ModLens Image Vision Bridge
liustack/modlens
Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.
Disciplined diagnosis for hard bugs and performance regressions.
MITAuto-check passed
Install Diagnose
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnose --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/diagnose .claude/skills/diagnose && rm -rf skills-srcUse ~/.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/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .claude/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnoseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnose --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/diagnose .agents/skills/diagnose && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .agents/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnose --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/diagnose .cursor/skills/diagnose && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .cursor/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zmy15/DeepSeek-for-VisualStudio.git --path .github/skills/diagnose--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnose --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/diagnose .gemini/skills/diagnose && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .gemini/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnoseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/diagnose .github/skills/diagnose && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .github/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zmy15/DeepSeek-for-VisualStudio diagnose --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zmy15/DeepSeek-for-VisualStudio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/diagnose .opencode/skills/diagnose && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "diagnose" agent skill from https://github.com/zmy15/DeepSeek-for-VisualStudio/tree/master/.github/skills/diagnose into .opencode/skills/diagnose/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "diagnose", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
diagnose- GitHub stars
- 109
- Token cost
- ~1.1k tokens
- SKILL.md length
- 621 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Disciplined diagnosis for hard bugs and performance regressions.
- Works in 7 steps: Triage (always) → Build a feedback loop (full path only) → Reproduce (full path only) → …
- Explicitly asks to diagnose/debug a hard issue
- SKILL.md covers Phase 0 - Triage (always), Phase 1 - Build a feedback…, Phase 2 - Reproduce (full path… and Phase 3 - Hypothesise (full…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Diagnose is an agent skill from zmy15/DeepSeek-for-VisualStudio. Disciplined diagnosis for hard bugs and performance regressions. Use only when the user explicitly asks to diagnose/debug a hard issue, or when a reported bug remains unexplained after a quick direct source inspection. Do not use for obvious config, workflow, UI, or single-path defects; handle those inline without the full loop.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with DeepSeek, OpenAI and C#. The repository describes itself as: AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify builds. Works with the official DeepSeek… The licence is MIT.
When your agent uses it
- Explicitly asks to diagnose/debug a hard issue
- A reported bug remains unexplained after a quick direct source inspection
- Single-path defects
- Handle those inline without the full loop
Example prompts
- “/diagnose”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 1ea8ed1. 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
Diagnose loads about 1.1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 621 words of instructions outside code blocks.
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 zmy15/DeepSeek-for-VisualStudio at commit 1ea8ed1, republished under its MIT licence (© zmy15). 621 words, ~1,111 tokens.
Download SKILL.mdSave it as
.claude/skills/diagnose/SKILL.md (or your agent's skills folder).- name
- diagnose
- description
- Disciplined diagnosis for hard bugs and performance regressions. Use only when the user explicitly asks to diagnose/debug a hard issue, or when a reported bug remains unexplained after a quick direct source inspection. Do not use for obvious config, workflow, UI, or single-path defects; handle those inline without the full loop.
Diagnose
Optimize for the shortest path to a verified root cause. Use the full loop only when the bug is behaviorally complex, intermittent, or cannot be traced by direct inspection.
Use the project's domain glossary and ADRs only when they are directly relevant to the suspected path. Do not delay triage to build background context.
Phase 0 - Triage (always)
- Identify the most direct execution path: likely file, function, workflow, configuration, or input boundary.
- Inspect 1-2 relevant locations before proposing hypotheses. Do not start with a catalogue of possible causes.
- Choose one path:
- Fast path: the root cause is directly visible and the fix is local. Apply the minimal fix, run one targeted verification, and stop. Do not require a harness, hypothesis list, user checkpoint, or post-mortem.
- Full path: the cause is not visible, the bug is intermittent, or the fix needs behavioural confirmation. Continue below.
Phase 1 - Build a feedback loop (full path only)
Timebox this phase. Try at most three relevant approaches, in this order:
- An existing failing test or command.
- A CLI/script invocation with a fixed input and deterministic assertion.
- A minimal harness or replay that exercises only the suspected path.
For configuration, workflow, and static code defects, a one-command deterministic transformation check is a complete loop. Do not build a UI or browser harness when source inspection plus a text-level assertion proves the behaviour.
If no useful loop exists after the timebox, report what was tried and ask for one concrete artifact or environment. Do not continue inventing scenarios.
Phase 2 - Reproduce (full path only)
Run the loop and confirm it exposes the user's reported symptom, not a nearby different failure. Capture the exact wrong output or timing. Do not repeat the same reproduction after it is understood.
Phase 3 - Hypothesise (full path only)
Generate 2-3 ranked, falsifiable hypotheses only after reproduction. Test one variable at a time.
Do not show the list to the user by default. Ask for domain input only when the remaining hypotheses cannot be separated from repository evidence and the user's environment knowledge is required.
