. Creates or updates one reversible local backlog entry with evidence and a readiness threshold. Not for decided or active work — use the project task system.

Use when the user faces multi-fork decisions or unresolved prerequisites. Maps a decision tree and asks its frontier as batched single-select questions until shared understanding is confirmed. Also handles "batch questions". Not for one-at-a-time interviews — use interview-me.

Use when asked to validate a web app, CLI, API, or generated artifact against a source-blind behavior contract. Produces a structured pass/fail/blocked/out-of-scope report with anti-cheat probes and redacted evidence. Not for source or remote-system changes.

Use when asked to determine what a change could break before it ships. Returns confirmed risks, cleared items, and the cheapest pre-merge test that catches the real bug. Not for remote, credential, publish, deploy, or irreversible 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 the user begins knowledge work with notes, a transcript, a brain dump, or a problem. Captures original wording, reads prior knowledge, resolves up to three load-bearing questions, and writes a brainstorm file before planning. For divergent option generation, use ideate.

Use when the user asks for branded or style-governed output. Produces a deliverable that follows a fetched brand authority and states the material constraints that shaped it. Not for remote, credential, publish, deploy, or irreversible changes.

Use when bloated code needs clean re-derivation, or the user says "this module is bloated" or "break it and rebuild". Classifies old behavior as essential or residue, cuts residue, and leaves the verifier green. Not for untracked data or changes without VCS rollback.

Use when the user runs /browser-cookie-store to populate the session cookie store from installed browsers for authenticated browsing. Discovers browser profiles, reads and decrypts local cookie databases, extracts session cookies, and writes them to the destination store. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user runs /browser-qa to run the QA verification pass and return report-only results without entering a fix loop. Runs configured build, test, and lint checks in order, collects findings, and writes one local report. Not for remote, credential, publish, deploy, or irreversible changes.

Use when building, debugging, or verifying browser-rendered code, or when asked to run browser tests for pages affected by a PR or branch. Interactive mode drives an attached browser via Chrome DevTools MCP to inspect runtime state with console, network, accessibility, and performance evidence. Diff-scoped mode derives affected routes from a git diff, exercises each against the local dev server, and reports every route as Pass, Fail, or Skip. Not for source, remote-system, credential, publish...

Use when a multi-language program graph is needed for call paths, entrypoints, blast radius, coarse taint reachability, privilege boundaries, or declared cross-system links. Builds the full graph, runs preanalysis, and gates every version-specific query behind a capability probe with bounded security claims. Not for a quick overview; use trailmark-summary. Not for a fixed snapshot payload; use trailmark-structural.

Use when a human invokes the Burp search command with a required .burp project file and optional parser operation. Runs the Burp Suite project parser wrapper and returns JSON search results. Not for source or remote-system changes.

Use when asked to search or analyze a Burp Suite .burp project to extract audit items, inspect request or response metadata, or search captured traffic. Reads through Burp Suite Professional headless JAR, preflights result size, and returns size-checked JSON with truncated body fields. Findings are indicators requiring validation.

Use when product copy needs buyer-objection evidence collected through approved outreach. Conducts structured interviews via approved channels with consent, then synthesizes a copy recommendation grounded in anonymized exact language. Not for unsolicited outreach or survey design.

Use when the user wants the current jargon weather of a domain described without advocacy. Surveys circulating terms, their signaling freight, and their usage trajectory from verifiable external sources. Not for choosing a positioning move — use buzzword-hijack.

Use when a user wants to choose and execute a bounded positioning move that rides a jargon wave without confusing trend with truth. Produces a written positioning artifact at a named output path. Not for describing the jargon landscape.

Use when the user requests a userspace C or C++ security review with an explicit threat model, severity filter, and model. Runs a partitioned read-only audit and writes report, SARIF, and findings to a .c-review-results run directory. Not for kernel drivers, managed languages, or embedded code.