New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Deepchat Sdd

by ThinkInAIXYZ in ThinkInAIXYZ/deepchat

Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path.

Apache-2.0Auto-check passedDevelopment

Install Deepchat Sdd

skills CLI
$ npx skills add ThinkInAIXYZ/deepchat --skill deepchat-sdd -a claude-code

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

GitHub CLI
$ gh skill install ThinkInAIXYZ/deepchat deepchat-sdd --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/ThinkInAIXYZ/deepchat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deepchat-sdd .claude/skills/deepchat-sdd && 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
deepchat-sdd
GitHub stars
6.4k
Token cost
~2.2k tokens
SKILL.md length
1,148 words
Files
2
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path.

  • Works in 12 steps: Inspect the current code and docs first. → Decide whether the work is substantial… → Pick the target folder from the… → …
  • Tasks that involve Refactoring
  • SKILL.md covers When To Use, Classify The Goal, Required Artifacts and Artifact Boundaries, plus 4 more sections
  • Calls pnpm

What it does

Deepchat Sdd is an agent skill from ThinkInAIXYZ/deepchat. Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Use plan.md as the only separate tracker when needed, default to implementation-first validation, and ask before optional GitHub issue sync unless the developer explicitly requested sync.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Refactoring. It works with GitHub and OpenAI. The repository describes itself as: 🐬DeepChat - A smart assistant that connects powerful AI to your personal world. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Refactoring

Example prompts

  • “/deepchat-sdd”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the current code and docs first.
  2. Decide whether the work is substantial enough for SDD; skip artifacts for trivial/local changes.
  3. Pick the target folder from the classification rules when SDD is needed.
  4. Write or update the RFC and resolve every question that could change the implementation.
  5. For feature, architecture, or multi-slice bug work, write one ordered implementation plan
  6. Keep the implementation aligned with existing DeepChat patterns
  7. For architecture work that changes or replaces a historical feature, update that feature's
  8. Complete the planned implementation before deciding whether to author new test code. Existing
  9. Review the whole change against the spec for hidden side effects, compatibility, failure
  10. Select the smallest useful validation, remove temporary verification, and add durable tests
  11. Update plan.md or the complex-bug spec checklist as coherent implementation slices land.
  12. Ask whether to sync an eligible GitHub issue only after the docs or implementation clarify the

What it can do on your machine

Read from SKILL.md and the folder at commit 4eb6062. 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

    Shell commands in SKILL.md call:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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

Deepchat Sdd loads about 2.2k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 1,148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~129
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 ThinkInAIXYZ/deepchat at commit 4eb6062, republished under its Apache-2.0 licence (© ThinkInAIXYZ). 1,148 words, ~2,188 tokens.

Download SKILL.mdSave it as .claude/skills/deepchat-sdd/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
deepchat-sdd
description
Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Use plan.md as the only separate tracker when needed, default to implementation-first validation, and ask before optional GitHub issue sync unless the developer explicitly requested sync.

DeepChat SDD

When To Use

Use this skill before substantial DeepChat source code, configuration, tests, docs, build scripts, release workflows, or project structure changes that need shared context or a durable decision record.

Skip SDD for trivial or tightly localized work unless the developer explicitly asks for it:

  • visual/style fixes, copy changes, and small UI layout adjustments
  • simple localized logic changes with a clear owner module
  • routine docs edits that do not change project direction
  • release metadata already covered by the release flow

If the scope is unclear, inspect first and then ask whether SDD is wanted instead of creating artifacts by default.

Classify The Goal

Create one kebab-case folder per goal:

  • New capability, user-visible behavior, integration, or tool large enough to need a shared plan: docs/features/<goal>/
  • Complex bug, regression, failing test, CI failure, reliability problem, or prompt/runtime issue: docs/issues/<goal>/
  • Refactor, migration, dependency boundary, shared contract, runtime architecture, or cross-module design: docs/architecture/<goal>/

If one request contains multiple independent goals, split them into separate folders. Keep current architecture reference docs such as docs/architecture/agent-system.md in place; use subfolders for new architecture targets.

Treat a bug as SDD-worthy only when the root cause, blast radius, or fix path is complex enough that future developers benefit from the written record. For simple style defects or obvious local logic fixes, skip docs/issues/* and implement directly.

If a bug fix introduces a new user-visible capability, data migration, public contract, or cross-module redesign, classify the work as feature or architecture instead.

Required Artifacts

Feature and architecture goals use two artifacts:

  • spec.md: the normative RFC covering context, goals, non-goals, design, ownership, interfaces, data flow, invariants, compatibility, acceptance criteria, and open questions
  • plan.md: ordered implementation steps and live completion state, followed by whole-change review, validation selection, cleanup, and quality gates

Do not create tasks.md. The plan is the only execution tracker.

Complex bug goals normally use one file:

  • spec.md: issue description, impact, root cause or suspected location, fix design, concise implementation checklist, validation outcome, and linked GitHub issue if one exists

Add plan.md only when a complex bug has multiple independently trackable implementation slices. Never add tasks.md.

