joshuadavidthomas

Dude, come on. You write at the density of your own thinking and leave the reader to unpack it. Apply whenever explaining anything to a human — not just end-of-run summaries, every message.

Use when creating or iterating staged planning artifacts for a complex feature: design discussion, structure outline, final executor plan, or supporting research/research questions. Also use when designing before coding, breaking work into vertical slices, or deepening a high-value roadmap item, NNN improve plan, architecture candidate, or HumanLayer-style task.

Use when turning a roadmap, repo priorities, architecture priorities, chosen opportunities, accepted feature outlines/plans, or “roadmap to plans” request into grouped improvement plan batches for future executors. Writes README.md indexes, 001-*.md/NNN-style plans, optional memo-*.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes.

Use when a user asks “what should I work on in this repo?”, “what’s worth doing next?”, repo audit, tech-debt priorities, architecture priorities, old-plan reconciliation, or repo-grounded opportunity discovery. Produces .agents/ROADMAP.md with generated opportunities, user-seeded ideas, Now/Next/Later sequencing, rejected/not-now items, and next-artifact recommendations. Not for standard product/release roadmaps; if multiple repos are requested, create one roadmap per repo.

Use when reviewing code quality, asking whether a refactor or design is good, looking for code smells, or evaluating architecture tradeoffs. Identifies shallow interfaces, invalid state models, unclear boundaries, hidden effects, weak failure contracts, over-mocking, over-abstraction, compatibility glue, and clean-looking code that preserves bad models.

Build evidence-backed software/product roadmaps from repo state, tickets, ideas, audit findings, or user goals — prioritize and sequence work across Now/Next/Later, milestones, dependencies, risks, and handoffs. Use when asked for a roadmap, feature roadmap, technical roadmap, release plan, milestone plan, backlog prioritization, sequencing, what to build next, or to turn improve/ideate/brainstorm/design-discussion outputs into an execution sequence. Not for implementing code or writing PR-level plans.

Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.

Write self-contained implementation plan files that a fresh, possibly weaker executor can run without the author's context — splitting work into PR-sized plans, with verification gates, STOP conditions, and a memo protocol for design forks. Use when asked to write/create a plan, turn a decided design or ticket into plans, or when another skill hands off plan-writing. Not for deciding what to build or executing plans.

Maintain the ported ty resolver test corpus in crates/djls-project/tests/resolve.rs. Use when bumping the ruff git pin in the workspace Cargo.toml or when adding/reviewing module-resolution tests.

Use when editing Django template parser tags, validation errors, diagnostics, environment scanning, inspector data, Python environment inventory, or DJLS domain model code. Handles project-specific semantic and parser conventions.

Use when adding release notes, changelog entries, user-facing changes, internal changelog notes, or preparing a PR/release for django-language-server. Handles Keep a Changelog formatting and entry style.

Use when editing djls-extraction or Rust code that consumes Ruff Python AST APIs, including parse_module, parameters, boxed expressions, f-strings, or exception handlers. Handles known Ruff AST shape gotchas in django-language-server.

Use when editing Salsa inputs, tracked functions, database traits, setters, SemanticDb, crate::Db, invalidation behavior, or incremental computation in django-language-server. Handles project-specific Salsa conventions and required impl updates.

Use when running tests, fixing failing tests, updating snapshots, syncing corpus data, validating before push, or working with Django matrix testing in django-language-server. Handles cargo, just, nox, insta, corpus, clippy, fmt, and lint commands.

Use when adding or editing crates, Cargo.toml files, workspace dependencies, crate manifests, lints, versions, or project structure in django-language-server. Handles Rust workspace layout, dependency grouping, and new crate setup.

Provides git workflow assistance, branch management, and commit message optimization

A test skill to verify all plugin tools work correctly - use_skill, read_skill_file, run_skill_script, find_skills

Manage agent skill dependencies with dotagents. Use when asked to "add a skill", "install skills", "remove a skill", "update skills", "dotagents init", "agents.toml", "agents.lock", "sync skills", "list skills", "set up dotagents", "configure trust", "add MCP server", "add hook", "wildcard skills", "user scope", or any dotagents-related task.

Jujutsu (jj) — the Git-compatible version control system. Activate ONLY when a .jj/ directory is present in the project or when jj/jujutsu is explicitly mentioned. Do NOT activate for plain git repos without .jj/. Use for any VCS operations in jj-managed projects: commit, push, pull, branch, bookmark, rebase, squash, merge, diff, log, status, working copy, change ID, revset, fileset, template, configuration, workspaces.

Use when adding, editing, or reviewing reviewer scout lenses in this agentkit repo — creates review lenses, wires them into REVIEW_LENSES, updates /review help/tool docs/README, and validates reviewer behavior. Handles requests like "add a new lens", "write a reviewer lens", "make a reviewer lens", or "update reviewer personas".

Use when diagnosing CodSpeed benchmark regressions, profiling with valgrind-codspeed/callgrind, comparing instruction counts between branches, or reading callgrind_annotate output. Also use when a CodSpeed PR check shows performance regression and you need to find the cause. Covers: just profile, callgrind Ir/Dr/Dw counts, flat vs tree annotation, branch comparison methodology.

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings