exerias21

@exerias21 source repo

18 skills
0 followers
7 hours ago last updated

▌
Sdlc 2 · exerias21
Run the full SDLC pipeline on a plan file, task id, task range (e.g. "1-5"), or an ad-hoc description: sanity-check -> implement -> evals -> fix -> validate -> flowsim, then hand off the validated changes for you to commit. No commit, no branch, no push, no PR. Codex overlay of the canonical skill -- every stage runs inline (sequential, no parallel sub-agents). Use /task instead for a single small TDD fix with no plan.

0
installs
▌
Sdlc 3 · exerias21
Run the full SDLC pipeline on a plan file, task id, task range (e.g. "1-5"), or an ad-hoc description: sanity-check -> implement -> evals -> fix -> validate -> flowsim, then hand off the validated changes for you to commit. No commit, no branch, no push, no PR. Copilot overlay of the canonical skill -- every stage runs inline (no parallel sub-agents, no Plan mode). Use /task instead for a single small TDD fix with no plan.

0
installs
▌
Brainstorm 2 · exerias21
Interactive brainstorming and feature ideation skill. Guides the user through structured creative exploration: asking focused clarifying questions when the seed is ambiguous, exploring codebase context, generating multiple approaches, evaluating tradeoffs, and producing a concrete action plan. Use this skill whenever the user says /brainstorm, mentions "brainstorm", "let's think through", "I have an idea", "what if we", "how should we approach", "let's explore", or otherwise wants to ideate on a feature, improvement, or architectural change before jumping into code. This is the conversational planning companion — for heavy autonomous multi-agent product research, use /brainstorm-team (Claude Code only).

0
installs
▌
Brainstorm Team 2 · exerias21
Sequential product-strategy brainstorm for Copilot. Walk through five research passes (competitive landscape → codebase map → UX critique → ranked features → implementation blueprints) inline, producing a single strategy document. Use for "what should we build next", "competitive analysis", or product review sessions. Copilot-adapted version of the canonical — sequential instead of 5 parallel workers.

0
installs
▌
Dead Code Review 2 · exerias21
Sequential dead-code review for Copilot. Walk through six focused review phases (backend, frontend, database, docs, scripts, tests) inline, then triage findings and remove high-confidence items with test verification. Use /dead-code-review after a major feature, before a release, or when asked to "clean up" the repo, "what can be deleted", "what's no longer needed", or "what docs are worth keeping vs getting rid of". Copilot-adapted version of the canonical — sequential instead of parallel.

0
installs
▌
Sdlc · exerias21 bundle
Run the full SDLC pipeline on a plan file, task id, task range (e.g. "1-5"), or an ad-hoc description: sanity-check → implement → evals → fix → validate → flowsim, then hand off the validated changes in your working tree for you to commit. Never commits, branches, pushes, or opens a PR — no git writes at all. Use when you want full SDLC discipline on work you will review and commit yourself, e.g. onto an open PR's branch. Use /task instead for a single small TDD fix with no plan.

0
installs
▌
Task · exerias21
Create a bounded, single-purpose task and execute it with TDD. Appends a row to TASKS.md, writes a task file at plans/tasks/task-N-<slug>.md, and runs a write-test → implement → verify loop. Use for small to medium items that are too concrete for /brainstorm and too small to justify the full /sdlc pipeline. Invoke via /task or when the user asks to "just do X" with a clear, bounded ask.

0
installs
▌
Gotcha · exerias21
Maintains a running log of project-specific "gotchas" — non-obvious pitfalls, traps, and hard-won lessons that have caused bugs or wasted time in this codebase. Use this skill proactively whenever writing or modifying code in any area where a prior gotcha has been recorded. Also use when the user invokes /gotcha to add a new entry or review existing ones. Consult the project's GOTCHAS.md before writing code in any area where a known pitfall exists.

0
installs
▌
Flowsim · exerias21
Trace the claimed flow from a plan or task through the source code and report mismatches. This is a structured code-review pass formatted as a narrative execution trace — the goal is to surface "the plan said X but the code does Y" gaps that test suites and evals miss. Use during the /sdlc fix loop, after implementing a feature, or ad hoc when a plan and its implementation feel misaligned. Invoke via /flowsim or when the user says "trace the flow", "verify the plan matches", "walk through what actually happens".

