Skip to content
Skills Library
AI & agents · Research

open-skill-intel

/open-skill-intel

Finds facts before acting by asking the best source - how code works and where something is defined or configured (codegraph call paths, callers, impact of a change, tests that cover a diff), current library and framework docs (Context7), Claude API facts, database table schemas and columns, the web, notes the user saved earlier, and which installed skill can do a job. Use for questions like "how does this work", "where is X configured", "who calls this", "what breaks if I change it", "which tests cover my diff", "check the docs for", "which skill can", "what did I note about".

Licence
MIT
Last repository change
18.10.2026

Assessment and security

81/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content16 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 18.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Finds facts before acting by asking the best source - how code works and where something is defined or configured (codegraph call paths, callers, impact of a change, tests that cover a diff), current library and framework docs (Context7), Claude API facts, database table schemas and columns, the web, notes the user saved earlier, and which installed skill can do a job. Use for questions like "how does this work", "where is X configured", "who calls this", "what breaks if I change it", "which tests cover my diff", "check the docs for", "which skill can", "what did I note about".

Triggers from the description

how does this workwhere is X configuredwho calls thiswhat breaks if I change itwhich tests cover my diffcheck the docs forwhich skill canwhat did I note about
Original author description

Finds facts before acting by asking the best source - how code works and where something is defined or configured (codegraph call paths, callers, impact of a change, tests that cover a diff), current library and framework docs (Context7), Claude API facts, database table schemas and columns, the web, notes the user saved earlier, and which installed skill can do a job. Use for questions like "how does this work", "where is X configured", "who calls this", "what breaks if I change it", "which tests cover my diff", "check the docs for", "which skill can", "what did I note about".

How it works

SKILL.md has no level-two headings · 27 lines, 440 words

SKILL.md preview
---
name: open-skill-intel
description: Finds facts before acting by asking the best source - how code works and where something is defined or configured (codegraph call paths, callers, impact of a change, tests that cover a diff), current library and framework docs (Context7), Claude API facts, database table schemas and columns, the web, notes the user saved earlier, and which installed skill can do a job. Use for questions like "how does this work", "where is X configured", "who calls this", "what breaks if I change it", "which tests cover my diff", "check the docs for", "which skill can", "what did I note about".
---

# Open Skill Intel

Get the needed fact with the fewest calls instead of guessing. Each kind of question has a best source; guessing an API or crawling a whole repo with grep when a graph can answer are both slower and less reliable.

| Question | Source | How |
|---|---|---|
| How does this code work, where is X, trace X to Y | codegraph, when `.codegraph/` exists | MCP tool `codegraph_explore`, or `codegraph explore "<symbols or question>"` |
| Who calls X, what does X call | codegraph | `codegraph callers <symbol>`, `codegraph callees <symbol>` |
| What breaks if X changes | codegraph | `codegraph impact <symbol>` |
| Which tests cover this diff | codegraph | `git diff --name-only \| codegraph affected --stdin` |
| Which other parallel session my change reaches | Graphify, when `graphify-out/` exists | `open-skill session update --session <id> --json`; declare the session first with `open-skill session start --scope <glob> --task "..."` |
| Repo has no `.codegraph/` | Grep, Glob, Read | Mention once that `codegraph init` would help; indexing is the user's decision |
| SQL, dbt or notebook repos | Grep by table or model name | codegraph does not index SQL |
| Library or framework API | Context7 | The Context7 skill or MCP tool, for the version the project uses |
| Claude models, pricing, limits, SDK usage | The `claude-api` skill | Never from memory; these change often |
| Table schema, columns, sample rows | The project's database connector | `DESCRIBE` / `INFORMATION_SCHEMA` first, samples with `LIMIT`, only on tables the user named |
| Market, competitor, technical or academic research | BMad deep-recon, or web search | Cite sources |
| What the user prefers or learned before | Their knowledge | `ls ~/.open-skill/knowledge/`, or the `knowledge` field of `open-skill route` |
| Which skill can do X | The skill graph | `open-skill search "<need>"`; `open-skill doctor` for what is installed or missing |

Inside a declared session, keep Graphify answers to the session's scope and report files outside it as other sessions' ground; keep codegraph for call-level questions in TypeScript, since Graphify misses calls made through a namespace import (ns.fn()).

Stop at the first source that answers; check a second one only when sources disagree or the fact is about to decide something hard to undo. Answer briefly with the source of each fact (file and line, table, URL). If the answer decides the next step, say what it is, or hand back to `open-skill-router`.

`open-skill` means the CLI; if it is not on PATH use `uvx --from git+https://github.com/VoKhoiNhon/open-skill-standard@v0.7.5 open-skill`.

Versions

The database has no other skills named open-skill-intel.

Database snapshot: 13.11.2026 · package version 69e6c73a29e0 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 82axiomcode
    Use for any why, what or where question about code — how a codebase works, where something lives, who calls it, what a change to it breaks, which tests cover an edit. Also use when resolving an issue or bug report, which names a symptom rather than a file. Examples: "How does X…
  • 90docs-lookup
    Get facts from live official docs through docs MCP connectors, not WebFetch or web search: Claude Code, claude.ai/Cowork, Claude API, MCP, ACP, OpenAI/Codex, xAI/Grok, plus any docs connector the session has. Use whenever a doc fact matters: answering, building, reviewing or debugging.
  • 100glia
    Answer structural questions about a codebase with the glia CLI, no MCP server needed. Use it for where X is defined, what changing X (or a diff) affects, how feature Y flows across services, what calls, serves or implements X, what X writes or sends, which tests cover a change,…
  • 90codegraph-partner
    Use when the user explicitly mentions codegraph, asks structural code questions such as callers/callees/impact, asks where a symbol is defined, asks what breaks if a symbol changes, or asks for an architectural overview of a code repository. Skip for prose-only or vault-only questions.
  • 100ask-claude
    Recommend the best way to have Claude do something, checked against Anthropic's current docs, then write the prompt and run it once approved. Use when someone asks how they should prompt you, what the best way to ask for something is, or which Claude feature fits a job…
  • 100code-intel
    Pick the right code-graph tool for the current repo (GitNexus for code-heavy repos, Graphify when docs, PDFs or notes matter as much as code), index it, and document the choice in AGENTS.md. Use when the user runs /kit:code-intel, at the end of /kit:kickoff, when an AGENTS.md…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.