bowen31337

@bowen31337 source repo

17 skills
0 followers
6 hours ago last updated

▌
Long Running Agent · bowen31337 bundle
Build autonomous, long-running AI agents that parse PRDs/specifications into structured task lists and execute them autonomously with state persistence, error recovery, and cross-session resumption. Works with any agent framework (Cursor, OpenCode, etc.).

0
installs
▌
Bug Report Processor · bowen31337 bundle
Processes bug reports from markdown files exported from any ticket system (Linear, GitHub Issues, Bugzilla, etc.), extracts reproduction steps, error logs, and environment details. Manages debugging workflow through Detective Methodology including reproduction, investigation, root cause analysis, fix verification, and regression testing. Use when handling bug reports, debugging issues, or tracking bug resolution.

0
installs
▌
Debt Tracker · bowen31337
Technical debt tracker so agents can log known shortcuts, compromises, or TODOs into docs/exec-plans/debt.md with a severity level and clear remediation notes. Debt items are auto-assigned sequential DEBT-NNN IDs, and the summary table is rebuilt on every write. Use when: (1) identifying a shortcut or workaround taken during implementation, (2) logging a TODO that cannot be addressed in the current plan, (3) noting a security, reliability, or maintainability concern for later remediation, (4) resolving a previously logged debt item with a description of what was done, (5) printing a current debt summary to check overall health, (6) reviewing which items are open or already resolved, (7) triaging debt by severity before a release or sprint planning session. Triggers on: log debt, technical debt, record debt, track debt, known shortcut, TODO tracker, debt item, debt entry, remediation, debt summary, DEBT-NNN, open debt, resolve debt, mark resolved, severity high, severity critical, debt tracker, shortcuts taken

1
install
▌
Dom Snapshot · bowen31337 bundle
Browser-free DOM inspection for agents. Fetches or parses server-rendered HTML and returns a compact, structured text snapshot covering headings, ARIA landmarks, navigation, forms, interactive buttons, tables, images, and visible body text — sized to fit comfortably in an LLM context window. Use when: (1) understanding a page's structure before deciding the next action, (2) checking whether a form, heading, or link is present after a navigation event, (3) verifying UI state in a test harness without spinning up Playwright or Selenium, (4) parsing raw HTML retrieved by a previous step. Triggers on: inspect page, DOM snapshot, page structure, check form, check heading, check link, UI state, parse HTML, page metadata, navigation links, accessible landmarks.

1
install
▌
Progress Log · bowen31337
Append-only agent progress log for tracking step completion within a plan. Agents call this skill to record timestamped entries as they start, finish, fail, or skip individual steps in an execution plan. All entries accumulate in docs/exec-plans/progress.md as a Markdown table — safe for concurrent writes from multiple agents. Use when: (1) starting work on a plan step, (2) marking a step done with a completion note, (3) recording a step failure with error detail, (4) skipping a step that is not applicable, (5) reviewing what steps have been completed so far, (6) generating a per-plan done/total progress summary, (7) coordinating progress visibility across parallel agents. Triggers on: log progress, append progress, mark step done, record step started, step failed, step skipped, progress entry, progress log, plan progress, track step, update progress, what steps are done, show progress, progress summary.

1
install
▌
Shared State · bowen31337
Shared agent state publisher and query tool. Agents publish intermediate results (discovered endpoints, schema changes, test results, or arbitrary structured data) into docs/exec-plans/shared-state.yaml so other concurrently-running agents can read them. All writes are protected by an advisory file lock for safe concurrent access. Use when: (1) an agent has discovered API endpoints that other agents need, (2) an agent has applied schema changes that downstream agents should know about, (3) an agent has run tests and wants to share pass/fail counts or coverage data, (4) any agent wants to leave structured breadcrumbs for agents that run later, (5) querying what intermediate state has already been published before starting a task. Triggers on: publish result, share intermediate result, discovered endpoints, schema changes, test results, shared state, agent breadcrumbs, inter-agent communication, query shared state.

