Skills for Real Engineers. Straight from my .agents directory.
writing-specs
Agent skill fromJetBrains/thinkrail
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
How to install writing-specs
npx skills add JetBrains/thinkrail# or add only this skill to Claude Code: copy the folder
packages/pi-thinkrail-workflow/skills/writing-specs/
# into
~/.claude/skills/writing-specs/ (all projects)
.claude/skills/writing-specs/ (one project)
1# Writing Specs23The workflow family's shared bar for every spec a workflow produces: **short, honest, on-rails**.4Process skills name this concept at the steps that draft or revise specs; *what* to draft and *when*5stays with the referencing skill. Graph mechanics — frontmatter, link kinds, the `spec_*` tools — are6the spec-graph skill's ground; this concept carries the quality bar the family holds on top of them,7and is where the family's rules for specs and the spec graph accrue.89## Short1011- Small enough to read in one sitting. Target signal, not completeness.12- Explain intent, not inventory: what the thing is for, what it owns, where its boundary runs — never13 a file listing or a restatement of the code.1415## Honest1617- Only settled content appears. Never pad with `[TBD]` or placeholder sections — a section that18 hasn't been settled simply doesn't exist yet.19- Anything inferred rather than confirmed is marked unconfirmed, inline, where it stands.20- New and inferred specs are `status: draft` until the user has reviewed them — the flip out of21 `draft` follows the user's review, never the drafting agent's own judgment. A reviewed durable spec22 goes `active`, never `done`: it stays in force and evolves with the project.2324## On-rails2526- High-signal enough that a future agent (or human) lands on the decisions without re-deriving them.27- The spec is the *only* home for rationale: decisions, invariants, trade-offs, and bug post-mortems28…
Excerpt shown under the repository's Apache-2.0 license.
More skills in thinkrail
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