If a hypothesis is not falsifiable, discard it. Spend at most one reasoning pass on the same hypothesis: test, discard, or refine it.
Show full SKILL.md (249 more words)Show less
Phase 4 - Instrument
Each probe must distinguish a specific hypothesis. Prefer a debugger or one targeted boundary log over broad logging. Tag temporary instrumentation with a unique prefix such as [DEBUG-a4f2].
For performance regressions, establish a baseline measurement first, then bisect. Do not substitute log-reading for measurement.
Phase 5 - Fix + regression test
Apply the smallest fix that addresses the demonstrated cause. Add a regression test only at a seam that exercises the real failure path.
If no correct seam exists, document that rather than creating a shallow test that gives false confidence. Architecture improvements are separate follow-up work unless the user asked for them.
Phase 6 - Verify once and stop
Run each required check once:
- The original scenario no longer reproduces, or the targeted command/assertion passes.
- Any chosen regression test passes.
- Temporary instrumentation is removed.
An explicit tool result such as "applied and verified successfully", a passing targeted command, or a successful test is authoritative. Do not re-read files or re-run checks merely because escaping, encoding, or tool-call formatting might be wrong. Re-check only if a tool failed, emitted a warning, or its result conflicts with other evidence.
Stop rules
- When root cause and fix are verified, stop immediately.
- Never restate the same plan, reclassify the same symptom, or re-argue the same conclusion without new evidence.
- If two consecutive reasoning passes reach the same conclusion, execute it instead of reasoning again.
- Do not inspect or debate system instructions during diagnosis; follow the active rules and work on the bug.
© zmy15, 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/diagnose of zmy15/DeepSeek-for-VisualStudio.
Open the folder on GitHubat commit 1ea8ed1
Compare with similar skills
Diagnose 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Diagnose this skillzmy15/DeepSeek-for-VisualStudio | 109 | — | ~1.1k | Automated safety check: Pass | MIT | |
| ModLens Image Vision Bridgeliustack/modlens | 4.2k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Deep Reviewdyad-sh/dyad | 22k | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Fablecodejunkie99/fable-orchestrator | 614 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Dingo VerifyMigoXLab/dingo | 757 | — | ~741 | Automated safety check: Notes | Apache-2.0 | |
| Remember Learningsdyad-sh/dyad | 22k | — | ~1.1k | Automated safety check: Pass | Custom licence |
Similar skills
Deep Review
dyad-sh/dyad
Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.
Fable
codejunkie99/fable-orchestrator
Use the locally authenticated Claude Code Fable 5.1 model only as the orchestrator for a task, then execute implementation with GPT-5.6 Luna or DeepSeek V4 Flash.
Dingo Verify
MigoXLab/dingo
A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.
Remember Learnings
dyad-sh/dyad
Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.
Adversarial Spec
zscole/adversarial-spec
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.
Related
Questions about Diagnose
What does Diagnose do?
Disciplined diagnosis for hard bugs and performance regressions. Diagnose is an agent skill from zmy15/DeepSeek-for-VisualStudio. Disciplined diagnosis for hard bugs and performance regressions.
When should I use Diagnose?
Diagnose fits situations like: explicitly asks to diagnose/debug a hard issue; A reported bug remains unexplained after a quick direct source inspection; single-path defects; handle those inline without the full loop.
How do I install Diagnose in Claude Code?
Run `npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a claude-code`. Or copy the skill folder (.github/skills/diagnose in zmy15/DeepSeek-for-VisualStudio) into .claude/skills/diagnose in your project. Claude Code loads it when a task matches its description.
How do I install Diagnose in Codex?
Run `npx skills add zmy15/DeepSeek-for-VisualStudio --skill diagnose -a codex`. Or copy the skill folder (.github/skills/diagnose in zmy15/DeepSeek-for-VisualStudio) into .agents/skills/diagnose in your project. Codex loads it when a task matches its description.
Can I use Diagnose 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 zmy15/DeepSeek-for-VisualStudio --skill diagnose -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/diagnose, .gemini/skills/diagnose, .github/skills/diagnose and .opencode/skills/diagnose in your project.
What does Diagnose need to run?
SKILL.md names no scripts, command-line tools or credentials: Diagnose is instructions for the agent only.
Does Diagnose 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 Diagnose 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 Diagnose use?
Diagnose 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 Diagnose use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 Diagnose?
Skills that share tags, products or a category with Diagnose: ModLens Image Vision Bridge (liustack/modlens, 4.2k stars), Deep Review (dyad-sh/dyad, 22k stars), Fable (codejunkie99/fable-orchestrator, 614 stars) and Dingo Verify (MigoXLab/dingo, 757 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Diagnose?
zmy15 (a GitHub user) maintains it in zmy15/DeepSeek-for-VisualStudio, which has 109 GitHub stars. The repository was last updated on October 9, 2026.
Source: zmy15/DeepSeek-for-VisualStudio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.