1
install
▌
Env Isolation · bowen31337
Generates environment isolation configuration artefacts for per-worktree agent isolation. Produces .env files, docker-compose service overrides, and shell export scripts that assign each worktree its own port, PostgreSQL schema, SQLite database file, or container — without launching any process. Use when: (1) setting up environment variables for an isolated worktree before starting the app, (2) generating a .env file to commit alongside the worktree, (3) creating docker-compose overrides for per-agent containers, (4) scripting CI environments where each job needs its own isolated service, (5) auto-assigning a collision-free port from a pool. Triggers on: generate env config, environment isolation, worktree isolation, per-worktree env, dotenv generation, docker-compose override, port assignment, database schema isolation, isolate worktree.

1
install
▌
Harness Resume · bowen31337 bundle
Load and present the most recent plan state for agent context handoff. Reads .claude/plan-progress.md (primary) or .plan_progress.jsonl (fallback) and formats the structured plan state — task, status, accomplished work, in-progress items, next steps, and search hints — so a new agent session can orient itself immediately. Search hints are presented as actionable pointers (file paths, grep patterns, key symbols) that the resuming agent verifies with its own Read/Grep/Glob tools. Use when: (1) starting a new session that continues previous agent work, (2) quickly checking what the current plan state is, (3) injecting saved plan state into an agent system prompt via the SDK, (4) bridging sessions after a context window limit or session restart, (5) presenting a handoff summary before a new agent begins. Triggers on: harness resume, load plan state, what was I working on, resume previous session, show plan progress, continue from last session, where did I leave off, read handoff, present context handoff.

1
install
▌
Error Aggregation · bowen31337 bundle
Error aggregation view for agents. Groups recent harness error events by domain and frequency so agents can query the error landscape without parsing raw logs. Pre-computes deduplication, trend detection (rising/falling/stable), and JSON-serialisable summaries. Use when: (1) diagnosing which component is failing most often, (2) investigating a spike in a specific domain, (3) checking whether an error rate is rising or recovering, (4) providing a structured error briefing before a remediation agent runs, (5) summarising errors across a multi-agent pipeline. Triggers on: show me recent errors, what errors are happening, error summary, query errors by domain, which domain is failing, error aggregation, rising errors, error frequency.

1
install
▌
Logging Convention · bowen31337 bundle
Generates a versioned SPEC.md (or SPEC.json) logging convention document specifying the five required fields every log entry must carry: timestamp, level, domain, trace_id, message. Validates existing NDJSON log files against the convention. Use when bootstrapping a new service that needs a structured logging standard, generating a canonical SPEC.md, or producing a machine-readable JSON Schema for cross-language log validation. Triggers on: logging convention, log spec, log entry fields, structured logging, trace_id, NDJSON, log schema, observability contract, generate SPEC.md, logging standard.

1
install
▌
Concurrency Patterns · bowen31337
Scans the codebase for async/await patterns, thread-safety mechanisms, and pool usage, then generates framework-specific concurrency rules and code snippets matched to the detected conventions. Detects: anyio, asyncio (stdlib), threading, concurrent.futures, aiohttp, httpx. Flags anti-patterns: blocking calls (time.sleep, requests.get) inside async functions, missing in-memory locks for shared mutable state, bare thread spawns without join, deprecated asyncio.get_event_loop(). Generates ready-to-paste code snippets for: anyio TaskGroup, asyncio.TaskGroup, asyncio.Lock / anyio.Lock, ThreadPoolExecutor with correct sizing, run_sync / run_in_executor for bridging sync code, fcntl.LOCK_EX for cross-process file safety. Use when: (1) starting work in an async codebase and need to know the team's conventions, (2) reviewing a PR that adds concurrency primitives, (3) a linter or code-review agent needs concrete async/thread-safety rules, (4) debugging a suspected race condition or blocking-in-async bug, (5) on-boardi

1
install
▌
Golden Principles Cleanup · bowen31337
Background cleanup task generator for principle violations. Reads .claude/principles.yaml, scans the codebase for violations using the harness principles gate (or text-based fallback), and emits one cleanup task definition per violation cluster into docs/exec-plans/cleanup-tasks.yaml. Each task carries enough context (scope, description, pr_title, pr_body) for an agent to open a focused refactoring PR without any further analysis. Use when: (1) principles have just been added or updated and you want to enforce them across the existing codebase, (2) planning a cleanup sprint and need a structured backlog of refactoring PRs, (3) running post-harness-evaluate cleanup to track principle violations as actionable tasks, (4) generating background work items that can be dispatched to worker agents. Triggers on: generate cleanup tasks, enforce principles, principle violations, refactoring PR backlog, cleanup sprint, background tasks, post-evaluate cleanup.

