Agent skill

Tsh Technical Context Discovering

by TheSoftwareHouse in TheSoftwareHouse/copilot-collections

Discover and establish technical context before implementing any feature.

MITAuto-check passedDevelopment

Install Tsh Technical Context Discovering

skills CLI
$ npx skills add TheSoftwareHouse/copilot-collections --skill tsh-technical-context-discovering -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheSoftwareHouse/copilot-collections tsh-technical-context-discovering --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheSoftwareHouse/copilot-collections.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/tsh-technical-context-discovering .claude/skills/tsh-technical-context-discovering && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tsh-technical-context-discovering
GitHub stars
284
Token cost
~1.4k tokens
SKILL.md length
604 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Discover and establish technical context before implementing any feature.

  • Any task requiring understanding of project conventions
  • SKILL.md covers When to Use and Technical Context Discovery…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Coding standards

What it does

Tsh Technical Context Discovering is an agent skill from TheSoftwareHouse/copilot-collections. Discover and establish technical context before implementing any feature. Prioritize project instructions, existing codebase patterns, and external documentation in that order. Use for any task requiring understanding of project conventions, coding standards, architecture patterns, and established practices before writing code.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code quality and Software architecture. The repository describes itself as: Opinionated AI-enabled workflows for product engineering. The licence is MIT.

When your agent uses it

  • Any task requiring understanding of project conventions
  • Coding standards
  • Architecture patterns
  • Established practices before writing code

Example prompts

  • “/tsh-technical-context-discovering”

What it can do on your machine

Read from SKILL.md and the folder at commit 2fbe51e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tsh Technical Context Discovering loads about 1.4k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 604 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheSoftwareHouse/copilot-collections at commit 2fbe51e, republished under its MIT licence (© TheSoftwareHouse). 604 words, ~1,364 tokens.

Download SKILL.mdSave it as .claude/skills/tsh-technical-context-discovering/SKILL.md (or your agent's skills folder).
name
tsh-technical-context-discovering
description
Discover and establish technical context before implementing any feature. Prioritize project instructions, existing codebase patterns, and external documentation in that order. Use for any task requiring understanding of project conventions, coding standards, architecture patterns, and established practices before writing code.
user-invocable
false

Technical Context Discovery

This skill provides a systematic approach for understanding a project's technical context before making any code changes. It ensures consistency with existing patterns and prevents introducing conflicting conventions.

When to Use

  • Before implementing any feature or fix
  • Before writing tests (unit, integration, E2E)
  • Before making architectural decisions that affect existing code
  • When onboarding to a new area of the codebase

Technical Context Discovery Process

Use the checklist below and track your progress:

Discovery progress:
- [ ] Step 0: Check plan file for persisted context
- [ ] Step 1: Check Copilot instruction files
- [ ] Step 2: Analyze existing codebase patterns
- [ ] Step 3: Consult external documentation (if needed)
- [ ] Step 4: Apply the implementation rule

Step 0: Check Plan File for Persisted Context

ALWAYS check first whether a plan file (*.plan.md) exists for the current task and contains a "Technical Context" section.

If a "Technical Context" section exists and is populated:

  • Use it as-is — do not re-discover conventions, patterns, or standards that are already documented there.
  • Skip Steps 1-2 entirely. Proceed directly to Step 4 (Apply the implementation rule) using the persisted context.
  • Only perform targeted discovery (Steps 1-2) for aspects not covered by the persisted context.

If no plan file exists, or the "Technical Context" section is missing/empty:

  • Proceed with Steps 1-4 as normal.

Step 1: Check Copilot Instruction Files

ALWAYS check first for existing Copilot instructions in the project:

  • Search for .github/copilot-instructions.md at the repository root.
  • Search for *.instructions.md files in relevant directories (e.g., src/, tests/, e2e/, backend/, feature-specific folders).
  • Search for .copilot/ directory with configuration files.

