agentleFS
iwesysiwesys/IWE/.claude/skills/platform-bottleneck/SKILL.md

platform-bottleneck

Skill0 starsChanged 25 days agoMITView on GitHub

IWE Skill — see file body

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Skill: /platform-bottleneck

Alias. Delegates to /bottleneck-pick --layer platform.

Decision (S-46, 2026-05-21): two skills (intra + platform) merged into one via the --layer parameter. A separate skill is redundant. Kept as a convenience trigger.

SC: DP.SC.152. Owner: DP.ROLE.054.

When to use

IWE Skill — see file body

Algorithm

Step 1. Parse arguments

Extract --horizon, --subsystem, and the optional --systems-map <path> from the call arguments. The map path is user data and is not part of the public Template.

Step 2. Verify the systems map

Before delegating, determine the root of the installed workspace (WS="${IWE_WORKSPACE:-$PWD}") and load its .iwe-paths: . "$WS/.iwe-paths". If the file is missing or IWE_TEMPLATE/IWE_WORKSPACE are empty — report that path setup is incomplete and stop. The Script lives in the nested Template, not in workspace/scripts: run bash "$IWE_TEMPLATE/scripts/check-platform-systems-map.sh"; if --systems-map is provided, append --map "<path>". Exit code 2: pass the script's diagnostic output to the user and stop — do not build analysis on an incomplete map. A successful call prints the verified path from the workspace; pass exactly that path to the next step as a single argument.

Step 3. Delegate to /bottleneck-pick

Without --subsystem:

/bottleneck-pick --target c2:platform --layer platform --systems-map "<verified_path>" [--horizon <h>]

With --subsystem:

/bottleneck-pick --target c2:platform --layer platform --subsystem <s> --systems-map "<verified_path>" [--horizon <h>]

Step 4. Return the result

The result of /bottleneck-pick is passed to the pilot without modification.

Full documentation

→ /bottleneck-pick SKILL.md (section --layer=platform) → DP.SC.152 (platform-specific analysis promise)

<!-- USER-SPACE --><!-- /USER-SPACE -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.