mwguerra/plugins-haiku/deep-work

Claude Code and agent skill by mwguerra/plugins-haiku

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Run a large, multi-place task as a checkpointed state machine over the runs store — plan, adversarial plan review, wave-by-wave execution, synthesis — one step per invocation, resumable after any interruption. Trigger: cross-file refactor, data migration, large feature build, multi-source research — work that cannot finish in one pass. Manual invocation: /deep-work.

Install

npx vskill@latest install mwguerra/plugins-haiku/deep-work

SKILL.md

deep-work — a state machine over run-state

A deep-work run is rows, not memory: a runs row plus one run_steps row per step in .taskmanager/taskmanager.db, with one brief file per step at .taskmanager/runs/<run-id>/step-<seq>-<name>.md. The window holds nothing; resume, crash recovery, and post-compaction pickup are all the same query. Store spec: docs/architecture/runtime-state.md (schema v5, v_next_step, checkpoint rules).

Entry conditions (counted, not felt)

Run deep-work when ANY row fires; no row fired → /implement handles it directly.

CountableThreshold
files the task will touch (glob/grep its nouns)> 5
estimated LOC (sum of per-file estimates)> 200
acceptance criteria on the ask> 4
distinct top-level dirs touched> 2

An audit / production-readiness ask is not deep-work — run deep-analysis.

The step machine

run_steps.namePhase file (load ONE, execute, checkpoint)
planreferences/phase-1-plan.md
adversarial-reviewreferences/phase-2-adversarial-review.md
execute-<k>references/phase-3-execute-wave.md
synthesizereferences/phase-4-synthesize.md

The plan step inserts the execute-<k> and synthesize rows and writes every brief; execution order is run_steps.seq, served by v_next_step.

Invariant rules (always in force)

  1. One step per invocation. Read the step's phase file and its brief; execute;

checkpoint; only then query v_next_step again. Never read ahead to other steps; never load two phase files at once.

  1. Every step opens with the re-orientation preamble (fixed text in each phase

file): the brief is the complete truth; read ONLY what its attention contract names; files win over memory.

  1. Checkpoint order: artifacts to disk → the step's run_steps row

(status, artifacts_json, notes) → runs.current_step. The DB may lag disk, never lead it.

  1. A failed step halts the run — v_next_step returns no row for it, by

construction. Never silently retry in the same window; a step retried ×2 across windows escalates per docs/architecture/escalation-ladder.md row 8.

  1. Parallelism is decided at plan time by the wave table in phase-1 — counted

from the subtasks' file lists, never from a feel for "large enough".

  1. The board lives in the store. Step notes go in run_steps.notes; anything

larger is a disk artifact listed in artifacts_json. No thoughts/ directory (retired — see skills/thoughts/SKILL.md).

Preflight

No .taskmanager/ → run taskmanager:init first. runs table absent (schema < v5) → stop and name the migration per docs/architecture/runtime-state.md (migrate-v4.2-to-v5.sh); never emulate the store with files.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mwguerra/plugins-haiku/deep-work/badge)](https://verified-skill.com/skills/mwguerra/plugins-haiku/deep-work)

Something wrong with this skill or its page? Tell us.