GitHub collection
outlinedriven/outline-driven-development
Imported from GitHub — is this yours?
145 skills imported from this repository.
abi-and-calling-conventions
Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.
abstract-well
Use when the user wants to classify abstractions as useful, bad, or busy and keep one shallow level. Not for tasks requiring source or remote-system changes.
adc-dac-baremetal
Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.
agent-environment-retrospective
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
agent-surface-forge
Use when asked to audit or repair agent surfaces (plugins, agents, skills, CLAUDE.md/AGENTS.md, docs, prompts, commands, hooks) or improve one skill at depth. Not for agent grading: use skill-doctor.
agent-transcript
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.
ai-collab-protocols
Use when the user describes an AI workflow gap or uses an ambiguous cross-session reference such as 'the PR Bob mentioned'. Not for tasks that require source or remote-system changes.
analysis-artifacts
Use when the user requests a deep dive, exploratory analysis, or data analysis on BigQuery. Not for credential, publish, deploy, or irreversible changes.
api-and-interface-design
Use when asked to design or change a public API, route, CLI flag, or module boundary. Not for remote, credential, publish, deploy, or irreversible changes.
articulate
Use when the user knows what they mean but cannot express it completely or clearly. Not for discovery, ideation, or style-only editing: use unslop for style.
artifact-arena
Use when asked to run /artifact-arena to generate and judge competing artifact implementations. Not for remote, credential, publish, deploy, or irreversible changes.
assembly-arm
Use when reading or writing AArch64 or AArch32 Thumb assembly, inline asm in C, AAPCS64 register roles, or NEON and SVE vector code. Not for ABI detail across ISAs: use abi-and-calling-conventions.
assembly-riscv
Use when reading or writing RV32/RV64 assembly, inline asm in C, the RISC-V psABI, IMAFD extension naming, compressed instructions, or QEMU RISC-V debugging.
assembly-x86
Use when reading GCC or Clang x86-64 assembly, writing inline asm, decoding AT&T syntax, or applying System V AMD64 register rules. Not for SIMD intrinsic selection: use simd-intrinsics.
atomic-issues-prs
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.
attack-shape
Use when the user wants adversarial stress-testing of a proposed architecture, structure, or shape. Not for tasks that require source or remote-system changes.
audit-loop-scaffold
Use when loop scaffold files have drifted from their provenance-pinned templates. Not for remote, credential, publish, deploy, or irreversible changes.
audit-project
Use when the user says "audit my code", "find all the bugs", "review until clean", or "grill my changes". Not for remote, credential, or irreversible changes.
automate-me
Use when asked to create or refresh a personal mode skill and open a reviewable PR. Not for shared repo skills or work that skips human approval.
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Not for implementing or deploying the system.
automatic-freeform-graphs-design
Use when a user wants a looser conceptual graph for exploratory work. Not for remote, credential, publish, deploy, or irreversible changes.
axiom-mode
Use when the user requests axiom, axiom-mode, axiom-compact, formal-logic, or compact form. Not for changing code or remote state.
baremetal-startup
Use when writing reset-to-main startup code, vector tables, VTOR, .data/.bss init, stack setup, startup.s, or crt0 for Cortex-M/RISC-V. Not for the bootloader jump: use bootloaders-embedded.
behavior-validator
Use when asked to validate a web app, CLI, API, or generated artifact against a source-blind behavior contract. Not for source or remote-system changes.
blast-radius
Use when asked to determine what a change could break before it ships. Not for remote, credential, publish, deploy, or irreversible changes.
book-to-skill
Use when the user names one book, course, paper, or source document and asks to distill it into a reusable skill. Not for a folder of sources: use map-corpus.
bootloaders-embedded
Use when writing a custom bootloader, jumping to application code, relocating VTOR, or implementing DFU/USB firmware update on Cortex-M. Not for reset-to-main: use baremetal-startup.
