diagnose-docs

A skill for finding documentation problems that may have caused an AI agent to make mistakes. It uses task descriptions and, when available, grading results to identify missing, inaccurate, or unclear instructions.

In plain words
What is it for?
Use it to review failed tasks, inspect incorrect grading results, and recommend documentation changes that could prevent similar mistakes.
Why use it?
It helps explain whether an error came from the documentation rather than from the agent's execution, including cases where the agent wasted effort searching for basic information.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/madgraphteam/madagents/diagnose-docs
Any agent
npx skills add MadGraphTeam/MadAgents --skill diagnose-docs
Clone the repo
git clone --depth 1 https://github.com/MadGraphTeam/MadAgents

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.00676
Opus 5 $0.00014 $0.00338
Sonnet 5 $0.00006 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured 3d ago against content hash dd5bd2d7c9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagnose-docs 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 3d 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.

legacy/madagents_v2/claude_code/.claude/skills/diagnose-docs/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose Documentation Issues

Find documentation issues that caused or contributed to problems. Your goal is to identify what needs to change in the docs to prevent similar issues.

Input

$ARGUMENTS

If a description was given, use it as the problem to diagnose. If a file path was given (e.g. verdicts JSON), read it and extract entries where correct is false. If nothing was given, ask the user what went wrong.

If a grade file is available (e.g. /workspace/train/grade/grade.json), read it for context. When the inefficient tag is present, also look for unnecessary effort in the agent's workflow caused by doc gaps.

Documentation Scope

The docs at /madgraph_docs/ are operational reference for an expert LLM agent using MadGraph. They cover MadGraph-specific syntax, parameters, defaults, and behavior — not textbook physics. A topic is in scope if knowing it helps the agent correctly use MadGraph.

Some web search and code inspection is expected and healthy — looking up specifics about papers or model implementations is normal. Inefficiency means the agent had to search for basic operational information that the docs should provide (common commands, default values, parameter names, standard workflows).

Task

  1. Get the docs: Call get_doc_draft("/workspace/docs_check") to get a local copy you can read.

  2. For each issue:

    1. Check whether the topic is in scope for the documentation (see above).
    2. If in scope, check whether the docs cover it correctly and clearly.
    3. If the docs are missing, wrong, or ambiguous — write a finding.
    4. If the docs already cover the topic correctly — skip it (not actionable).

Rules

  • Identify root causes, not symptoms. If multiple issues stem from the same gap, write one finding.
  • Findings must be generalizable — not specific to this one question.
  • Recommendations should be practical (e.g. "note that parameter X differs between LO and NLO"), not sweeping rewrites.
  • If no issues are documentation problems, write empty lists.

Read the full file on GitHub · 73 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. 3d ago First seen · 73 lines · 28 tokens per session scan A dd5bd2d7c9fd

Subscribe to this mod's changes

diagnose-docs is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 676 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens