core-router
/core-router
Use when the user asks how to use Codex Next, which bundled skill fits, or whether a workflow is needed. Do not trigger for a clear task that can be completed directly.
- Author
- blueskyxn ↗
- Repository
- codex-is-all-you-need ↗
- Licence
- GPL-3.0
- Last repository change
- 17.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 17.09.2026, without references to retired models or APIs.
GPL-3.0, otwarta.
What it does and when to use it
Use when the user asks how to use Codex Next, which bundled skill fits, or whether a workflow is needed. Do not trigger for a clear task that can be completed directly.
Original author description
Use when the user asks how to use Codex Next, which bundled skill fits, or whether a workflow is needed. Do not trigger for a clear task that can be completed directly.
How it works
- Route Choices
- Capability Map
- Decision Rules
- Output
- Boundaries
SKILL.md preview
--- name: core-router description: Use when the user asks how to use Codex Next, which bundled skill fits, or whether a workflow is needed. Do not trigger for a clear task that can be completed directly. metadata: version: "1.0" updated: "2026-07-26" --- # Codex Next Router Treat this skill as the optional discovery entrance to Codex Next, not as a mandatory gateway. Recommend the smallest useful path and stop. Do not invoke, reproduce, or begin the recommended workflow. ## Route Choices Choose exactly one primary route: 1. **Direct execution** — no Codex Next skill is needed. 2. **One bounded skill** — the user already requested the result that skill produces, such as a PR review, HLD, weekly report, or data analysis. 3. **One explicit control workflow** — the work would introduce interrogation, persistent tracking, SDLC governance, readiness gating, change control, or multi-artifact coordination. Direct execution is a successful routing result. Do not recommend a skill only because one exists. ## Capability Map - `core-*`: optional discovery, explicit plan interrogation, goal tracking, and skill evaluation. - `dev-*`: implementation, diagnosis, review, Git, release, and focused engineering workflows. - `sdlc-*`: user-requested requirements, design, validation, traceability, and explicit SDLC control workflows. - `data-*`: bounded tabular, SQL, cleaning, and analysis-report work. - `office-*`: bounded meeting, report, briefing, weekly-report, and presentation outline outputs. - `research-*`: evidence tables, source deduplication, and synthesis from supplied or already mapped material. ## Decision Rules 1. Prefer direct work for clear, local, reversible, and verifiable requests. 2. Recommend a bounded skill only when its output matches the user's stated outcome without adding prerequisites or artifacts. 3. Do not infer that a midstream project needs BRD, PRD, SRS, HLD, RTM, readiness review, or a handoff package merely because those skills exist. 4. When a control workflow is justified, show its exact `$codex-next:<skill-name>` command and wait for the user to invoke it explicitly. Approval of the recommendation is not invocation, and authorization does not transfer from this router to another skill. 5. Ask at most one question, and only when its answer would change the primary route. Include the recommended default. ## Output Return a compact recommendation: ```markdown ## Codex Next Route - Path: direct / bounded skill / explicit control workflow - Recommendation: <no skill or one skill name> - Why: <one concrete sentence> - Avoid: <unnecessary workflow or artifact, when relevant> ``` If the path is direct, write `Recommendation: no skill; complete the task directly`. ## Boundaries - Do not call another skill or imitate its workflow. - Do not create or edit files, trackers, plans, or SDLC artifacts. - Do not run commands, spawn agents, or change Git or external state. - Do not turn ambiguity alone into an unknowns, grilling, or readiness process. - Do not return several equally weighted routes. Recommend the best path; name one alternative only when a real user decision remains.
Versions
The database has no other skills named core-router.
Database snapshot: 13.11.2026 · package version 3bfaf80e7106 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 1 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100find-me-a-skill
Suggest which skill or workflow fits a task, with model and /effort per step and paste-ready commands; runs nothing. Use for "which skill should I use", "find me a skill", "how should I run this", "what model/effort for this". - 90adlc-router
ADLC Next guide. Recommends which ADLC Next skill, if any, fits a software request, with its exact command, and stops without doing the work. Use when the user invokes $adlc-next:adlc-router or /adlc-next:adlc-router, or asks which ADLC skill or workflow fits a request. Not for… - 100skill-router
Decide which installed skill, or which chain of two or three skills, fits a task before starting it, and run them in the right order with each one's output feeding the next. Works with any set of skills, because it reads every installed skill's description at run time. Use when… - 90ask-matt
Recommends the skill or flow that fits the user's situation. A router over the skills in this repo. Use when the user asks which skill to use, is unsure what fits, or needs a pointer to the right workflow. - 85using
Router and index for the arcforge toolkit. Use when you are unsure which skill fits the work in front of you, want the shortest workflow for a task, or need a map of what this toolkit actually offers. - 86ditz-router
Use to pick which ditz-* engineering skill fits the task.