github-resume-assistant
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub personal access token (fine-grained with public repo access) to increase API rate limits. Optional; unauthenticated requests work with lower limits. | |
| ANTHROPIC_MODEL | No | Anthropic model name (e.g., claude-sonnet-5, claude-opus-4-8). Currently read but unused until v0.2. | |
| ANTHROPIC_API_KEY | No | Anthropic API key for Claude model access. Currently read but unused until v0.2. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_github_reposA | Fetch a GitHub user's public profile and repositories. Use this to ground resume advice in someone's real GitHub activity: it returns their profile summary plus every public repo with stars, primary language, and creation / last-push dates. Handles users with no public repositories gracefully. Args: username: The GitHub login to look up (e.g. "octocat"). |
| analyze_resumeA | Find which resume claims a GitHub profile does and doesn't back up. Extracts the strongest, most concrete claims from the resume, cross-references them against the user's real public repositories, and returns a gap report: which claims have public GitHub evidence and which are gaps to close. Handles an empty or thin GitHub gracefully — that's the common case for engineers whose work lives in private repos, and the report frames it as the gap to close. Args: resume_text: The full text of the resume to analyze. username: The GitHub login whose public repos ground the analysis. |
| suggest_projectsA | Prescribe a ranked 30-day plan of projects to make a resume credible. Builds the resume-vs-GitHub gap report, then prescribes specific, shippable projects to close the highest-value gaps: each is tied to a concrete resume claim it would prove, sized ("a weekend" / "a week"), and scoped (what to skip). This is the star tool — the prescription, not just the diagnosis. Handles an empty or thin GitHub as the main case: it prescribes what to build from scratch rather than reporting that there's nothing to show. Args: resume_text: The full text of the resume to ground suggestions in. username: The GitHub login whose public repos ground the analysis. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool serves a distinct purpose: fetching repos, analyzing resume claims, and suggesting projects. No overlap or ambiguity.
All tools follow a consistent verb_noun pattern with snake_case (analyze_resume, fetch_github_repos, suggest_projects).
With 3 tools, the server is well-scoped for its purpose—fetching data, diagnosing gaps, and prescribing projects. No unnecessary tools.
The tool set covers the full workflow: retrieving GitHub data, analyzing resume claims, and suggesting projects. No obvious missing functionality.