Resolve every [NEEDS CLARIFICATION] marker before implementation. If the requested change is tiny, prefer skipping SDD over creating a token artifact.

Artifact Boundaries

Write spec.md as an RFC. It must explain enough implementation direction to constrain local code decisions without becoming a file-by-file task list. Acceptance criteria describe observable outcomes or independently verifiable contracts, not a test inventory.

Use plan.md as both plan and task tracker. Organize it into ordered checkbox sections whose steps are coherent, reviewable implementation slices. Include the objective, ownership boundary, essential guidance, dependencies when any, and completion condition. Reference the spec instead of repeating its design.

GitHub Issue Sync

Do not sync GitHub issues by default. Issue sync is a follow-up record, not a gate for local SDD or implementation.

Only create or link a GitHub issue when the developer explicitly asks, or after asking and getting approval once the SDD artifacts are written or the implementation is complete.

Eligible work:

  • Complex bugs only; simple style defects and obvious local logic fixes should not get issues.
  • Whole new features or major feature rewrites only; single actions, small behavior tweaks, and ordinary adjustments should not get issues.

If eligibility is unclear, ask the developer after the work is understood. Never self-authorize issue creation just because local gh is installed and authenticated.

When approved:

  • Feature issues use the [feature] label.
  • Bug issues use the [bug] label.
  • Create the label first if it is missing and gh has permission.
  • Record the issue URL or number in the SDD artifact.
  • If gh is unavailable or unauthorized, continue local-only and note that no GitHub issue was created only when sync was requested or approved.

When creating a PR for linked work, include Closes #NNN in the PR body so GitHub closes the issue automatically after merge.

Show full SKILL.md (505 more words)Show less

Workflow

  1. Inspect the current code and docs first.
  2. Decide whether the work is substantial enough for SDD; skip artifacts for trivial/local changes.
  3. Pick the target folder from the classification rules when SDD is needed.
  4. Write or update the RFC and resolve every question that could change the implementation.
  5. For feature, architecture, or multi-slice bug work, write one ordered implementation plan without a separate task list or upfront test matrix.
  6. Keep the implementation aligned with existing DeepChat patterns:
    • main process Presenter boundaries
    • typed shared/contracts/*
    • renderer api/*Client
    • Vue 3 Composition API and i18n for UI strings
  7. For architecture work that changes or replaces a historical feature, update that feature's retained spec.md if it is still a maintained contract.
  8. Complete the planned implementation before deciding whether to author new test code. Existing checks may run at any time.
  9. Review the whole change against the spec for hidden side effects, compatibility, failure behavior, performance, security, naming, and maintenance cost.
  10. Select the smallest useful validation, remove temporary verification, and add durable tests only for qualifying behavior or contracts.
  11. Update plan.md or the complex-bug spec checklist as coherent implementation slices land.
  12. Ask whether to sync an eligible GitHub issue only after the docs or implementation clarify the scope, unless the developer already requested issue sync.
  13. Run pnpm run format, pnpm run i18n, pnpm run lint, and pnpm run typecheck before handoff when app code, tests, i18n, or project docs changed.

Implementation-First Validation

Implementation-first means finishing the planned implementation before deciding whether to author new tests. It does not prohibit running existing tests, type checking, linting, builds, or manual checks during development.

New test code before implementation is exceptional. Use it only when the developer requests TDD, a minimal executable reproduction is required to understand a complex failure, or migration, concurrency, recovery, or protocol compatibility needs characterization of current behavior. Record the reason in one sentence in plan.md or the complex-bug spec.

After implementation, choose among:

  • existing tests and static or build checks;
  • temporary probes, scripts, or tests that must be removed before handoff; and
  • the smallest durable regression tests for user-visible behavior, documented cross-module contracts, persistence or migration, lifecycle or concurrency, recovery, security boundaries, or proven regressions.

Do not retain tests that mirror private control flow, assert incidental call order, duplicate the implementation through mocks, or exist only to increase coverage. Prefer no new test to a low-value implementation-coupled test.

Documentation Hygiene

  • Do not perform broad SDD cleanup during ordinary feature, bug, or architecture work.
  • Use the separate deepchat-sdd-cleanup skill only when the developer explicitly asks to clean or organize SDD documentation.
  • Treat existing tasks.md files as legacy and migrate them only when that goal is actively updated. Merge remaining work into an existing plan.md; without one, keep a single-slice complex bug checklist in spec.md and create plan.md for feature, architecture, or multi-slice bug work. Do not perform a repository-wide migration during unrelated work.
  • During the current goal, update directly affected historical specs when they remain active contracts.

© ThinkInAIXYZ, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/deepchat-sdd of ThinkInAIXYZ/deepchat.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 4eb6062

Compare with similar skills

Deepchat Sdd 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.

Deepchat Sdd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deepchat Sdd this skillThinkInAIXYZ/deepchat6.4k—~2.2kAutomated safety check: PassApache-2.0
Codexskills-directory/skill-codex1.5k3 repos~1.8kAutomated safety check: PassMIT
Valgocohesivestack/valgo508—~2.4kAutomated safety check: PassMIT
ReleaseOpenSource03/harnss382—~1.1kAutomated safety check: NotesMIT
Rust Hygiene Audittsz-org/tsz577—~1.5kAutomated safety check: PassApache-2.0
Examples Run Analysisopenai/openai-agents-python30k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Codex

    skills-directory/skill-codex

    A skill your agent uses when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

    1.5k GitHub starsUsed in 3 repos~1.8k tokens
    DevelopmentAuto-check passed

  • Valgo

    cohesivestack/valgo

    Add, refactor, debug, review, explain, or migrate type-safe validation in consumer Go applications using github.com/cohesivestack/valgo.

    508 GitHub stars~2.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Release

    OpenSource03/harnss

    Run the Harnss release workflow — review staged diff, bump version, commit, tag, push, and create a GitHub release.

    382 GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check: notes

  • Rust Hygiene Audit

    tsz-org/tsz

    Run a deep DRY + code-hygiene audit of the Rust workspace and turn the findings into verified, deduplicated, hierarchical GitHub tech-debt issues.

    577 GitHub stars~1.5k tokensUpdated 29 days ago
    DevelopmentAuto-check passed

  • Examples Run Analysis

    openai/openai-agents-python

    Official

    Analyze logs and source from a completed manual examples run.

    30k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

  • Release

    pwrdrvr/openclaw-codex-app-server

    Plan and publish a GitHub Release in a tag-driven repository.

    265 GitHub stars~2.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from ThinkInAIXYZ/deepchat

All 15 skills in this repo

  • DeepChat Release Process

    ThinkInAIXYZ/deepchat

    Runs the DeepChat repository's release flow: prepares bilingual release notes and a version bump on dev, cuts or updates a release branch, then fast-forwards main and tags the version.

    6.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • DeepChat Provider Integration

    ThinkInAIXYZ/deepchat

    Guides adding an LLM provider to DeepChat through explicit source changes: collect the provider details, pick a transport path and add registry entries and tests.

    6.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • DeepChat CLI

    ThinkInAIXYZ/deepchat

    Lets an agent drive DeepChat's bundled CLI for model calls, media generation, transcription, OCR, artifacts, configuration, Skills and MCP operations, within strict command rules.

    6.4k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • DeepChat Settings

    ThinkInAIXYZ/deepchat

    Changes DeepChat's own application settings, such as theme, language, font size and sound, through a fixed set of settings tools, and points to the right screen for anything else.

    6.4k GitHub stars~786 tokensUpdated today
    Auto-check passed

  • DeepChat Data Import Helper

    ThinkInAIXYZ/deepchat

    Guides building a third-party importer for DeepChat's local SQLite data, covering schema, encryption and safe read-only access patterns.

    6.4k GitHub stars~738 tokensUpdated today
    Auto-check passed

  • DeepChat Desktop Control

    ThinkInAIXYZ/deepchat

    Operates native desktop apps through DeepChat's built-in Computer Use tools, following a snapshot-then-act loop with session setup, app launch and window inspection.

    6.4k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Deepchat Sdd

What does Deepchat Sdd do?

Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Deepchat Sdd is an agent skill from ThinkInAIXYZ/deepchat. Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path.

When should I use Deepchat Sdd?

Deepchat Sdd fits situations like: tasks that involve Refactoring.

How do I install Deepchat Sdd in Claude Code?

Run `npx skills add ThinkInAIXYZ/deepchat --skill deepchat-sdd -a claude-code`. Or copy the skill folder (.agents/skills/deepchat-sdd in ThinkInAIXYZ/deepchat) into .claude/skills/deepchat-sdd in your project. Claude Code loads it when a task matches its description.

How do I install Deepchat Sdd in Codex?

Run `npx skills add ThinkInAIXYZ/deepchat --skill deepchat-sdd -a codex`. Or copy the skill folder (.agents/skills/deepchat-sdd in ThinkInAIXYZ/deepchat) into .agents/skills/deepchat-sdd in your project. Codex loads it when a task matches its description.

Can I use Deepchat Sdd 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 ThinkInAIXYZ/deepchat --skill deepchat-sdd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepchat-sdd, .gemini/skills/deepchat-sdd, .github/skills/deepchat-sdd and .opencode/skills/deepchat-sdd in your project.

What does Deepchat Sdd need to run?

Going by SKILL.md and its folder, Deepchat Sdd needs the command-line tools its instructions call (pnpm).

Does Deepchat Sdd 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 Deepchat Sdd 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 Deepchat Sdd use?

Deepchat Sdd is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepchat Sdd use?

About 2.2k tokens (SKILL.md is roughly 8.8k 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 Deepchat Sdd?

Skills that share tags, products or a category with Deepchat Sdd: Codex (skills-directory/skill-codex, 1.5k stars), Valgo (cohesivestack/valgo, 508 stars), Release (OpenSource03/harnss, 382 stars) and Rust Hygiene Audit (tsz-org/tsz, 577 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepchat Sdd?

ThinkInAIXYZ (a GitHub organization) maintains it in ThinkInAIXYZ/deepchat, which has 6,359 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

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