Source profileQuality 93/100

event4u-app/agent-config/src/skills/copilot-agents-optimization/SKILL.md

copilot-agents-optimization

Use when optimizing AGENTS.md or copilot-instructions.md — deduplicates against .augment/ content, enforces line budgets, and focuses each file on its audience.

Source repository stars
7
Declared platforms
0
Static risk flags
0
Last source update
2026-07-28
Source checked
2026-07-28

Decision brief

What it does—and where it fits

md or copilot-instructions. md — deduplicates against .

Best for

  • Running /docs-optimize to refactor AGENTS.md and copilot-instructions.md
  • Adding new content to either file and needing to check if it belongs there
  • After changes to .augment/ (new skills, rules, guidelines) that may make content in these files redundant

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/copilot-agents-optimization"
Safe inspection promptEditorial

Inspect the Agent Skill "copilot-agents-optimization" from https://github.com/event4u-app/agent-config/blob/0adf49a8ae84b0ff6e2de8759eea43257e020eff/src/skills/copilot-agents-optimization/SKILL.md at commit 0adf49a8ae84b0ff6e2de8759eea43257e020eff. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Procedure: Optimize copilot/agents files

    Before changing anything, read and understand:

    Read AGENTS.md — current content, line count, what's duplicated vs. unique.Read .github/copilot-instructions.md — same analysis.Scan .augment/ — which skills, rules, and guidelines already cover topics from the files above.
  2. 02

    .github/copilot-instructions.md — Self-Contained for Copilot

    What belongs here: - Architecture rules (thin controllers, service layer, policies) - PHP 8.2 patterns (readonly, final, enums — with exceptions) - Project-specific conventions (custom helpers, environment config, naming) - Code review scope and comment behavior rules - Language…

    Architecture rules (thin controllers, service layer, policies)PHP 8.2 patterns (readonly, final, enums — with exceptions)Project-specific conventions (custom helpers, environment config, naming)
  3. 03

    When to use

    Use this skill when: - Running /docs-optimize to refactor AGENTS.md and copilot-instructions.md - Adding new content to either file and needing to check if it belongs there - After changes to .augment/ (new skills, rules, guidelines) that may make content in these files redundan…

    Running /docs-optimize to refactor AGENTS.md and copilot-instructions.mdAdding new content to either file and needing to check if it belongs thereAfter changes to .augment/ (new skills, rules, guidelines) that may make content in these files redundant
  4. 04

    0. Analyze current state

    Before changing anything, read and understand:

    Read AGENTS.md — current content, line count, what's duplicated vs. unique.Read .github/copilot-instructions.md — same analysis.Scan .augment/ — which skills, rules, and guidelines already cover topics from the files above.
  5. 05

    AGENTS.md — Project Entry Point for AI Agents

    What belongs here: - Tech stack and framework versions - Development setup (Docker, Make targets, env files) - Database and multi-tenancy setup - Testing framework, suites, and conventions - Quality tool commands (PHPStan, Rector, ECS) - Project structure overview (brief, link t…

    Tech stack and framework versionsDevelopment setup (Docker, Make targets, env files)Database and multi-tenancy setup

Permission review

Static risk signals and limitations

No configured static risk pattern was detected

This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score93/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars7SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
event4u-app/agent-config
Skill path
src/skills/copilot-agents-optimization/SKILL.md
Commit
0adf49a8ae84b0ff6e2de8759eea43257e020eff
License
MIT
Collected
2026-07-28
Default branch
main
View the original SKILL.md

Copilot & AGENTS Optimizer Skill

When to use

Use this skill when:

  • Running /docs-optimize to refactor AGENTS.md and copilot-instructions.md
  • Adding new content to either file and needing to check if it belongs there
  • After changes to .augment/ (new skills, rules, guidelines) that may make content in these files redundant
  • When either file exceeds the line budget

Do NOT use when:

  • Writing application code
  • Creating new skills or commands

Procedure: Optimize copilot/agents files

0. Analyze current state

Before changing anything, read and understand:

  1. Read AGENTS.md — current content, line count, what's duplicated vs. unique.
  2. Read .github/copilot-instructions.md — same analysis.
  3. Scan .augment/ — which skills, rules, and guidelines already cover topics from the files above.
  4. Identify duplication — what content exists in both AGENTS.md and .augment/?

Only after this analysis, proceed with optimization.

