How do I install the Prime Context skill?

Run npx skillmds@latest add kdoronin/prime-context in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prime Context safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prime Context?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prime Context free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Prime Context?

kdoronin (@kdoronin) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prime Context by kdoronin — Agent Skill

Name: Prime Context
Author: kdoronin

Prime Context

Use before starting pipeline work on a Ready feature the agent hasn't worked yet. Triggers — "engineer plugin -> prime-context skill", "prime context", "load context before we start", "get up to speed on feature X".

kdoronin 069fab6 2.1 KB Updated Sep 17, 2026

File contents

prime-context

Load working memory before pipeline work on a Ready feature — the convergent counterpart to discuss. Forked from superpowers:brainstorming but inverted: no exploration, just loading and orienting. Produces no artifact.

When to use

A prep step (not a checkpoint) between feature-init and discover-acs, on any feature the agent hasn't already worked this session.

Skip when: the agent just created the feature this session (context already warm). Not for: exploring whether a feature is worth doing (discuss).

Workflow

Resolve + locate — resolve the methodology root + manifest via ${PLUGIN_ROOT}/scripts/dae_resolve.py (see references/resolving.md); locate the feature (slug arg or branch name). Reject if no folder / no feature.md.
Silent batch load — without narrating: feature.md, CHARTER.md, manifest.yml, prior handoffs/ (especially the originating *-discuss.md), and the files named in feature.md's "Related code / design pointers".
Orient — give a concise summary: outcome, scope, autonomy level (+ charter cap), key prior decisions, related code, relevant ADRs.
One prompt — ask exactly one question: anything else to load? If the user names a new code pointer, load it and offer to add it to feature.md. Then stop — prime-context orients, it does not interview.
Handoff — emit a summary.

Re-invocation re-loads fresh (no incremental diffing).

Handoff

Emit per ${PLUGIN_ROOT}/references/handoff-summary.md. checkpoint: null; artifacts: []; human_action_needed: no; recommended_next: "engineer plugin -> discover-acs skill".

References

Foundation Design — feature.md schema
Discuss & Upstream Funnel — methodology_root resolution

---name: prime-contextdescription: Use before starting pipeline work on a Ready feature the agent hasn't worked yet. Triggers — "engineer plugin -> prime-context skill", "prime context", "load context before we start", "get up to speed on feature X".---# prime-contextLoad working memory before pipeline work on a Ready feature — the convergent counterpart to `discuss`. Forked from `superpowers:brainstorming` but inverted: no exploration, just loading and orienting. Produces no artifact.## When to useA prep step (not a checkpoint) between `feature-init` and `discover-acs`, on any feature the agent hasn't already worked this session.**Skip when:** the agent just created the feature this session (context already warm). **Not for:** exploring whether a feature is worth doing (`discuss`).## Workflow1. **Resolve + locate** — resolve the methodology root + manifest via `${PLUGIN_ROOT}/scripts/dae_resolve.py` (see `references/resolving.md`); locate the feature (slug arg or branch name). Reject if no folder / no `feature.md`.2. **Silent batch load** — without narrating: `feature.md`, `CHARTER.md`, `manifest.yml`, prior `handoffs/` (especially the originating `*-discuss.md`), and the files named in `feature.md`'s "Related code / design pointers".3. **Orient** — give a concise summary: outcome, scope, autonomy level (+ charter cap), key prior decisions, related code, relevant ADRs.4. **One prompt** — ask exactly one question: anything else to load? If the user names a new code pointer, load it and offer to add it to `feature.md`. Then stop — prime-context orients, it does not interview.5. **Handoff** — emit a summary.Re-invocation re-loads fresh (no incremental diffing).## HandoffEmit per `${PLUGIN_ROOT}/references/handoff-summary.md`. `checkpoint: null`; `artifacts: []`; `human_action_needed: no`; `recommended_next`: "engineer plugin -> discover-acs skill".## References- [Foundation Design](https://www.notion.so/3585ecdee0e2811bbc67ff4913c03207) — feature.md schema- [Discuss & Upstream Funnel](https://www.notion.so/35a5ecdee0e281eaa35fced0c4e23384) — methodology_root resolution

Frequently asked questions