If instructions files exist, they are the primary source of truth for:

  • Coding standards and conventions
  • Architecture patterns and project structure
  • Technology stack specifics and version requirements
  • Testing strategies and patterns
  • Naming conventions and file organization
  • Locator strategies (for E2E tests)
  • Test data management approaches
  • Environment configuration

Step 2: Analyze Existing Codebase Patterns

If no Copilot instructions are found, or if they don't cover specific aspects, analyze the existing codebase to understand and replicate established patterns:

  • Architecture patterns: Examine folder structure, layering (controllers, services, repositories), and module organization.
  • Code style: Analyze existing files for naming conventions, formatting, and idioms used.
  • Error handling: Look at how exceptions are caught, logged, and returned to clients.
  • Validation patterns: Check how input validation is implemented (decorators, middleware, manual checks).
  • Testing patterns: Review existing tests to understand structure, mocking strategies, assertion styles, fixtures, and test data management.
  • Database patterns: Examine existing migrations, entities/models, and query patterns.
  • API patterns: Analyze existing endpoints for response formats, status codes, and documentation style.
  • Configuration: Check how environment variables, feature flags, and configuration are managed.
Show full SKILL.md (210 more words)Show less

Use search and usages tools to find similar implementations in the codebase and follow the same approach.

Step 3: Consult External Documentation

If neither Copilot instructions nor sufficient existing codebase patterns are available (e.g., new project, greenfield feature, or first implementation of a specific pattern), use external documentation and industry best practices:

  • Use context7 tool to search for official documentation of the framework/library being used (check project config for exact versions first).
  • Apply industry-standard best practices for the technology stack.
  • Follow OWASP security guidelines for secure coding practices.
  • Apply SOLID principles and clean architecture patterns.
  • Use well-established design patterns appropriate for the use case.

IMPORTANT: When using best practices in a greenfield scenario, document your decisions in code comments or README to establish patterns for future development.

Step 4: Apply the Implementation Rule

Based on what you discovered, apply this decision hierarchy:

Context AvailableAction
Instructions files existFollow them strictly. Instructions take precedence over general best practices.
No instructions, but codebase has patternsMirror existing patterns exactly. Consistency with existing code > theoretical best practices.
No instructions, no existing patternsApply documentation-based best practices and industry standards. Document decisions for future reference.

Critical rule: Never introduce new patterns unless explicitly requested by the user or specified in the implementation plan.

© TheSoftwareHouse, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/tsh-technical-context-discovering of TheSoftwareHouse/copilot-collections.

Open the folder on GitHubat commit 2fbe51e

Compare with similar skills

Tsh Technical Context Discovering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tsh Technical Context Discovering compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tsh Technical Context Discovering this skillTheSoftwareHouse/copilot-collections284—~1.4kAutomated safety check: PassMIT
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT
Code Review SkillRain-kl/OpenFlare288—~2.3kAutomated safety check: NotesMIT
Marmite Developmentrochacbruno/marmite883—~6.9kAutomated safety check: PassAGPL-3.0
Code Review Excellenceandrew-yangy/gru-ai155—~1.7kAutomated safety check: NotesMIT
A Philosophy of Software Designciembor/agent-rules-books2.9k—~181Automated safety check: PassMIT

Similar skills

  • Code Review Skill

    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…

    2.1k GitHub stars~2.8k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Code Review Skill

    Rain-kl/OpenFlare

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C/.NET, Kotlin, Swift, NestJS, C/C++, and more.

    288 GitHub stars~2.3k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Marmite Development

    rochacbruno/marmite

    Guidelines and workflows for contributing to the marmite codebase - covers code quality, testing, architecture patterns, and contribution checklists

    883 GitHub stars~6.9k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Code Review Excellence

    andrew-yangy/gru-ai

    Provides comprehensive code review guidance for React 19, Vue 3, Rust, TypeScript, Java, Python, and C/C++.

