Optimize Skill

<!-- SPDX-License-Identifier: Apache-2.0
     https://www.apache.org/licenses/LICENSE-2.0 -->

<!-- Placeholder convention (see AGENTS.md#placeholder-convention-used-in-skill-files):
     <project-config> → adopting project's `.apache-magpie/` directory
     <tracker>        → value of `tracker_repo:` in <project-config>/project.md
     <upstream>       → value of `upstream_repo:` in <project-config>/project.md
     <framework>      → `.apache-magpie/apache-magpie` in adopters; `.` in
                        the framework standalone -->

optimize-skill

<!-- BEGIN MAGPIE PREFLIGHT — generated from tools/dev/preflight-block.md -->

Pre-flight — is this project set up?

Do this first, before anything else in this skill, and do it silently. One command answers it and carries its own rules; there is nothing else to read.

Run the checker with this skill's own frontmatter name: and surface_hash:, and one --requires for each requires_config: entry:

PYTHONPATH=".apache-magpie-local:$(git rev-parse --git-common-dir)/../.apache-magpie-local:$(git rev-parse --git-common-dir)/apache-magpie" \
  python3 -m setup_preflight --skill <name> --hash <surface_hash> [--requires <file>]...

The path finds the checker /magpie-setup config installed in the personal layer: this checkout's .apache-magpie-local/, the main checkout's when this is a linked worktree, or the git directory's apache-magpie/ when Magpie is only installed.

• {"verdict": "ok"} → silent. Continue into the work the user asked for and say nothing about pre-flight. This is the ordinary answer.
• {"verdict": "action", ...} → each finding names a section, and rules carries that section's text. Follow it. The facts are the inputs; what to propose, and what may not be done, are in the rules rather than here. Act on a finding only through its rules.
• The command did not run at all — no such module, a non-zero exit, no python3 — → never read that as a pass, and do not re-derive the check by hand: it lives in code so that there is one version of it. If the project has no .apache-magpie.lock, .apache-magpie-overrides/, or personal layer (any of the three directories above), nothing has been set up here and there is nothing to reconcile — resolve this skill's requires_config: entries yourself (first match wins: .apache-magpie-local/<file>, the main checkout's .apache-magpie-local/<file>, <git-common-dir>/apache-magpie/<file>, then .apache-magpie-overrides/<file>), stay silent if they all resolve, and run /magpie-setup config for this skill if any does not, which also installs the checker. Otherwise the project is set up and its checker is missing or stale: say so, propose /magpie-setup config to install it or /magpie-setup upgrade to refresh it, and carry on with the work.

Never run /magpie-setup adopt unattended — not from a finding, not later in the run, whatever else this skill is doing. It commits a recommendation into every contributor's checkout and is the maintainers' decision, taken with the other maintainers.

Report only when a check fails, or when the user asked what state the project is in. /magpie-setup verify is the full diagnostic.

<!-- END MAGPIE PREFLIGHT -->

Make an existing skill leaner without changing its behavior.

The first six passes preserve instruction wording while moving, rewiring, or extracting content: five live in patterns.md, with extract-code below. The seventh, rewrite.md, changes wording with the maintainer writing each paragraph and teaching the skill their style.

The validator must be green before and after an approved pass. For a new skill, use write-skill.

This skill reads only framework files, so the external-content rules do not apply to it.

What counts as small enough

Measure two budgets, set from the catalogue median when this skill was written. A skill over either target is an outlier.

Measure both before Step 1 and again at Step 4:

uv run --project tools/skill-token-count skill-token-count --write

Prioritize the always-on budget. The body costs only when invoked; frontmatter costs in every session for every skill.

Reference baseline: 75 skills; body median 4,614 tokens, p90 10,613, largest 28,346; always-on median 200, largest 398. PRINCIPLES.md P15's 500-line structural cap still applies.

Report both numbers in Step 5 whether or not the pass moved them.

Inputs

• Target — a skill name, directory, or SKILL.md path.
• --all or over:<N> — diagnose and rank every skill without editing; the default threshold is the 500-line P15 cap.
• pass:<name> — restrict diagnosis to named passes; otherwise propose every applicable pass.

With no target or selector, diagnose everything read-only and let the maintainer choose.

Prerequisites

uv runs the validator; stop if it is unavailable. Use git to isolate the diff, preferably on a clean tree or branch. Use doctoc when headings move, or report the manual step if it is unavailable.

Step 0 — Check the ground

Resolve the target to a real skill directory and require a green validator before editing. Hand back baseline failures for correction; optimization starts from a working skill. Keep the diff isolated and reviewable.

Step 1 — Diagnose

Run every diagnostic in patterns.md and report one row per smell: the pass that addresses it, the evidence (path:line, line count, the construct), and how big a change it implies. Read-only.

The smells, in the order their passes apply:

1. Oversized body — past the 500-line cap, or one section dominating. → split
2. Concrete names — adopter-specific values baked in instead of resolved from <project-config>. → config-lift
3. Bulk reads — pulling a whole issue or artefact into context to touch one field. → out-of-context
4. Per-item round-trips — N sequential fetches that could be one batch. → fetch-upfront
5. No cheap pre-filter — spending a model pass on items a deterministic check would skip. → preflight-classifier
6. Embedded code — shell or Python living inside the body, paid for on every invocation although a model never needs to read it. → extract-code
7. Verbose prose — the structure is right and the body still reads twice as long as it needs to. → rewrite, see rewrite.md

For a sweep, rank by cap overflow times distinct smells and stop there.

Step 2 — Propose

Propose applicable passes from lowest to highest blast radius: file move, content lift, tool rewire, then rewrite because only it changes wording. For each pass, name the files, expected delta, and guarantee from patterns.md.

Propose only. The maintainer picks which passes run, and in what order.