AGENT SKILL

task-slicing

Wire a work breakdown into the tracker — depends_on edges, frontier, expand–contract for wide refactors. Use when filling plan.md's Steps section (routed from plan-gate), decomposing an epic into child tasks, or carving a mid-execute remainder into successor tasks.

适用职业律师与法务
License 许可
MIT
所属仓库
muratovv/ai-hats
最近更新
2026-11-05
Stars
★ 3
Forks
1

01 前言 Front Matter

name
task-slicing
license
MIT
description
Wire a work breakdown into the tracker — depends_on edges, frontier, expand–contract for wide refactors. Use when filling plan.md's Steps section (routed from plan-gate), decomposing an epic into child tasks, or carving a mid-execute remainder into successor tasks.

03 SKILL.md 正文

Task Slicing

Slices are tracer bullets — each a narrow but complete path to a verifiable result, sized to one session. This skill carries what that looks like in this tracker, and the one sequence that must not be sliced naively.

When to Use

  • Owns the Steps section of plan.md — plan-gate routes here.
  • NOT the test-writing rule: "vertical slicing" in trait-se-mindset governs one-test-at-a-time TDD; this skill slices work into tasks.
  • Mid-execute remainder ("tail doesn't fit the context"): context-reset step 3 carries it out via ## Steps items + plan-extract.

Wiring the breakdown

  • Declare blocking edges. Each child task names its blockers via depends_on (rack transition <ID> --link depends:<DEP>); a task whose blockers are all done is on the frontier — takeable in parallel without coordination.
  • Gate before publishing. Show the supervisor the breakdown — title, blockers, what it delivers; granularity, edges, merge/split answered — then publish via rack plan-extract (skill hatrack).

Wide refactors: expand–contract

One mechanical change whose blast radius fans across the codebase (rename, retype, package split) can't land as one green tracer bullet. Sequence it:

  1. Expand — add the new form beside the old; nothing breaks.
  2. Migrate — convert call sites in batches sized by blast radius (per package / directory), one child task per batch, blocked by the expand, CI green batch to batch.
  3. Contract — delete the old form when no caller remains; blocked by every migrate batch.

Batches that can't stay green alone share an integration branch plus a final integrate-and-verify task — green is promised only there. (Retrofitted after review; the failure mode was a 470-line, 88-importer move made mid-execute.)

Completion

Steps section holds one-session slices with edges declared; any wide refactor is sequenced expand–contract.

04 同仓库更多 Skills

muratovv
muratovv/ai-hats

tool-evaluation-protocol

Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML/LLM frameworks, testing approaches), or following up on a hype-driven recommendation.

★ 3
muratovv
muratovv/ai-hats

systematic-debugging

4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.

★ 3
muratovv
muratovv/ai-hats

skill-template

Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

skill-optimization

Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.

Skill与智能体开发
★ 3
muratovv
muratovv/ai-hats

silent-fallback-gate

PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.

★ 3
muratovv
muratovv/ai-hats

retro-to-framework

Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.

Skill与智能体开发
★ 3