1
install
▌
Boot · bowen31337
Per-worktree boot script generator and instance launcher. Generates a self-contained bash script that starts an isolated application instance on a dedicated port, optionally isolates the database (PostgreSQL schema, SQLite file, or container), and polls a health endpoint until the instance is ready. Also supports booting the instance directly from Python without writing a script to disk. Use when: (1) starting an app server for an agent worktree so it doesn't collide with other concurrent agents, (2) generating a reproducible boot script to store alongside the worktree, (3) verifying an instance is healthy before running tests, (4) setting up database isolation per task, (5) scripting multi-agent environments where each agent needs its own running service. Triggers on: boot instance, start isolated server, per-worktree boot, generate boot script, health check, isolate database, launch app for agent, worktree isolation.

1
install
▌
Detect Env Vars · bowen31337
Codebase analysis skill that detects environment variable patterns from .env.example / .env.sample template files, YAML/TOML/JSON/INI config files that use ${VAR} interpolation, and source code references (os.environ, os.getenv, process.env, os.Getenv, ENV[]) across Python, JavaScript, TypeScript, Go, Ruby, and Shell. Produces a structured, de-duplicated inventory of every environment variable the project depends on. Use when: (1) onboarding to a new project and need to know what env vars to set, (2) auditing which services / files read a given variable, (3) generating .env documentation, (4) validating that .env.example is complete against actual code usage. Triggers on: env var, environment variable, .env.example, process.env, os.environ, os.getenv, config variables, secret inventory, required environment, dotenv.

1
install
▌
Perf Hooks · bowen31337 bundle
Performance measurement hooks so agents can record and query response times, memory usage (RSS), and startup duration. All measurements are appended to an agent-shared Markdown audit log (docs/exec-plans/perf.md). Timer state survives process boundaries via a JSON sidecar file, so start and stop calls can come from different shells or agents. Use when: (1) measuring wall-clock elapsed time for any labelled operation (LLM call, index build, embedding batch, etc.), (2) sampling current process resident-set-size at a specific point, (3) recording agent cold-start / initialisation duration, (4) querying or printing aggregate statistics (min / max / mean / p95) for a metric, (5) comparing performance across agents or across plan runs, (6) diagnosing latency regressions between iterations, (7) profiling memory growth through a pipeline. Triggers on: measure response time, time this operation, start timer, stop timer, record elapsed, sample memory, memory usage, RSS, startup duration, cold start, perf hooks, perform

1
install
▌
Harness Screenshot · bowen31337 bundle
Screenshot capture skill for recording application state as a visual artifact. Captures browser pages, desktop windows, or terminal output and saves them as timestamped PNG files (or base64-encoded inline artifacts). Use when: (1) documenting the visual state of a running web application, (2) capturing a UI before/after a code change, (3) recording terminal or CLI output as an image, (4) producing evidence artifacts for a bug report or test run, (5) snapshotting intermediate UI states during an automated agent workflow, (6) comparing layouts across breakpoints or themes. Triggers on: take a screenshot, capture the screen, screenshot the app, record the UI, capture application state, visual snapshot, screenshot artifact, capture browser, capture window, harness screenshot.

1
install
▌
Harness CLI · bowen31337 bundle
Drive the `harness` Python CLI — the agent-harness-skills toolkit that generates per-project harness configs, runs quality gates, manages execution plans, boots isolated app instances, and emits structured telemetry. Use whenever the user (or another agent) asks to scaffold/refresh harness artifacts, gate a worktree's code against architecture or principles rules, plan or resume a multi-step task, boot an isolated server for an agent worktree, capture screenshots or logs, search the symbol index, or chain any of the above into one invocation with `--then`. Triggers on: harness create, harness lint, harness evaluate, harness plan, harness resume, harness status, harness boot, harness observe, harness screenshot, harness search, harness coordinate, harness audit, harness manifest, harness telemetry, harness completion-report, harness context, harness update, run a harness command, agent harness, agent-harness-skills, quality gate, exec plan, worktree boot, --then pipeline.

1
install

17 published skills