bounded-model-checking-c
Use when C or C++ code needs memory-safety or undefined-behavior guarantees proved with CBMC, or ACSL contracts checked with Frama-C Eva or WP. Not for choosing the proof policy: use proof-driven.
branch-prediction-and-speculation
Use when explaining branch predictors, mispredict penalties, speculative execution, Spectre or Meltdown mitigations, or branchless code. Not for pipeline stage theory: use cpu-pipelines-and-hazards.
brand-authority
Use when the user asks for branded or style-governed output. Not for remote, credential, publish, deploy, or irreversible changes.
breaking-driven
Use when bloated code needs clean re-derivation, or the user says "this module is bloated" or "break it and rebuild". Not for untracked data or changes without VCS rollback.
browser-cookie-store
Use when the user runs /browser-cookie-store to populate the session cookie store from installed browsers. Not for remote, credential, publish, deploy, or irreversible changes.
browser-qa
Use when the user runs /browser-qa for report-only QA results without entering a fix loop. Not for remote, credential, publish, deploy, or irreversible changes.
browser-testing
Use when building, debugging, or verifying browser-rendered code, or running browser tests for PR- or branch-affected pages. Not for source, remote-system, credential, publish, or deploy changes.
build-acceleration
Use when reducing C/C++ compilation times with ccache, sccache, distcc, unity builds, precompiled headers, split DWARF, IWYU, or link time reduction.
burpsuite-project-parser
Use when asked to analyze a Burp Suite .burp project for audit items, request/response metadata, or captured traffic. Modes: parsed (default) and stream. Not for source or remote-system changes.
buyer-objection-research
Use when product copy needs buyer-objection evidence collected through approved, consented outreach. Not for unsolicited outreach or survey design.
buzzword-analysis
Use when the user wants the current jargon weather of a domain described without advocacy. Not for choosing a positioning move: use buzzword-hijack.
buzzword-hijack
Use when a user wants to choose and execute a bounded positioning move that rides a jargon wave. Not for describing the jargon weather of a domain: use buzzword-analysis.
can-i-help
Use when the user asks "where to help", "contribution opportunities", or "find a good first issue". Returns data-backed first steps. Not for PR review queues: use gh-review-requests.
carbon-lang
Use when evaluating Carbon for a C++ code base, running the carbon toolchain from a nightly or Bazel build, or comparing Carbon with staying on C++. Not for C++ modules: use cpp-modules.
cargo-fuzz
Use when initializing, running, measuring coverage, or triaging a cargo-fuzz target in a Rust crate. Not for remote, credential, publish, deploy, or irreversible changes.
cargo-workflows
Use when managing Cargo workspaces, feature flags, build scripts, CI caching, dependency auditing, or Cargo.lock with Rust.
cascade-dedup
Use when prompt-doctrine is duplicated, drifted, or conflicting across output-style embeds and external harness AGENTS files. Not for editing the canonical baseline itself.
chain-vulnerability-scanner
Use when an Algorand, Cairo, Cosmos SDK, Solana, Substrate, or TON codebase needs vulnerability scanning with reachability-backed findings. Not for non-chain review: use security-review.
changelog-updates
Use when a release or a since-tag window needs user-facing release notes drafted. Not for publishing the release.
c-hardening-baseline
Use when C code is written or audited and needs a pure-C baseline: standard, undefined behavior, integer and buffer safety, sanitizers, fuzzing, build flags. Not for C++: use modern-cpp-practices.
check-agent-compatibility
Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes. Not for tasks that require source or remote-system changes.
cherrypick-to-release
Use when the user asks to cherry-pick, backport, or apply a hotfix to a release branch. Not for merging feature branches or cutting new release branches.
chrome-extension
Use when the user explicitly asks to build, modify, or publish a Manifest V3 Chrome extension. Not for store submission without human-gated credentials.
claude-settings-audit
Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential, publish, deploy, or irreversible changes.
