A workflow operating system for AI-assisted engineering. Task state, decisions, and plans live on disk as files, not in chat history, so context survives across sessions, tools, and restarts.
This repository also configures its own agents. See what fhorja.dev tells them →
Skill Claude Code
Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity…
Skill Claude Code
Triage a concrete observed technical failure (stack trace, error, failing test, runtime symptom, production alert), classify the failure type (REGRESSION/NEWBUG/CONFIG/EXTERNALDEPENDENCY/REPRODUCIBILITY/DIAGNOSTICINSUFFICIENT), recommend fix size (HOTFIX/SLICE/INVESTIGATION/ESCALATE), and validate against locked…
Skill Claude Code
Identify the invariants, non-goals, and forbidden changes for the active task, then persist them as INVARIANTSANDNONGOALS.md so implementation boundaries are locked before planning or coding. Use when impact analysis is done or mostly clear, the task may touch sensitive behavior or contracts or schema or runtime…
Skill Claude Code
Snapshot the upstream Figma component library into docs/research/inventory/figmacomponents.md. For each Figma component: name, inferred tier, node ID, and whether a spec/code/story exists in the WOS-UI surface. Produces delta vs previous snapshot. Use after design ships a Figma library update or to seed the inventory…
Skill Claude Code
Document a user journey from screen references and a user story input. Produces a journey spec doc matching the JOURNEYSPEC.md template with outcome, screen flow, components consumed, critical states, accessibility, security, and performance sections. Use when mapping a user flow across multiple screens. Do not use…
Skill Claude Code
Senior product researcher running Jobs-to-be-Done switch interviews (Christensen / Moesta lineage) to surface the four forces of adoption (push, pull, anxiety, habit) and the trigger -> struggle -> switch timeline. Replaces internal motivation assumptions with verbatim user evidence. Activates when SOURCEOFTRUTH.md or…
Skill Claude Code
Read-only safety inspection of a third-party MCP server BEFORE it is added to a config or trusted. Reads the server's declared tool descriptions, input schemas, scopes, transport, and env/secret surface (not just its README), compares declared behavior against what the tools actually expose, scans for tool-description…
Skill Claude Code
Senior database migration safety steward auditing DDL (ALTER TABLE, CREATE INDEX, DROP COLUMN, ALTER TYPE, ADD CONSTRAINT, trigger changes, FK adds, RENAME COLUMN) for production-unsafe patterns BEFORE the migration is applied. Activates when IMPLEMENTATIONPLAN.md slices include schema changes, when TASKSTATE.md ##…
Skill Claude Code
Document a reusable UX pattern (empty state, error handling, confirmation dialog, search-filter-sort, loading skeleton) that applies across multiple screens and projects. Produces a pattern spec doc matching the PATTERNSPEC.md template. Use when formalizing a recurring UX solution. Do not use when documenting a single…
Skill Claude Code
Senior performance-budget auditor that declares the numeric non-functional budgets a change must hold (Core Web Vitals, backend latency percentiles, payload and bundle size, key-operation cost) and the action when a metric regresses. Produces PERFORMANCEBUDGET.md, a per-metric table of threshold, percentile…
Skill Claude Code
Read-only cross-task board across every active task in all projects. Runs scripts/portfolio-review.sh to classify each active task as done-unclosed, blocked, my-move, stale, or in-flight, then renders one ranked board with a single recommended next action per row, so picking the next thread and catching…
Skill Claude Code
Senior reliability engineer producing a per-slice post-deploy verification plan mapping each acceptance criterion to a concrete live signal (exact log query, dashboard panel, smoke-test walkthrough, flag check, DB invariant query) plus negative checks and rollback trigger checklist. Activates when TASKSTATE.md ##…
Skill Claude Code
Capture what a PR or team review changed about the intended behavior or approach, separate keep vs revert/replace, and produce the smallest safe set of updates to task memory and follow-on work. Does not implement product code. Use when a PR or team feedback requests a meaningful direction change (wrong fields, wrong…
Skill Claude Code
Senior reliability engineer authoring a blameless postmortem for a resolved incident: a timeline, contributing causes (not blame), impact measured against the SLO and error budget, and concrete action items with owners. Produces POSTMORTEM.md. Activates when incident-triage resolved an ESCALATE or a significant HOTFIX…
Skill Claude Code
Turn PR feedback (Greptile, CI, bots, humans) into a structured traceable backlog aligned with TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md so the next execution step can be a narrow implement-approved-slice or a small planning touch without losing alignment. Corrective scope only. Use when a PR is open or…
Skill Claude Code
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
Skill Claude Code
Run a short socratic intake that questions whether the stated problem is the right problem BEFORE a task exists, then write a task-level BRIEF.md (problem statement, success criteria, non-goals, recommended approach from 2-3 considered, named deliverables) that task-init consumes. Asks one question at a time, prefers…
Skill Claude Code
Initialize a new project context inside the task repository before any task exists. Creates projects/ /, PROJECTCHARTER.md, REFERENCES.md skeleton, and active/ plus archive/ subfolders so subsequent task-init runs have grounded project-level memory to consume. Use when starting a brand-new project, product…
Skill Claude Code
Shape the best possible prompt for the current task and workflow phase. Aligns the prompt content with the intended editor mode and the chosen command's required inputs, producing a copy-paste-ready handoff. Use when prompt precision would materially improve the next workflow action, the next step is known but the…
Skill Claude Code
Design a pre-deploy release and rollout strategy for a change: pick the rollout pattern (feature flag, canary, blue-green, or full progressive delivery) by risk and infra, then specify the exposure ramp, the promotion metric and threshold that advances each step, and the rollback trigger and mechanism. Produces…
Skill Claude Code needs its repo
Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability…
Skill Claude Code
Turn unresolved or contradictory behavior, contract, or policy gaps into one canonical implementation-safe decision set, then persist the result in DECISIONS.md and TASKSTATE.md as explicit reviewable proposals (not silent intent changes). Use when key ambiguities have already been identified, the task has enough…
Skill Claude Code
Resume the task from TASKSTATE.md and linked task artifacts, reconstruct the current truth, and determine the best next step. Used to bring back full task context after a session break or chat switch. Use when work is resuming in a new chat or session, the task was paused and needs fast reconstruction, or the user…
Skill Claude Code
Review the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Surfaces meaningful issues (not cosmetic feedback); not a replacement for external review systems. Returns no-op when the review would not materially…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: