AGENT SKILL

deniz-process.writing-plans

Use when you have a spec or requirements for multi-session work, or several people's worth, before touching code — not for a change that fits one sitting

License 许可
MIT
最近更新
2026-11-13
Stars
★ 1
Forks
0

01 前言 Front Matter

name
deniz-process.writing-plans
description
Use when you have a spec or requirements for multi-session work, or several people's worth, before touching code — not for a change that fits one sitting

03 SKILL.md 正文

Writing Plans

Overview

Write implementation plans for an engineer who has not seen this codebase or this spec. Assume they write idiomatic code in the project's language once they know the exact interface and the exact test, and that they will make a reasonable choice wherever the plan leaves one open. What they cannot know is what you decided: which files, which names and signatures, which values from the spec, which tests prove each task. Document those. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Size before ceremony

Some work arrives already sized: the user explicitly asks for a written plan (typing this skill's invocation counts). Write the plan; do not size that work again. Otherwise, size the work before creating an artifact. Work that brainstorming hands over with an approved design doc is sized here too, with that doc as its input: a change that fits one sitting skips the plan and is built from the doc on the ordinary path, unless the request was design-only; then stop after the design. Multi-session work gets the plan. A change that fits one sitting belongs to ordinary implementation: keep its steps in chat and do not create a plan document, a spec, or an execution workspace merely because it has several steps. Use this ceremony for multi-session work or several people's worth. A loaded skill is not a reason to make the task larger. Return to the task on the ordinary path; the remaining sections apply only to the written-plan path.

Announce at start, only after that gate: "I'm using the writing-plans skill to create the implementation plan."

Context: If working in an isolated worktree, it should have been created via the deniz-process.using-git-worktrees skill at execution time.

Save plans to: docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md

  • (User preferences for plan location override this default)

Scope Check

If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.

File Structure

Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.

  • Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.
  • You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.
  • Files that change together should live together. Split by responsibility, not by technical layer.
  • In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.
  • Verification and one-off operations use the tools the repository and platform already have (the dotnet CLI, dotnet test, existing scripts). Do not plan a new project, script, harness, tool in another language, or evidence document in the repository for verification or a one-off operation unless the request asks for one. A one-off check is a command in a step, not a file.

This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.

Task Right-Sizing

A task is the smallest unit that carries its own test cycle and is worth a fresh reviewer's gate. When drawing task boundaries: fold setup, configuration, scaffolding, and documentation steps into the task whose deliverable needs them; split only where a reviewer could meaningfully reject one task while approving its neighbor. Each task ends with an independently testable deliverable.

Step Granularity

Each step is one action with a checkable result:

  • "Write the failing test" - step
  • "Run it to make sure it fails" - step
  • "Implement the minimal code to make the test pass" - step
  • "Run the tests and make sure they pass" - step
  • "Commit" - step

Plan Document Header

Every plan MUST start with this header:

# [Feature Name] Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use deniz-process.subagent-driven-development or deniz-process.executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

**Goal:** [One sentence describing what this builds]

**Architecture:** [2-3 sentences about approach]

**Tech Stack:** [Key technologies/libraries]

**Spec:** [path to the spec/design doc this plan implements — the plan
argues from the spec, so the spec travels with it; executors read both]

## Global Constraints

[The spec's project-wide requirements — version floors, dependency limits,
naming and copy rules, platform requirements — one line each, with exact
values copied verbatim from the spec. Every task's requirements implicitly
include this section.]

## Review Focus

[The five input classes or failure modes the spec implies but no task's
tests exercise that are most likely to bite a person using this software
— one line each, naming the input or condition and the behavior a
reasonable person would expect, most likely first. The spec is a vision
document: it says what the software must do, not everything it will
meet, and its silence on an input is not permission for that input to
break the program. Write the list here, once, with the spec in front of
you. Then, for each line, add the test that pins it to the task that
owns the code, in that task's own step style.]

---

Task Structure

### Task N: [Component Name]

**Files:**
- Create: `exact/path/to/file.py`
- Modify: `exact/path/to/existing.py:123-145`
- Test: `tests/exact/path/to/test.py`

**Interfaces:**
- Consumes: [what this task uses from earlier tasks — exact signatures]
- Produces: [what later tasks rely on — exact function names, parameter
  and return types. A task's implementer sees only their own task; this
  block is how they learn the names and types neighboring tasks use.]

- [ ] **Step 1: Write the failing test**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected
```

- [ ] **Step 2: Run test to verify it fails**

Run: `pytest tests/path/test.py::test_name -v`
Expected: FAIL with "function not defined"

- [ ] **Step 3: Implement `function(input: InputType) -> ResultType` in `exact/path/to/file.py`**

One line on the approach when the signature and the test leave a choice
(which library call, which data structure); a code block only for an
algorithm they do not determine.

- [ ] **Step 4: Run test to verify it passes**

Run: `pytest tests/path/test.py::test_name -v`
Expected: PASS

- [ ] **Step 5: Commit**

```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```

What a Step Contains

A step is done when the implementer can write exactly one reasonable thing from it. That is the whole requirement: unambiguous, not complete. Each kind of step carries what makes it unambiguous and nothing more:

  • A test step: the test's name and its assertions, as code, with the spec's exact values in them.
  • A code step: the exact signature (name, parameters, return type), the file it lives in, and the specific values the spec pins. The implementer writes the body. A body appears only for an algorithm the signature and tests do not determine, or for exact copy the spec fixes.
  • A verification step: the command to run and the output that means it passed.
  • A reference to another task: that task's Interfaces block says what to use; the plan does not repeat that task's code.

A plan is the set of decisions the implementer cannot make alone. A plan longer than the code it describes has written the code instead. Lines that decide nothing ("TBD", "handle edge cases", "add appropriate validation", "write tests for the above", a type or function no task defines) are the opposite failure, and the self-review catches both.

Self-Review

After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.

1. Spec coverage: Skim each section/requirement in the spec. Can you point to a task that implements it? List any gaps.

2. Step scan: Every step must let the implementer write exactly one reasonable thing, and no step may carry more than that: a line that decides nothing is a gap, a function body the signature and tests already determine is a transcript. Fix both.

3. Type consistency: Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called clearLayers() in Task 3 but clearFullLayers() in Task 7 is a bug.

4. Review Focus: For each input class or failure mode the spec implies, is there a task whose tests exercise it? The five uncovered ones most likely to bite a person go in the Review Focus section, and each line there gets its test added to the owning task. An empty section means you checked and found none, not that you skipped the check.

5. Proportion: Compare the plan's length to the spec's. A plan several times longer than the spec it implements is a transcript of the program, not a plan. If code blocks are most of the document, replace bodies with signatures, test names and assertions, and check that each step is still unambiguous.

If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.

Execution Handoff

After saving and self-reviewing the plan, give the user its path and a short summary. What comes next depends on what the user asked for at the start, not on the design approval:

  • A request to build, add, fix, or change something ("let's add X") is a request to execute. Continue into execution after the summary; do not wait for a plan review.
  • A plan-only request ("write a plan", "design X") ends with that delivery and authorizes no implementation.

If the user already requested execution of the approved scope, do not ask for the same approval because you created a plan. Preserve an execution method or working-directory choice they already gave. Ask again only for a material change to the approved scope or a separately gated destructive, security-sensitive, or external action; present those changes together, with a recommendation.

When execution is authorized but no method was specified, choose by judgment, not a fixed label: deniz-process.executing-plans when the plan fits the current context and per-task isolation buys little; deniz-process.subagent-driven-development when the user chose per-task implementers and reviews, or substantial independent tasks benefit from fresh contexts. State the choice and its cost in one line, then continue the authorized work; choosing an executor is not an approval step. Only when you are genuinely torn between the two, ask once, with your recommendation.

04 同仓库更多 Skills

Blind-Striker
Blind-Striker/agent-skills-and-plugins

writing-tunit-tests

Write tests in TUnit — the attributes, the async assertion model, data-driven cases, lifecycle hooks, and the parallelism rules. USE FOR writing or fixing a test in a TUnit project, translating a test idea into TUnit syntax, or reviewing TUnit test code for API mistakes. DO NOT USE FOR deciding what to test, judging whether a test is any good, or running tests.

★ 1
Blind-Striker
Blind-Striker/agent-skills-and-plugins

dotnet-walls

Walls for a .NET change in a repository without its own quality gates — pinned, ephemeral analyzer, format, clone and scanner commands for the verify step, their identity ratchet, and the build traps. Use during a walls preflight, or when a worker's verify step needs .NET quality gates.

★ 1
Blind-Striker
Blind-Striker/agent-skills-and-plugins

csharp-15

Write, review and modernize C# 15 (.NET 11) code correctly. Covers every C# 15 feature - collection expression arguments (`[with(...), ...]`), union types (`union`, `[Union]`, `IUnion`, custom unions), closed class hierarchies (`closed`), extension indexers, labeled `break`/`continue`, non-virtual static interface members on runtimes without default interface methods, and the preview memory-safety model (`unsafe(expr)`, `safe`, requires-unsafe members). Use when code targets net11.0 or LangVersion 15/preview, when the user mentions any of these features, when replacing marker interfaces, OneOf-style results, `goto`/flag loop exits or capacity/comparer boilerplate, or when the build reports CS8121, CS8509, CS8655, CS8510, CS0121/CS0411 on a `with(...)` element, CS9370, CS9380 or CS9363.

★ 1
Blind-Striker
Blind-Striker/agent-skills-and-plugins

verified-waves

Run one task as verified multi-agent waves. Plans the fan-out, sends findings to fresh skeptics, keeps a ledger, and reports N of M done; small tasks stay solo.

★ 1
Blind-Striker
Blind-Striker/agent-skills-and-plugins

harness

The bundled dispatch harness, which runs a task file on worker models through OpenCode or Codex, fences their writes, escalates their asks to the operator, settles each result from git and its verify commands, and records every step in a ledger. Its commands, task file, modes and write fence, configuration, runs and their recovery, ledger and exit codes.

★ 1
Blind-Striker
Blind-Striker/agent-skills-and-plugins

delegating-to-worker-models

Use when you hand off implementation, a plan, research a decision will rely on, or a review, and you brief the worker and check what comes back. A subagent that searches, reads in parallel, or keeps your context small is ordinary tool use. Covers what stays with you, the mechanism, assigning work by strength, the walls preflight, prompts without contradictions, the worker contract and model profiles, evidence from your own run, review, and the fix-up loop.

★ 1