Claude Skills by jscraik

Purpose: sidecar for the requested he-eval-report review infographic. Repository image path: `.harness/media/2026-05-10-he-eval-report-codex-harness-skill.png`. Source generated-image cache path: `~/.codex/generated_images/019e1236-9dbc-7bb1-a32e-332f9d8c9cea/ig_06b22062ce4dc1f9016a00d21db120819195e98ea8f5d4e05d.png`. Prompt metadata path: `.harness/media/2026-05-10-he-eval-report-codex-harness-skill-prompt.md` Sidecar path: `.harness/media/2026-05-10-he-eval-report-codex-harness-skill.md` Li...

Create or refactor AGENTS.md and linked instruction docs using progressive disclosure. Use when the user wants repo-specific agent guidance organized, deduplicated, or routed cleanly, not ordinary product documentation edits.

Create, install, validate, and orchestrate Codex custom subagents as standalone TOMLs with canonical global defaults (`~/dev/configs/codex/agents/{name}/{name}.toml`, `~/dev/configs/codex/config.toml`) plus optional project scope (`${project_root}/.codex/agents/{name}/{name}.toml`), where project config writes occur only when runtime-limit flags are explicitly requested.

Analyze broad frontend design requests and route them to the correct local UI skill after classifying intent and maturity. Use when the user asks for frontend design generally and the specific design owner is not yet clear.

WHAT: Generate Codex-authored HTML insights from local Codex sessions and telemetry. WHEN: Use when the user asks for Codex usage analytics, workflow patterns, session summaries, prompting help, or recommendations for improving how they use Codex.

Review and triage file-based `todos/` findings into ready, skipped, or revised states before execution. Use this skill when the repo already uses the file-based todo workflow and the user wants approval-style triage, not tracker triage or todo execution.

Use when you need focused cleanup audits, safe removals, scoped quality-risk reductions, and evidence-backed cleanup plans before touching code.

Build or adapt Oak Curriculum API learning experiences, especially child-facing Apps SDK flows. Use when the user wants Oak endpoints or curriculum data turned into guided learning interactions with age-appropriate guardrails.

Create and maintain an LLM-managed markdown wiki that incrementally compiles source material into a persistent, queryable knowledge base; use this skill when users ask for persistent wiki architecture, ingest/query/lint workflows, or schema governance.

Draft and validate release notes, changelog entries, and GitHub release-history summaries from commits, PRs, issues, or tags; use before package publishing or when a PR needs a Release notes section.

Generate self-contained HTML explainers for systems, diffs, plans, or data with clearer visual presentation than plain text. Use when the user wants a diagram or visual technical explainer, or when a large ASCII table would be hard to scan.

Design or implement production-ready frontend UI components and screens with strong visual direction, layout rhythm, spacing hierarchy, accessibility, and reusable structure. Use when the user wants standard UI build or redesign work, including fixing crowded or structurally weak layouts, not design-system governance or post-direction polish only.

Generate brand-aligned Open Graph images for existing routes by inspecting a web codebase and rendering assets with Playwright components. Use when a user asks for route-specific OG image generation or refresh in an existing app.

Route ambiguous Harness Engineering requests to one lifecycle stage when users ask where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain terminology.

Use this skill to analyze underspecified requests through a short interview and surface missing tradeoffs, assumptions, and approval gates before implementation when a prompt is underdefined and guessing would be risky.

Scan Codex session history for skill failures, usage patterns, and coverage gaps. Use when the user wants daily skill-health monitoring or evidence-backed recommendations about installing, improving, merging, or pruning skills.

Capture a completed Codex workflow as a reusable SKILL.md package by analyzing session context plus optional session-collector evidence, interviewing the user with structured prompts, and writing a validated skill artifact. Use when the user asks to skillify or operationalize a repeatable process.

Review PRs, branches, diffs, and workflow artifacts for package-level go/no-go readiness with severity-ranked synthesis. Use when users need readiness synthesis rather than detailed technical-risk critique.

Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness. Use when the work involves new services, significant service changes, multiple external dependencies, or high blast-radius failure scenarios.

Review diffs, PRs, specs, plans, or review-feedback items and return severity-ranked engineering findings with exact locations. Use when technical risks or feedback correctness must be verified before implementation.

Define problem scope, requirements, and decision options before spec or plan stages. Use when the user has ambiguity in what to build, why it matters, or which direction to choose.

Analyze and validate compound Harness Engineering run state, blockers, validation status, and Linear context. Use when lifecycle runs drift, gates fail, blockers appear, or compound work needs refresh.

Run a bounded Harness Engineering lifecycle across multiple stages. Use when the user wants coordinated brainstorm, spec, plan, work, review, and fix flow rather than one isolated stage.

Deepen an existing implementation plan so sequencing, verification, and risk treatment are strong enough for execution. Use when the user wants Harness Engineering plan hardening before he-work.

Deepen an existing system or UI spec so boundaries, lifecycle rules, failure handling, and validation are strong enough for planning. Use when the user wants Harness Engineering spec hardening or a requirements review pass before planning.

Restore broken behavior by reproducing failures, identifying root cause, and delivering verified fixes. Use when the user needs regression debugging, incident triage, or bug repair from tracker or direct reports.

Create, review, or repair recurring Harness Engineering heartbeats that wake a thread, re-check live state, and route back into the right HE stage; use when PRs, CI, reviews, deploys, validation ladders, or compound runs need recurring follow-up until done, blocked, or cancelled.

Generate and compare grounded product or engineering directions with tradeoffs. Use when users want possibilities, critique, or direction-setting before a spec.

Improve existing Harness Engineering implementations or workflows with evidence-backed changes. Use when users ask for targeted enhancement of shipped or drafted work.

Plan execution work from specs, brainstorm outputs, bugs, or feature requests into an implementation-ready sequence. Use when the user needs the Harness Engineering planning stage before execution.

Review and prune stale branches safely. Use when branch cleanup needs evidence, protected-branch caution, PR awareness, and non-destructive recommendations.

Write Harness Engineering specs before planning. Use when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract.

Build behavior-safe code changes with TDD and RED/GREEN evidence. Use when he-plan or he-work requires TDD for a concrete behavior target.

Implement approved Harness Engineering work. Use when a plan, todo list, or tiny spec needs traceable delivery and validation.

Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans. Use when users ask for tightening, simplification, or lifecycle repair.

Generate closure-grade HE eval and drift proof for one execution slice. Use when Linear, milestone, or source-prompt closure needs validation evidence.

Convert approved HE cognition into small live-ready Linear execution tracking. Use when strategy, reframe, plan, bug, or source-prompt evidence needs scoped issue, milestone, or project routing with explicit confirmation before any live mutation.

Routes old phase-heartbeat requests into HE phase work: check the approved plan, reuse or create a 10-minute he-heartbeat only with authority, run phase gates, delegate the active slice to he-work, and stop before commit or tracker closure. Use when a user says phase heartbeat, keep this PR moving, or continue phases.

Runs approved Harness Engineering plans in recurring phases: check live state, wake with he-heartbeat, execute only the active he-work slice, verify gates, update Linear only with approval, and stop before unsafe staging or closure. Use when a plan, issue, or PR needs continued phase-by-phase execution.

Analyze repo, tracker, PR, validation, session, and .harness evidence. Use when multi-stage Harness Engineering work needs safe resume routing.

Create evidence-backed HE reframe migration programs. Use when structural drift, routing ambiguity, or source-prompt gaps need phased rollback-safe execution.

Create or refresh evidence-bound Harness Engineering learning artifacts from verified solved problems. Use when a fix worked, a repeated failure should become durable knowledge, or .harness/solutions and Project Brain need maintenance.

Selects one Harness Engineering stage for mixed requests. Use when a request could mean brainstorm, spec, plan, work, review, eval, Linear planning, reconcile, reinforce, heartbeat, branch hygiene, or specialist steering.

Compress HE cognition artifacts into evidence-backed strategy. Use when intent, review, triage, ADR, core, or source-prompt comparison evidence needs durable direction.

Harden and validate Codex plugin packages with contract-grade checks before install or release. Use when the deliverable is a plugin package that needs conversion or hardening.

Install validated Codex plugins from trusted sources with quarantine validation, provenance, and rollback. Use when distribution and installation are the primary goals.

Scaffold Codex plugin packages with deterministic manifests, marketplace metadata, and traceability or evidence contracts for non-trivial adoption. Use when creating plugin roots or adopting existing skills into plugin ownership.

Analyze broad, mixed, or unclear Plugin Factory follow-up requests and select the correct plugin lane. Use when plugin intent lacks a clear lane owner.

Route plugin-factory requests to the right lane. Use when plugin creation, building, installation, review, or routing is broad, mixed, or under-specified.

Analyze and harden Codex skills and plugin packages for contract quality, eval coverage, and safety compliance. Use this skill when an existing package is approaching release and needs evidence-backed validation.