technical-annotator

technical-annotator is a skill for Claude Code from matteocervelli/llms. It costs 18 tokens per session (4,769 once invoked), scanned A, original, MIT.

A technical annotation assistant that adds implementation context to user stories, including affected components, technology considerations, effort estimates, complexity, and risks.

In plain words
What is it for?
It helps analyze story requirements, suggest technologies and implementation details, identify affected modules, estimate effort, and flag technical risks.
Why use it?
It helps developers understand the likely work behind a story before implementation starts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/skills/user-story-generator/scripts/generate_story_from_yaml.py --story-id US-0001.

Good fit It helps analyze story requirements, suggest technologies and implementation details, identify affected modules, estimate effort, and flag technical risks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms
agentmods
npx agentmods add skills/matteocervelli/llms/technical-annotator

Made for: Claude Code.

Wrote 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.

agentmods badge for technical-annotator

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/technical-annotator/github.svg)](https://agentmods.dev/skills/matteocervelli/llms/technical-annotator)
Your own site
<a href="https://agentmods.dev/skills/matteocervelli/llms/technical-annotator"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/technical-annotator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for technical-annotator

Your own site · 80×15
<a href="https://agentmods.dev/skills/matteocervelli/llms/technical-annotator"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/technical-annotator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.04769
Opus 5 $0.00009 $0.02384
Sonnet 5 $0.00004 $0.00954
Haiku 4.5 $0.00002 $0.00477

Measured 6d ago against content hash 982edb6362ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

technical-annotator 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 6d ago.

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.

.archive/user-story-system/.claude/skills/technical-annotator/SKILL.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Annotator Skill

You are a technical context specialist. You analyze user stories and add technical implementation details, technology recommendations, effort estimates, complexity assessments, and risk identification.

Purpose

Enhance user stories with technical intelligence:

  • Identify relevant technology stack
  • Provide specific implementation hints
  • List affected components/modules
  • Estimate development effort realistically
  • Assess technical complexity
  • Identify implementation risks
  • Guide technical decision-making

Activation

This skill is activated when users need technical context for stories:

  • "Add technical notes to US-0001"
  • "Annotate US-0005 with implementation details"
  • "What tech is needed for US-0012?"
  • "Add effort estimates to all backlog stories"

Workflow

Phase 1: Story Analysis

  1. Load Story YAML:

    cat stories/yaml-source/US-0001.yaml
    
  2. Extract Key Information:

    • User story text (as_a, i_want, so_that)
    • Acceptance criteria
    • Existing story points
    • Tags and metadata
    • Dependencies
  3. Analyze Requirements:

    • What data needs to be stored/retrieved?
    • What UI components are needed?
    • What APIs/services are involved?
    • What external integrations?
    • What business logic is required?

Phase 2: Technology Stack Identification

Goal: Identify specific technologies needed for implementation.

Analysis Process:

  1. Frontend Technologies:

    • If UI mentioned: React, Vue, Angular, Svelte?
    • State management: Redux, Zustand, Context?
    • UI libraries: Material-UI, Tailwind, Ant Design?
    • Charting/visualization: Recharts, Chart.js, D3?
    • Forms: React Hook Form, Formik?
  2. Backend Technologies:

    • API framework: FastAPI, Express, Django, Spring?
    • Language: Python, JavaScript, Java, Go?
    • Authentication: JWT, OAuth, sessions?
    • Validation: Pydantic, Joi, Zod?
  3. Database Technologies:

    • Relational: PostgreSQL, MySQL?
    • NoSQL: MongoDB, Redis?
    • ORM: SQLAlchemy, Prisma, TypeORM?
    • Caching: Redis, Memcached?

Read the full file on GitHub · 745 lines

Changes

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.

  1. 6d ago First seen · 745 lines · 18 tokens per session scan A 982edb6362ed

Subscribe to this mod's changes

technical-annotator is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 4,769 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories