How do I install the Pkc Context skill?

Run npx skillmds@latest add spillwavesolutions/pkc-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.

What does the Pkc Context skill do?

Build a progressive-disclosure context pack for a Feature (or any concept). Supports --tiny (1 hop / 8 nodes) for chat focus and mermaid graphs. Auto-run when starting work on a Feature. It is listed under Coding & Dev Tools on SkillMD.

Is Pkc 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 Pkc 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 Pkc Context free to use?

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

Who published Pkc Context?

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

Pkc Context by spillwavesolutions — Agent Skill

Name: Pkc Context
Author: spillwavesolutions

File contents

PKC Context Pack

Auto-inject rule: When the user opens or starts work on a Feature path, the parent should spawn knowledge-retriever (/pkc-retrieve) rather than packing inline. This skill is the pack procedure the retriever (and post-capture verification) runs. Lead with DecisionRecords + originating Meetings/Experiments.

# Standard (2 hops, ~20 nodes)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pkc_pack.py" features/<slug>.md --repo . --hops 2

# Tiny / ADHD / chat (1 hop, 8 nodes)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pkc_pack.py" features/<slug>.md --tiny

# Mermaid only
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pkc_pack.py" features/<slug>.md --mermaid

# Compact card for a retriever sub-agent (no mermaid / ranked bodies)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pkc_pack.py" features/<slug>.md --tiny --summary --json

Prefer okf-plugin pack when installed. Never invent edges.

Token budget. Default is 1/4 of SECOND_BRAIN_WINDOW_TOKENS (128000 → 32000). Override with --max-tokens or SECOND_BRAIN_PACK_MAX_TOKENS. Over budget exits 1 and writes nothing. --max-nodes / --tiny clip the walk; they are not a token budget. Bodies stay off unless that node is the pack root.

Frequently asked questions

Pkc Context