agentleFS
Sign inStart free
DemonDamonDemonDamon/AgenticX/.cursor/skills/code-deep-research/SKILL.md

code-deep-research

Skill1k starsChanged 17 days agoApache-2.0View on GitHub

Use when deeply researching an open-source GitHub repository for AgenticX adoption, selective mechanism internalization, gap analysis, or an evidence-backed implementation proposal.

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the DemonDamon/AgenticX repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about DemonDamon/AgenticX

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use for:

    line 20
  2. Distinctive:

    Before taking research actions:

    line 27
  3. Distinctive:

    Read TEMPLATES.md before creating research artifacts.

    line 31
  4. Distinctive:

    Do not infer the workflow from this summary alone.

    line 33
  5. Very specific:

    Verify implementation claims against local source using SHA + path + line range + symbol.

    line 39
  6. Very specific:

    Do not modify AgenticX production code during research.

    line 42
  7. Distinctive:

    Do not invent benchmarks, user needs, issue numbers, runtime validation, or repository behavior.

    line 43
  8. Distinctive:

    Do not create an implementation plan or code task unless the user separately requests implementation.

    line 44
  9. Distinctive:

    Do not promote a Gap to force a desired verdict.

    line 54
  10. Distinctive:

    Only claim completion when S0–S7 are completed or legitimately skipped, all quality gates in WORKFLOW pass, and S8 is then marked complete.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Deep Research

Overview

Research an upstream repository from a locked commit, compare it with verified AgenticX code, and make an evidence-backed adoption decision. The local upstream clone is the source of truth; MCP tools accelerate discovery but never replace source verification.

When to Use

Use for:

  • /codedeepresearch requests.
  • “调研这个 GitHub 项目能否集成进 AgenticX”。
  • Comparing an upstream framework, SDK, agent runtime, tool, memory, planner, UI, or protocol with AgenticX.
  • Producing ADOPT, SELECTIVE_ADOPT, or DO_NOT_ADOPT recommendations.

Do not use for:

  • Implementing an already-approved plan.
  • General web research without a required GitHub repository.
  • A quick API lookup or a review of one known source file.

Required References

Before taking research actions:

  1. Read WORKFLOW.md completely.
  2. Copy its S0–S8 status ledger into research/codedeepresearch/<repo_name>/meta.md.
  3. Read TEMPLATES.md before creating research artifacts.

Do not infer the workflow from this summary alone.

Non-Negotiable Rules

  • Clone the repository into research/codedeepresearch/<repo_name>/upstream/ and lock its SHA.
  • A failed clone blocks normal research. Do not emit Gap, Proposal, P0/P1, or an adoption verdict.
  • Verify implementation claims against local source using SHA + path + line range + symbol.
  • DeepWiki, GitHub MCP, and ZRead are optional accelerators. Discover their schemas before use; failure must follow the documented fallback.
  • ZRead quota failure never makes a successful local-source study “incomplete”.
  • Do not modify AgenticX production code during research.
  • Do not invent benchmarks, user needs, issue numbers, runtime validation, or repository behavior.
  • Do not create an implementation plan or code task unless the user separately requests implementation.

Decision Rule

Determine Gap priority first, then derive the verdict:

  • ADOPT: at least one valid P0.
  • SELECTIVE_ADOPT: no P0, but at least one evidence-backed P1 with a real user problem.
  • DO_NOT_ADOPT: only P2/NO-GAP, unvalidated demand, or insufficient value.

Do not promote a Gap to force a desired verdict.

Completion Rule

Only claim completion when S0–S7 are completed or legitimately skipped, all quality gates in WORKFLOW pass, and S8 is then marked complete. Final chat output must lead with the verdict and link the written artifacts.

Common Failures

  • Starting with DeepWiki instead of locking the upstream SHA.
  • Treating README or MCP-generated code as implementation evidence.
  • Reading only upstream code and assuming AgenticX lacks the capability.
  • Turning every upstream feature into a P0.
  • Forcing PoC/MVP sections when the correct verdict is DO_NOT_ADOPT.
  • Leaving stale evidence from an older upstream SHA in current artifacts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free