clean-and-true
Use when the user just edited a durable artifact, or says "clean and true", "run the hygiene pass", or "taste the output". Routes the artifact through the hygiene passes it earned.
clean-clean-cut
Use when asked to run /clean-clean-cut to cut accumulated records and residue. Not for untracked or non-VCS changes, or branch/worktree cleanup: use git-cleanup.
cli-for-agents
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.
close-done
Use when the user wants to batch-close resolved or outdated tracker items. The agent never closes tracker items itself. Not for individual closure or items still under active work.
cloud-task-orchestrator
Use when a human explicitly runs /cloud-task-orchestrator for a large task across cloud agents to drain a verified task graph. Not for local subagent coordination: use orchestration-patterns.
code-generation-and-backends
Use when reading llc output, tracing IR through legalization and instruction selection, or scoping a new LLVM target. Not for IR-level passes: use llvm-ir-and-passes.
codeql-security-analysis
Use when building or reusing a CodeQL database, running CodeQL security analysis, or modeling project-specific sources and sinks. Not for manual vulnerability review: use security-review (mode: confirmed).
code-simplification
Use when the user asks to simplify, clean, or refine code. Not for new abstractions or whole-codebase refactors.
commit-push-current
Use when a human asks to commit and push, not publish, the checked-out branch, including directly to the default branch, with no branch creation and no pull request. Not for a feature branch off the default: use commit-push-pr in its no-PR mode.
commit-push-pr
Use when asked to commit and push a feature branch, with or without a pull request. Its no-PR mode publishes without a PR. Not for a PR body alone: use create-pull-request.
competitor-feature-research
Use when asked to research a feature across competitor products or to analyze competitor release changelogs (mode: changelog), and publish a cited report.
compile-3d-workflow
Use when the user asks for direction and a compilable 3D workflow from an interview. Not for remote, credential, publish, deploy, or irreversible changes.
compiler-frontend
Use when building a lexer, Pratt or recursive-descent parser, AST, symbol table, type checker, or LLVM IR emitter for a language or DSL. Not for optimizing IR: use llvm-passes.
compiler-optimizations-deep
Use when -O3 leaves a hot loop scalar, spills appear in assembly, or a PGO or BOLT deployment is planned or stalls. Not for machine lowering: use code-generation-and-backends.
complexity-grill
Use when a user wants to identify the true sources of complexity qualitatively before counting metrics. Not for source or remote mutation.
conan-vcpkg
Use when adding C/C++ dependencies with Conan or vcpkg, managing binary compatibility, integrating with CMake via conanfile.txt or vcpkg.json, or choosing between Conan and vcpkg.
concurrency-debugging
Use when reading TSan race reports, debugging deadlocks with GDB thread inspection, analyzing Helgrind lock-order violations, or reviewing std::atomic and happens-before usage.
constant-time-analysis
Use when reviewing cryptographic code for timing side-channels, statically in compiled output or at runtime with statistical timing tests. Not for known-answer vectors: use wycheproof.
constraint-driven-development
Use when asked to implement under non-negotiable constraints: performance budgets, platform limits, legal or API rules. Not for remote, credential, publish, deploy, or irreversible changes.
consult-deployment
Use when the user asks to rank deployment platforms and stacks against their product with quantitative trade-offs. Not for source or remote mutation.
containers-internals
Use when explaining or building on Linux container primitives: namespaces, cgroups v2, overlayfs, runc and the OCI spec, seccomp-bpf, capabilities, or escapes. Not for VM isolation: use qemu-kvm.
context-engineering
Use when a long session has accumulated stale or conflicting context or the user asks to refresh it. Not for remote, credential, publish, deploy, or irreversible changes.
continual-learning
Use when asked to mine prior chats on a scheduled or watcher tick and maintain project memory. Not for remote, credential, publish, deploy, or irreversible mutation.
