majiayu000
UserNative rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.
Categories
Indexed Skills (44)
awk-posix-compat
Shell 脚本中 awk 的 POSIX 兼容性指南。 Use when: 编写或审查包含 awk 的 shell 脚本， 尤其是需要 macOS + Linux 跨平台运行的场景。 触发词: awk, BSD awk, POSIX regex, [[:space:]], guard 脚本, 跨平台 shell
specrail-plan-tasks
Use when turning an approved SpecRail product and technical spec into the numbered `tasks.md` plan. Creates stable task IDs, owners, done-when conditions, verification commands, dependencies, and handoff notes without implementing the tasks.
specrail-pr-gate
Use before reporting a SpecRail PR as merge-ready. Collects read-only PR evidence, runs the offline PR gate, checks linked work, current head SHA, CI, review decision, review threads, merge state, and human merge authorization without merging.
specrail-review-pr
Use when performing an advisory SpecRail PR review. Checks linked issue/spec evidence, route gates, verification evidence, review-thread state, human-gate preservation, and implementation quality without granting final approval or merging.
specrail-triage-issue
Use when triaging a GitHub issue or issue-like request in a SpecRail-governed repository. Handles search-first duplicate checks, issue classification, readiness label proposals, security-private routing, and triage handoffs without bypassing human gates.
specrail-workflow
Use as the router/startup skill when working in a repository that adopts SpecRail for issue-first, spec-first, AI-assisted development. Routes triage, spec writing, task planning, implementation, PR review, CI diagnosis, PR gates, release notes, and spec-vs-implementation checks to focused SpecRail skills while preserving locale and human-gate boundaries.
specrail-write-product-spec
Use when writing or updating a SpecRail product spec for a linked issue. Produces the numbered `product.md` spec from the locale-appropriate template, focusing on user-facing behavior, goals, non-goals, and acceptance criteria without implementation detail.
specrail-write-tech-spec
Use when writing or updating a SpecRail technical spec for a linked issue. Produces the numbered `tech.md` spec from the locale-appropriate template, translating accepted product behavior into design, affected files, risks, verification, and rollback without starting implementation.
benchmark-regression-triage
Use this skill whenever VibeGuard hook latency, benchmark-action output, GitHub Actions bench-output artifacts, or a suspected performance regression needs investigation. It preserves the PR-to-CI-artifact workflow for comparing recent PRs, older anchors such as PR
vibeguard-observe
Use when the user asks for a VibeGuard dashboard, hook health, stats, doctor output, metrics export, or local observability status from the Codex App plugin.
agentsmd-audit
Audit AGENTS.md / CLAUDE.md against the five high-leverage patterns (progressive disclosure, procedural workflows, decision tables, production code examples, domain rules with concrete alternatives). Reports per-pattern coverage, anti-patterns, and a prioritized fix list.
eval-harness
Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.
implx
Use when the user says "implx", "use implx", "用 implx", or asks for the one-line SpecRail queue shortcut. Plain implx means drain the full actionable issue/PR queue in review mode: run SpecRail preflight, create missing spec/task PR work before implementation, use threads for reviewer/merge-reviewer lanes when available, create per-issue implementation PRs, require CI/reviewThreads/pr_gate evidence, preserve per-PR human merge authorization, and perform closure audit. Say "implx auto" / "implx 自动" for the explicit auto mode that treats the invocation as standing merge authorization for this run.
iterative-retrieval
Iterative retrieval — 4-stage loop (DISPATCH→EVALUATE→REFINE→LOOP) to pinpoint relevant information in the code base. Up to 3 rounds.
specrail-implement-queue
Use when implementing or draining a GitHub issue/PR queue in a SpecRail-governed repository where approved specs already exist, such as multiple numbered docs/specs/GH packets that need one or more implementation PRs per issue. Maps issues to specs and existing PRs, supports full-queue drain requests from implx, selects single-agent or optional threads orchestration, preserves partial versus final closing semantics, and requires SpecRail verification plus PR gates before merge-readiness claims.
specrail-install
Use when installing, updating, verifying, or adopting SpecRail for agents. Guides local Codex skill installation, global AGENTS.md guidance setup, repository adoption planning, dry-run-first verification, and explicit human authorization boundaries.
strategic-compact
Strategic compression — Manual compression of contexts at logical boundaries rather than arbitrary automatic compression. Key decisions and constraints are preserved and intermediate exploration is discarded.
trajectory-review
Post-hoc diagnosis of a failed agent trajectory. Classifies the first unrecoverable step into one of nine failure categories (plan adherence, hallucinated information, invalid tool call, misread tool output, intent–plan mismatch, under-specified intent, unsupported intent, guardrail trigger, system failure) and produces an evidence-backed root-cause report.
auto-optimize
Automate analysis, evaluation, design and optimization of target projects. Integrate VibeGuard as a baseline scan, the remediation process adheres to VibeGuard specifications, and a compliance check is run at the end. Support auto-run-agent autonomous execution.
fixflow
Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.
