pco-routing
Use when deciding which PCO files, sections, concepts, or workflows to load for a task.
Skill by Sigit-AP
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/sigit-ap-pco-routing
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: productivity
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/pco-routing
What's inside
- Skill name
pco-routing- Description
- Use when deciding which PCO files, sections, concepts, or workflows to load for a task.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Procedure 1. Run the executable reference runtime: ```bash node references/runtime/pco-reference-runtime.mjs route "<task>" --limit 8 --depth 1 ``` 2. For deeper context, generate an embedded context block: ```bash node references/runtime/pco-reference-runtime.mjs context "<task>" --limit 8 --depth 1 ``` 3. If the task is subsystem-specific, use that folder runtime: ```bash node references/workflows/runtime.mjs route "<task>" node references/quality-safety/runtime.mjs route "<task>" node references/cognitive-engines/runtime.mjs route "<task>" ``` 4. Load selected startup files first. 5. Expand with runtime neighbors, concepts, axes, and section IDs. 6. Use `.pco/cache/*.json` only as compatibility output when a harness cannot import/run the executable runtime. ## Routing Discipline Never route only by filename. Route by: ```text task intent → axis → workflow → concept → dependency → graph neighbor → section ``` ## Failure Modes - If route is ambiguous, choose `any-professional-task`. - If concept match is weak, load core + quality-safety + workflow index. - If graph has too many neighbors, sort by weight and load top 5 first.
From Sigit-AP/Pure-Cognitive-Oil, MIT.
More from Sigit-AP/Pure-Cognitive-Oil
- 0.471score
pco-verification
Sigit-AP
Use before claiming a PCO task is complete, especially after changing scripts, mappings, hooks, skills, or generated context.
SkillCFreshness: CClaude Code +9 - 0.470score
finishing-a-development-branch-with-pco
Sigit-AP
Use when performing finishing a development branch work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
subagent-driven-development-with-pco
Sigit-AP
Use when performing subagent driven development work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
writing-plans-with-pco
Sigit-AP
Use when performing writing plans work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
using-git-worktrees-with-pco
Sigit-AP
Use when performing using git worktrees work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
verification-before-completion-with-pco
Sigit-AP
Use when performing verification before completion work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
using-pco
Sigit-AP
Use when starting any serious task or whenever PCO resources may apply; bootstraps deterministic cognitive routing before action.
SkillCFreshness: CClaude Code +9 - 0.470score
brainstorming-with-pco
Sigit-AP
Use when performing brainstorming work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
dispatching-parallel-agents-with-pco
Sigit-AP
Use when performing dispatching parallel agents work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
executing-plans-with-pco
Sigit-AP
Use when performing executing plans work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
receiving-code-review-with-pco
Sigit-AP
Use when performing receiving code review work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
requesting-code-review-with-pco
Sigit-AP
Use when performing requesting code review work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 29, 2026 (5 months ago)
- Last release
- May 28, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Sigit-AP/Pure-Cognitive-Oil
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Sigit-AP
- 0.471score
pco-verification
Sigit-AP
Use before claiming a PCO task is complete, especially after changing scripts, mappings, hooks, skills, or generated context.
SkillCFreshness: CClaude Code +9 - 0.470score
subagent-driven-development-with-pco
Sigit-AP
Use when performing subagent driven development work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
finishing-a-development-branch-with-pco
Sigit-AP
Use when performing finishing a development branch work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
using-pco
Sigit-AP
Use when starting any serious task or whenever PCO resources may apply; bootstraps deterministic cognitive routing before action.
SkillCFreshness: CClaude Code +9 - 0.470score
brainstorming-with-pco
Sigit-AP
Use when performing brainstorming work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9 - 0.470score
dispatching-parallel-agents-with-pco
Sigit-AP
Use when performing dispatching parallel agents work with PCO routing, bounded context, evidence gates, and honest completion language.
SkillCFreshness: CClaude Code +9
Cite this page
pco-routing skill. Agent Mart. https://agentmart.dev/skills/sigit-ap-pco-routing (last updated 2026-10-24)