Borrowing it
Nothing to install: this file belongs to tatargabor/set-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tatargabor/set-copilot/master/.claude/skills/set/write-spec/SKILL.mdgit clone --depth 1 https://github.com/tatargabor/set-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tatargabor/set-copilot/write-spec)<a href="https://agentmods.dev/skills/tatargabor/set-copilot/write-spec"><img src="https://agentmods.dev/badge/skills/tatargabor/set-copilot/write-spec.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01964 |
| Opus 5 | $0.00026 | $0.00982 |
| Sonnet 5 | $0.00011 | $0.00393 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
write-spec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Spec — Profile-Driven Specification Generator
Guide the user through writing a detailed project specification. The spec is the most important input to the orchestration pipeline — spec quality directly determines output quality.
Key principles:
- Requirements describe WHAT, not HOW (no code blocks, no file paths)
- Every requirement gets a REQ-ID and at least one WHEN/THEN scenario
- Modular output for projects with 3+ features (main + per-feature files)
- Profile-driven: web projects get data model, seed, auth sections; others get core only
Workflow
Phase 0: Project Context Detection + Profile Loading
Before asking questions, detect the project type and load spec sections:
# Detect project type and tech stack
ls package.json pyproject.toml Cargo.toml go.mod Makefile docker-compose.yml 2>/dev/null
cat package.json 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print('Name:', d.get('name','')); deps=list(d.get('dependencies',{}).keys()); print('Deps:', ', '.join(deps[:15]))" 2>/dev/null
ls prisma/schema.prisma 2>/dev/null && echo "Prisma detected"
ls docs/*.make docs/design.make docs/design-system.md 2>/dev/null && echo "Design files detected"
Load profile sections:
python3 -c "
from set_orch.profile_loader import resolve_profile
import json
p = resolve_profile('.')
sections = [{'id':s.id,'title':s.title,'description':s.description,'required':s.required,'phase':s.phase,'output_path':s.output_path,'prompt_hint':s.prompt_hint} for s in p.spec_sections()]
print(json.dumps(sections, indent=2))
" 2>/dev/null
If profile loading fails (set-core not installed as package), use these fallback core sections:
- overview (phase 1) — Project name, purpose, tech stack
- requirements (phase 5) — Main features with REQ-IDs and scenarios
- orchestrator_directives (phase 10) — Parallel hints, review gates
- verification_checklist (phase 11) — Auto-generated from requirements
If the tech stack is unfamiliar, use the Agent tool (Explore subagent) to investigate before proceeding.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 219 lines · 53 tokens per session scan A 2ab8b6d92aac
write-spec is a skill published in the GitHub repository tatargabor/set-copilot (2 stars, last pushed 13d ago), licensed MIT. It adds 53 tokens to every session and 1,964 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…