    155 GitHub stars~1.7k tokensUpdated 7 mo ago
    DevelopmentAuto-check: notes
  • A Philosophy of Software Design

    ciembor/agent-rules-books

    Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.

    2.9k GitHub stars~181 tokensUpdated 28 days ago
    DevelopmentAuto-check passed
  • Senior Fullstack

    davila7/claude-code-templates

    Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL.

    32k GitHub starsUsed in 7 repos~1.1k tokens
    DevelopmentAuto-check: notes

More from TheSoftwareHouse/copilot-collections

All 21 skills in this repo
  • Tsh Creating Skills

    TheSoftwareHouse/copilot-collections

    Create new skills (SKILL.md) for GitHub Copilot. An agent skill from TheSoftwareHouse/copilot-collections.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Implementing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend component patterns, composition, design token integration, barrel file organization, error handling, and Figma-to-code workflow.

    284 GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Implementing Terraform Modules

    TheSoftwareHouse/copilot-collections

    Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices.

    284 GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Optimizing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend rendering optimization, code splitting, memoization strategies, bundle size control, asset optimization, and memory management.

    284 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Reviewing Frontend

    TheSoftwareHouse/copilot-collections

    Frontend-specific code review criteria, component anti-patterns, hooks quality, rendering correctness, accessibility and performance spot-checks, and module organization issues.

    284 GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check passed
  • Tsh Writing Hooks

    TheSoftwareHouse/copilot-collections

    Custom hook and composable patterns — naming, composition, stable return shapes, lifecycle cleanup, and testing strategies.

    284 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed

Questions about Tsh Technical Context Discovering

What does Tsh Technical Context Discovering do?

Discover and establish technical context before implementing any feature. Tsh Technical Context Discovering is an agent skill from TheSoftwareHouse/copilot-collections. Discover and establish technical context before implementing any feature.

When should I use Tsh Technical Context Discovering?

Tsh Technical Context Discovering fits situations like: any task requiring understanding of project conventions; coding standards; architecture patterns; established practices before writing code.

How do I install Tsh Technical Context Discovering in Claude Code?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-technical-context-discovering -a claude-code`. Or copy the skill folder (.github/skills/tsh-technical-context-discovering in TheSoftwareHouse/copilot-collections) into .claude/skills/tsh-technical-context-discovering in your project. Claude Code loads it when a task matches its description.

How do I install Tsh Technical Context Discovering in Codex?

Run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-technical-context-discovering -a codex`. Or copy the skill folder (.github/skills/tsh-technical-context-discovering in TheSoftwareHouse/copilot-collections) into .agents/skills/tsh-technical-context-discovering in your project. Codex loads it when a task matches its description.

Can I use Tsh Technical Context Discovering in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheSoftwareHouse/copilot-collections --skill tsh-technical-context-discovering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsh-technical-context-discovering, .gemini/skills/tsh-technical-context-discovering, .github/skills/tsh-technical-context-discovering and .opencode/skills/tsh-technical-context-discovering in your project.

What does Tsh Technical Context Discovering need to run?

SKILL.md names no scripts, command-line tools or credentials: Tsh Technical Context Discovering is instructions for the agent only.

Does Tsh Technical Context Discovering access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tsh Technical Context Discovering safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tsh Technical Context Discovering use?

Tsh Technical Context Discovering is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tsh Technical Context Discovering use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tsh Technical Context Discovering?

Skills that share tags, products or a category with Tsh Technical Context Discovering: Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Code Review Skill (Rain-kl/OpenFlare, 288 stars), Marmite Development (rochacbruno/marmite, 883 stars) and Code Review Excellence (andrew-yangy/gru-ai, 155 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tsh Technical Context Discovering?

TheSoftwareHouse (a GitHub organization) maintains it in TheSoftwareHouse/copilot-collections, which has 284 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 5, 2026.

Source: TheSoftwareHouse/copilot-collections on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.