trifecta-mcp
Use for code navigation, graph impact analysis, semantic search, and context validation via Trifecta MCP.
Skill by gentleman-programming
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fegome90-cmd-trifecta-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/trifecta-mcp
What's inside
- Skill name
trifecta-mcp- Description
- Use for code navigation, graph impact analysis, semantic search, and context validation via Trifecta MCP. Trigger: When navigating code, answering architectural questions, finding dead code, testing impact, or validating context packs.
- License
- Apache-2.0
- Metadata
- author: gentleman-programming · version: 1.0
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- guide.md · references/
SKILL.md (first lines)
## When to Use - Navigating a codebase dynamically (callers, path, impact). - Searching for semantic knowledge (`ctx_search`). - Hovering over a symbol to find types/signatures (`ast_hover`). - Validating or indexing context packs (`ctx_validate`, `ctx_reindex_graph`). - Troubleshooting code graph staleness. ## Gentle AI Governance - **Evidence-First**: Every tool call must include the "evidence" field explaining the source of the fact. - **Fidelity Monitoring**: Agents MUST check the `fidelity` field. If `degraded`, pivot to structural tools (`ctx_graph`). - **Fail-Closed**: If a tool returns an error code (e.g., -32001 for LSP), do NOT hallucinate; report the limitation. - **Spec-Anchored**: Use `ctx_plan` to verify the engineering path before mass modifications. ## Critical Patterns - **Anti-Pattern (The "One-Tool MCP")**: DO NOT default to `ctx_oracle`. The Oracle is for broad, unspecific searches. - **Structural Tools (ctx_graph)**: - Use `action="callers"` to find who calls a function before modifying it. - Use `action="callees"` to find what a function calls. - Use `action="subclasses"` or `parents` when tracing class inheritance. - Use `action="path"` to trace relationships between two specific symbols. - Use `action="orphans"` to detect dead code. - Use `action="impact"` to determine blast radius. - **AST Tools**: - Use `ast_hover` to get immediate type signatures and docstrings. - Use `ast_analyze` to extract all symbols from a single file in ~10ms. - **Context Tools**: - Use `ctx_search` for semantic queries (e.g., "where is state saved?"). - Use `ctx_get` to retrieve full chunk contents once an ID is found. - Use `ctx_validate` to verify context pack health. - Use `ctx_reindex_graph` immediately after modifying `.py` files to prevent staleness. ## Commands ```bash # This skill primarily relies on MCP tools, but CLI fallbacks include: trifecta graph callers --symbol <symbol> trifecta ctx search -q "<query>" ``` ## Resources - **Documentation**: See [references/guide.md](references/guide.md) for full usage scenarios.
From fegome90-cmd/paper-writer, Apache-2.0.
More from fegome90-cmd/paper-writer
- 0.463score
literature-search
fegome90-cmd
Búsqueda bibliográfica sistemática con ranking de calidad, descarga de PDFs y exportación estructurada.
SkillCFreshness: CClaude Code +9 - 0.404score
essay_crafter
gentleman-programming
Trigger: essay, ensayo, academic essay, claim audit, citation check, reviewer.
SkillCFreshness: CClaude Code +9 - 0.247score
academic_writer
fegome90-cmd
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- Apache-2.0
- Repository
- github.com/fegome90-cmd/paper-writer
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gentleman-programming
- 0.724score
gentleman-bubbletea
gentleman-programming
Bubbletea TUI patterns for Gentleman.Dots installer.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.723score
engram-backlog-triage
gentleman-programming
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable…
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-commit-hygiene
gentleman-programming
Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-architecture-guardrails
gentleman-programming
Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-branch-pr
gentleman-programming
PR creation workflow for Engram following the issue-first enforcement system.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-business-rules
gentleman-programming
Product and business-rule guardrails for Engram.
SkillAFreshness: A★ 7.6KClaude Code +9
Cite this page
trifecta-mcp skill. Agent Mart. https://agentmart.dev/skills/fegome90-cmd-trifecta-mcp (last updated 2026-10-24)