optflow
Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).
plan-flow
Analyze repository-level duplicate/redundant design first, then build and execute a strict step-test-update plan in docs/plan. Use for deep architecture review, convergence planning, and traceable one-step-at-a-time delivery.
plan-mode
Use when the user asks to enter Plan mode, says /prompts:plan or /plan, or wants a structured execution plan written to plan/.
specrail-check-impl-against-spec
Use when comparing a SpecRail implementation, diff, or PR against its linked issue, product spec, technical spec, and task plan. Reports acceptance coverage, mismatches, omitted tasks, extra scope, and verification gaps without approving or merging.
specrail-diagnose-ci
Use when diagnosing or fixing CI failures in a SpecRail-governed repository. Collects fresh CI evidence, reproduces failures locally when possible, identifies root cause before fixing, and reports verification without claiming green CI from stale or missing data.
specrail-implement
Use when implementing a SpecRail-governed issue after the implementation gate. Executes the scoped task plan, keeps changes tied to linked specs and acceptance criteria, runs deterministic verification, and preserves human approval, merge, and security boundaries.
specrail-release-note
Use when drafting a SpecRail release note after a linked PR has merged. Summarizes user-visible changes, verification, linked issues, risks, and rollout notes while preserving release and security human gates.
loom-registry
Manage the local Loom Skill registry and CLI safely. Use for registry status, Skill lifecycle, targets, bindings, projections, activation, sync, operation history, rollback, or diagnostics. Do not use for Loom.com video recording, sharing, editing, or transcription.
vibeguard
Use when the user asks Codex to apply VibeGuard anti-hallucination rules, inspect VibeGuard observability, or route a task through VibeGuard preflight/review/check workflows.
vibeguard-setup
Use when the user asks to install, verify, inspect, or remove VibeGuard Codex hooks through the Codex App plugin.
remem-first-run-smoke
Validate remem first-run behavior from an isolated HOME and REMEM_DATA_DIR. Use when changing install, doctor, status, encrypt, hook activation, Codex/Claude setup, plugin activation, or user-facing onboarding documentation.
remem-plugin-version-sync
Keep remem binary, Cargo, Codex plugin, release manifest, and npm wrapper versions synchronized. Use when changing package.version, release metadata, plugin runtime behavior, npm wrapper behavior, or when CI/check_plugin_version_sync.py or check_version_bump.py fails.
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
specrail-workflow
Use as the router/startup skill when working in a repository that adopts SpecRail for issue-first, spec-first, AI-assisted development. Routes triage, spec writing, task planning, implementation, PR review, CI diagnosis, PR gates, release notes, and spec-vs-implementation checks to focused SpecRail skills while preserving locale and human-gate boundaries.
specrail-check-impl-against-spec
Use when comparing a SpecRail implementation, diff, or PR against its linked issue, product spec, technical spec, and task plan. Reports acceptance coverage, mismatches, omitted tasks, extra scope, and verification gaps without approving or merging.
specrail-diagnose-ci
Use when diagnosing or fixing CI failures in a SpecRail-governed repository. Collects fresh CI evidence, reproduces failures locally when possible, identifies root cause before fixing, and reports verification without claiming green CI from stale or missing data.
specrail-implement
Use when implementing a SpecRail-governed issue after the implementation gate. Executes the scoped task plan, keeps changes tied to linked specs and acceptance criteria, runs deterministic verification, and preserves human approval, merge, and security boundaries.
specrail-plan-tasks
Use when turning an approved SpecRail product and technical spec into the numbered `tasks.md` plan. Creates stable task IDs, owners, done-when conditions, verification commands, dependencies, and handoff notes without implementing the tasks.
specrail-pr-gate
Use before reporting a SpecRail PR as merge-ready. Collects read-only PR evidence, runs the offline PR gate, checks linked work, current head SHA, CI, review decision, review threads, merge state, and human merge authorization without merging.
specrail-release-note
Use when drafting a SpecRail release note after a linked PR has merged. Summarizes user-visible changes, verification, linked issues, risks, and rollout notes while preserving release and security human gates.
specrail-review-pr
Use when performing an advisory SpecRail PR review. Checks linked issue/spec evidence, route gates, verification evidence, review-thread state, human-gate preservation, and implementation quality without granting final approval or merging.
specrail-triage-issue
Use when triaging a GitHub issue or issue-like request in a SpecRail-governed repository. Handles search-first duplicate checks, issue classification, readiness label proposals, security-private routing, and triage handoffs without bypassing human gates.
specrail-write-product-spec
Use when writing or updating a SpecRail product spec for a linked issue. Produces the numbered `product.md` spec from the locale-appropriate template, focusing on user-facing behavior, goals, non-goals, and acceptance criteria without implementation detail.
specrail-write-tech-spec
Use when writing or updating a SpecRail technical spec for a linked issue. Produces the numbered `tech.md` spec from the locale-appropriate template, translating accepted product behavior into design, affected files, risks, verification, and rollback without starting implementation.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.