harness-forge

Auto-discoverable wrapper for `.hforge/library/skills/bug-investigation/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/double-diamond-feature/SKILL.md`.

Use for defects, regressions, outages, flaky tests, and unexpected behavior. Guides the agent through triage, containment, reproduction, hypotheses, root-cause evidence, fix verification, and recurrence prevention. Do not use as the primary workflow for new features; use double-diamond-feature instead.

Use for meaningful feature development before coding. Guides the agent through Discover, Define, Develop, and Deliver with evidence, options, validation, and rollback notes. Do not use for bugs, regressions, outages, or flaky tests; use bug-investigation instead.

Auto-discoverable wrapper for `.hforge/library/skills/complex-task-protocol/SKILL.md`.

Automatic operating protocol for complex agent tasks. Use when work is multi-step, risky, cross-module, orchestration-heavy, or likely to benefit from bounded sidecar help, verification discipline, recovery checkpoints, and durable learning capture.

Auto-discoverable wrapper for the Harness Forge recursive-investigate workflow. Use when a task is ambiguous, cross-module, investigation-heavy, or likely to benefit from Typed RLM, bounded subcalls, and durable recursive artifacts.

recursive investigation orchestration using harness forge. use when the task is hard, ambiguous, cross-module, or likely to benefit from Typed RLM, bounded subcalls, durable iterations, and replayable recursive artifacts instead of chat-only reasoning.

Discovery wrapper for the canonical Lua engineering skill.

Discovery wrapper for the canonical Perl engineering skill.

Discovery wrapper for the canonical PHP engineering skill.

Discovery wrapper for the canonical PowerShell engineering skill.

Discovery wrapper for the canonical Python engineering skill.

Discovery wrapper for the canonical Shell engineering skill.

Discovery wrapper for the canonical TypeScript engineering skill.

auto-discoverable wrapper for `.hforge/library/skills/impact-analysis/SKILL.md`.

universal change impact analysis for software, infrastructure, data, api, schema, configuration, ui, security, and operational work. use when evaluating a proposed or implemented change, diff, migration, dependency upgrade, rollout, hotfix, refactor, incident remediation, or architectural decision to determine what is affected, how much is affected, how risky the change is, which direct and indirect dependencies may break, which evidence supports the assessment, and what validation, rollout, and rollback plan is required.

auto-discoverable wrapper for `.hforge/library/skills/madr-decision-log/SKILL.md`.

lua engineering guidance seeded from the harness forge knowledge base. use when the repo or task is dominated by .lua files, neovim plugins, openresty, love2d, embedded scripting, luajit, or host-specific lua automation where runtime compatibility matters.

create, review, normalize, validate, and maintain markdown architectural decision records using madr conventions. use when a repository needs durable adr files, a repeatable docs/decisions workflow, adr indexing, status updates, supersession handling, or file-based quality checks around decision records.

typescript and javascript engineering guidance seeded from the harness forge knowledge base. use when the repo or task is dominated by .ts, .tsx, package.json, tsconfig, node.js services, react, next.js, frontend tooling, or multi-package workspaces where type boundaries matter.

Auto-discoverable wrapper for `.hforge/library/skills/token-budget-optimizer/SKILL.md`.

compact context, reuse existing runtime artifacts, and choose the smallest authoritative surface before expanding prompt history. use when the task is growing large, when earlier repo intelligence already exists, or when repeated rescans would waste tokens without adding new evidence.

Auto-discoverable wrapper for `.hforge/library/skills/recursive-structured-analysis/SKILL.md`.

session-scoped recursive structured analysis for difficult repository investigation. use when recursive work needs a bounded capability map, explicit execution posture, and durable run records instead of free-form chat exploration.

architecture and implementation orchestrator for cross-cutting engineering work. use when a task needs system design, code architecture, refactoring strategy, implementation planning, specialist-skill routing, or explicit project-memory and change-discipline guidance in one surface.

Auto-discoverable wrapper for `.hforge/library/skills/api-contract-review/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/architecture-decision-records/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/cloud-architect/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/db-migration-review/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/documentation-lookup/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/javascript-engineering/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/parallel-worktree-supervisor/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/release-readiness/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/repo-modernization/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/repo-onboarding/SKILL.md`.

Auto-discoverable wrapper for `.hforge/library/skills/security-scan/SKILL.md`.

review request, response, event, and schema contracts for compatibility and consumer safety. use when http, openapi, asyncapi, protobuf, json schema, generated clients, or external integration behavior changes.

create and maintain high-signal adrs for architecture, package, runtime, workflow, and operational decisions. use when a decision should stay reviewable after the current session or when multiple credible options need a durable rationale.

review database migrations for safety, compatibility windows, backfills, reversibility, and rollout risk. use when migration files, schema diffs, orm model changes, indexes, constraints, or data backfills change.