contract-driven
Use when crossing a public API boundary, guarding complex invariants, or hardening untrusted input or integration seams. Not for remote or irreversible changes.
control-cli
Use when asked to reproduce, profile, or verify CLI/TUI behavior. Produces a deterministic transcript or profile proof with session cleanup. Not for CLI design advice, use cli-for-agents.
control-ui
Use when asked to verify or reproduce browser or Electron UI behavior with before-and-after evidence and no leftover processes. Not for remote, credential, publish, deploy, or irreversible changes.
copywriting
Use when asked to write or fix product/marketing copy, landing pages, UI strings, brand voice, AI tells, an end-of-article CTA, or a hook/lede. Not for whole articles: use technical-article-writer.
copywriting-tone-of-voice-creator
Use when asked to create, refresh, or port a brand tone of voice guide (TONE.md) or measurable prose style rules (PROSE.md). Not for general copywriting: use copywriting.
core-dumps
Use when loading core files in GDB or LLDB, enabling core dump generation via ulimit or coredumpctl, mapping symbols with debuginfod, or extracting backtraces from production segfaults.
corroborate-by-independent-reruns
Use when a candidate patch or answer needs independent corroboration before it is trusted. Not for multi-stance investigation: use council.
cost-reduction
Use when a measured cost surface needs one-change-at-a-time reduction under frozen guardrails. Not for speed-only optimization: use optimize.
cpp-coroutines
Use when working with C++20 co_await, co_yield, and co_return, implementing promise_type, sizing coroutine frames, or debugging suspended coroutines in GDB. Not for Rust async: use idiomatic-rust.
cpp-modules
Use when a C++ project adopts C++20 modules: named modules, partitions, header units, the global module fragment, CMake CXX_MODULES, or a BMI lookup error. Not for flag basics: use clang.
cpp-templates
Use when a C++ template error needs decoding, a template needs a concept or requires-clause instead of SFINAE, or template instantiation is slowing compilation. Not for C++20 modules: use cpp-modules.
cpu-cache-opt
Use when diagnosing cache misses with perf, fixing false sharing, choosing AoS or SoA layout, or adding software prefetch. Not for cache theory: use memory-hierarchy-and-caches.
cpu-kernel-authoring
Use when writing, optimizing, or benchmarking a C++ CPU kernel with AVX2 or AVX512 intrinsics for the Hugging Face kernels ecosystem. Not for CUDA kernels: use cuda.
cpu-pipelines-and-hazards
Use when explaining pipeline stages, data or control hazards, forwarding, stalls, or superscalar basics behind a counter reading. Not for mispredict cost: use branch-prediction-and-speculation.
create-branch
Use when the user asks to create a new branch or start work on one. Not for remote, credential, publish, deploy, or irreversible changes.
create-learning-path
Use when asked to create a multi-session learning plan. Returns a milestoned plan, practice, and review rubric. Don't use for tasks that require source or remote-system changes.
create-plugin-scaffold
Use when asked to create a local agent-plugin directory tree or marketplace package. Not for remote, credential, publish, deploy, or irreversible changes.
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
cross-critique
Use when independent proposals on a contested decision need cross-critique before choosing, reusing the original authors. Not for parallel multi-stance investigation: use council.
cross-lens-converge
Use when one reviewer is not enough because failure modes are heterogeneous, or a claim needs cross-lens pressure before it ships. Not for collapsing a decision field: use converge.
cross-run-playbook
Use when a long agentic project needs each cycle to end in a learning memo and a keep/iterate/restart decision. Not for single-pass builds.
crypto-protocol-diagram
Use when asked for a sequence diagram of cryptographic protocol semantics from code, prose, RFCs, papers, ProVerif, or Tamarin, or for code/spec divergence. Not for architecture: use diagramming-code.
c-security-review
Use when the user requests a userspace C or C++ security review with a threat model and severity filter and wants validated findings. Not for kernel or bare-metal code: use kernel-security.
cuda-debugging
Use when debugging CUDA with cuda-gdb or Compute Sanitizer, reading GPU core dumps, using device printf, or triaging error codes 700, 701, 702, and 719. Not for performance: use cuda-profiling.
cuda-profiling
Use when profiling CUDA with Nsight Systems or Nsight Compute, reading roofline and occupancy metrics, or annotating phases with NVTX. Not for correctness: use cuda-debugging.
culture-burnout-detection
Use when Survey and Job Culture Index profiles need analysis for stress, burnout, disengagement, or flight-risk signals. Not for clinical diagnosis: use a qualified clinician.
culture-conflict-mediation
Use when two colleagues' working friction needs trait-based explanation, accommodations, process changes, and escalation boundaries, or for manager-report friction. Not for performance adjudication.
culture-interview-debrief
Use when a Culture Index profile needs comparison with role requirements, team composition, and manager profile for hiring. Not for transcript prediction: use culture-interview-profile-prediction.
culture-interview-profile-prediction
Use when asked to predict Culture Index traits from an interview transcript before a survey exists, including sparse or contradictory evidence. Not for interpreting completed survey results.
culture-manager-coaching
Use when a manager needs profile-specific communication, one-on-one, motivation, and energy guidance for a direct report. Not for general pair or team compatibility analysis.
culture-onboarding-plan
Use when a signed new hire's Culture Index profile and team profiles need a first-90-days plan. Not for manager coaching: use culture-manager-coaching.
custom-allocators
Use when implementing pool/slab/arena allocators, tuning jemalloc/mimalloc/tcmalloc, writing a Rust GlobalAlloc, or benchmarking allocator performance and fragmentation.
customer-feedback-report
Use when customer feedback, NPS, churn, email feedback, call transcripts, or voice-of-the-customer analysis needs a report over a time window.
cut-new-release-candidate
Use when the user asks to cut, trigger, or start a release candidate for a release branch. Not for full releases, hotfixes, or non-release-candidate workflow dispatches.
cybernetic-loop
Use when the caller supplies a falsifiable out-of-happy-path invariant and a finite budget. Restores via bounded patches or reverts. Not for normal feature delivery or universal retries.
cycle-memo
Use when a build, QA pass, demo, user complaint, or abandoned attempt leaves the next pass needing lessons rather than code. Not for changelog extraction. Not for session handoff: use handoff.
dbt-model-index
Use when a human-curated dbt model index must guide BigQuery SQL for a warehouse question. Not for discovering undocumented models or executing warehouse changes.
debloat-respect-richness
Use when a user asks to tighten verbose-but-correct prose without a full rewrite. Cuts in place to load-bearing density, preserving every load-bearing claim.
debug-optimized-builds
Use when debugging RelWithDebInfo or -O2 release builds, using -Og for debuggable optimization, split-DWARF, GDB scheduler-locking, reading inlined frames, or understanding "value optimized out".
decision-diary
Use when a user wants to record why one world won over the others, as a decision-diary entry. Not for remote, credential, publish, deploy, or irreversible changes.
decision-rationale-gaps
Use when a current decision needs pressure-testing until the rationale is clear to a skeptic. Not for tasks requiring source or remote-system changes.
deductive-verification-with-dafny-and-why3
Use when an imperative program needs pre-conditions, post-conditions, and loop invariants proved automatically by SMT in Dafny or Why3, short of a tactic prover.
dedup-skills
Use when asked to deduplicate a skill tree, fold overlapping skills, or cut the skill count: analyze, gate per family, then fold. Not for prompt-doctrine cascades: use cascade-dedup.
deep-research
Use when the user asks to research a topic and produce a thorough sourced report. Not for remote, credential, publish, deploy, or irreversible changes.
define-goalstate
Use when the user wants the finished-system contract for a piece of work: behavior, protocols, allowed, forbidden, and impossible states with a state-space proof. Not for runtime verification.