0
installs
▌
Code Tour · exerias21 bundle
Turn an existing codebase into teaching material: audit docstring coverage, write why-focused docstrings that explain the reasoning behind each design decision, and generate a guided reading path (TOUR.md) with a pattern index and graded exercises. Use this whenever someone wants to document a codebase for humans rather than for an API reference — onboarding a new hire, handing a repo to another team, preparing a repo as a training or teaching module, "explain this codebase", "add docstrings", "write documentation for all the code", or after /repo-onboarding when the architecture is mapped but the code itself is undocumented. Distinct from its neighbours: /repo-onboarding generates the toolkit's contract files and /repo-health is a read-only sweep — this one writes documentation into the source, "help someone learn this repo", or when /code-tour, /docstrings, /codetour, or /onboarding-docs is invoked. Also use it when documentation exists but only says WHAT the code does and the user wants the WHY captured be

0
installs
▌
Plan HTML · exerias21 bundle
Render a markdown plan file as a self-contained, shareable HTML page. Zero external assets (no CDN, no JS framework), embedded CSS with light/dark mode, anchored TOC at top, every section open by default, and auto-generated inline-SVG visuals (effort×impact map, phase flow) when the plan's structure warrants — no flag, data-driven. Composes with any plan — brainstorm output, SDLC plans, refactor docs, threat models. Use when you want to share a plan with a stakeholder, scroll-engage with a long plan in a browser, or hand off a roadmap. Output is throwaway: the .md remains canonical.

0
installs
▌
Brainstorm · exerias21 bundle
Interactive brainstorming and feature ideation skill. Guides the user through structured creative exploration: clarifying the idea, exploring codebase context, generating multiple approaches, evaluating tradeoffs, and writing a concrete action plan to `plans/`. Asks focused clarifying questions first whenever the seed is ambiguous, and stops to ask rather than guess when a plan-shaping unknown surfaces later. Use this skill whenever the user says /brainstorm, mentions "brainstorm", "let's think through", "I have an idea", "what if we", "how should we approach", "let's explore", or otherwise wants to ideate on a feature, improvement, or architectural change before jumping into code. This is the conversational planning companion — for heavy autonomous multi-agent product research, use /brainstorm-team instead.

0
installs
▌
Test Check · exerias21
Run all relevant tests, feature evals and log audits after code changes. Reads `.claude/project.json` for project-specific commands. Gracefully skips any steps whose commands are not configured. Use after implementing features, fixing bugs, or before marking work done.

0
installs
▌
Repo Health · exerias21
Read-only repo hygiene sweep. Runs dead-code, tests, dependency audit, secret scan, and gotchas-currency in parallel; rolls findings into a single scored report. Use this when the user says /repo-health, asks for a "hygiene check", "weekly sweep", "is this repo healthy", "what should I clean up", or before a release. Read-only — produces a report and a `.next-action` suggestion, never modifies code. Run it after merges land, not mid-implementation — a sweep is noisy while you're actively changing things. For a deep dead-code investigation use /dead-code-review; for PR-scoped review use /sdlc's Stage 5. Also flags migration drift (migration files newer than the recorded applied version), stale pipeline run-state, and stale memory pointers.

0
installs
▌
Sdlc Status · exerias21
Show a quick readout of the current work queue: task counts by state, the active task, and the most recently completed task. Also surfaces any non-terminal pipeline runs (so a stalled /sdlc run can't hide). Reads TASKS.md and .claude/pipeline/ directly — no subagents, no dashboards. Invoke via /sdlc-status or when the user asks "what's left?", "current task?", "status". Read-only by default; `--prune-stale` is an opt-in, confirm-gated cleanup of stale/orphaned pipeline envelopes.

0
installs
▌
Brainstorm Team · exerias21
Launches a coordinated multi-agent team (5 agents in parallel) to produce a complete product strategy document: competitive research, codebase mapping, UX critique, ranked feature list, and detailed implementation blueprints. Use when the user wants heavy autonomous product research or says "brainstorm team", "what should we build next", "competitive analysis", "product review", or invokes /brainstorm-team. For conversational ideation with the user in-session, use /brainstorm instead.

0
installs
▌
Repo Onboarding · exerias21
Inspect a repository and generate the cross-tool contract files this toolkit's skills rely on: `AGENTS.md` (architecture + agent instructions), `TASKS.md` (work queue), `.claude/project.json` (runner config), and `GOTCHAS.md` (pitfalls). Use when onboarding a new repo to the workflow toolkit, or when /onboard, /discovery, /codelearn, or /init-toolkit is invoked. Replaces the separate /codelearn skill — architecture discovery is part of onboarding here.

0
installs
▌
Dead Code Review · exerias21 bundle
Launches a parallel fan-out of review agents (tiered by load, Sonnet-first — capped per project.json models.cap / --model) to find dead code, dead docs, and dead plans, then removes them and runs the test suite before and after to verify zero regressions. THIS IS THE SKILL FOR "launch a few agents to review everything for dead code / anything no longer needed" — use it instead of hand-composing an ad-hoc agent fan-out. Scans whatever surfaces the repo actually has — server code, client code, data/migrations, documentation, scripts — for unused imports, dead functions, orphaned components, stale plans, and redundant migrations. Use when the user says /dead-code-review, "what can be deleted", "what's no longer needed", "what docs are worth keeping vs getting rid of", "clean this up", "look for dead code", or asks to sweep the repo after a feature lands, a refactor, or before a release.

0
installs

18 published skills