AGENTS.md — Project Entry Point for AI Agents

PropertyValue
AudienceAugment Agent, other AI agents
Can read .augment/?✅ Yes — can follow references
Line budgetMax 1000, ideal ≤ 500
PurposeProject-specific setup, Docker, testing, quality tools

What belongs here:

  • Tech stack and framework versions
  • Development setup (Docker, Make targets, env files)
  • Database and multi-tenancy setup
  • Testing framework, suites, and conventions
  • Quality tool commands (PHPStan, Rector, ECS)
  • Project structure overview (brief, link to module docs)
  • Agent infrastructure overview (layer table, key references)

What does NOT belong here:

  • Coding standards (→ .augment/rules/ and .augment/guidelines/)
  • Architecture principles like SOLID, KISS, DRY (→ .augment/rules/architecture.md)
  • PHP conventions (→ ../../../docs/guidelines/php/)
  • Scope control rules (→ .augment/rules/scope-control.md)
  • Language/tone rules (→ .augment/rules/language-and-tone.md)
  • Detailed module documentation (→ app/Modules/README.md)

.github/copilot-instructions.md — Self-Contained for Copilot

PropertyValue
AudienceGitHub Copilot (Code Review bot + Chat)
Can read .augment/?❌ Code Review cannot, ✅ Chat can
Line budgetMax 1000, ideal ≤ 500
PurposeCoding standards, review rules, architecture constraints

What belongs here:

  • Architecture rules (thin controllers, service layer, policies)
  • PHP 8.2 patterns (readonly, final, enums — with exceptions)
  • Project-specific conventions (custom helpers, environment config, naming)
  • Code review scope and comment behavior rules
  • Language rules (English comments, bilingual PR comments)
  • Known issues / false positives that Copilot should avoid
  • Package management rules

What does NOT belong here:

  • Docker setup or Make targets (Copilot doesn't run commands)
  • Testing setup details (Copilot doesn't run tests)
  • Agent infrastructure (Copilot doesn't use agents/)
  • Things auto-enforced by ECS/Rector (code style, formatting, trailing commas)
  • Detailed pattern documentation (too long, Copilot needs concise rules)

Deduplication Strategy

Rule: Content lives in ONE canonical place

.augment/rules/         ← Canonical for behavior rules
.augment/guidelines/    ← Canonical for coding conventions
.augment/skills/        ← Canonical for domain expertise
agents/                 ← Canonical for project-specific docs

When duplication is acceptable

copilot-instructions.md must duplicate essential rules because Copilot Code Review cannot read other files. But keep duplicated content:

  • Concise — one-liner summaries, not full explanations
  • Focused — only what Copilot needs for code suggestions and PR reviews
  • Stable — rules that rarely change (architecture, naming, key conventions)

When duplication is NOT acceptable

AGENTS.md should never duplicate .augment/ content because Augment Agent can read both. Instead, reference with a table:

| What | Where |
|---|---|
| PHP coding rules | `.augment/rules/php-coding.md` |
| Controller guidelines | `../../../docs/guidelines/php/controllers.md` |

Line Budget Enforcement

File🟢 Good🟡 Warning🔴 Over budget
AGENTS.md≤ 500501–800> 1000
copilot-instructions.md≤ 500501–800> 1000

Reduction strategies (when over budget)

  1. Extract to agents/ — Move project-specific details to dedicated files in agents/ and link from AGENTS.md (e.g., agents/reference/docs/database-setup.md, agents/reference/docs/testing.md)
  2. Remove duplicates — If content exists in .augment/, remove from AGENTS.md
  3. Condense — Turn verbose explanations into concise tables or bullet points
  4. Remove ECS/Rector-enforced rules — From copilot-instructions.md (auto-fixed anyway)
  5. Move examples to guidelines — Detailed code examples belong in .augment/guidelines/

Portability and Stack Coherence

Duplication is not the only way these files go wrong. They also lie about the project over time:

  • Legacy identifiers — references to a former repo name, a sibling project in the same monorepo, or content that was copied from another codebase as a starting template and never adapted.
  • Stack drift — the file claims "Laravel 11 + MariaDB" but the repo was converted to a Python library; or it names Docker services that no longer exist.
  • Dead commandsmake start in the docs, but Makefile no longer has that target.

Before deduplicating, run three scans:

  1. Legacy identifier scan — compare both files against the package's FORBIDDEN_IDENTIFIERS blocklist (see scripts/check_portability.ts) plus any project names from agents/ module docs that don't match the current project.
  2. Stack coherence scan — auto-detect the actual stack from composer.json / package.json / pyproject.toml / etc. and flag any claim that no longer matches reality.
  3. Dead-command scan — verify every make X, task X, composer X, php artisan X, or npm X still resolves.

Every hit from scan 1 is a 🔴 blocker: leaking another project's name into a consumer's own docs is the failure mode this skill exists to prevent. Fix or remove those BEFORE any dedup/condense work — there's no point deduplicating content that is about to be rewritten.

When the drift is severe (whole sections are wrong), recommend /agents init to scaffold a clean replacement rather than patching forever.

agent-config Path Conventions — Preserve, Don't "Fix"

copilot-instructions.md ships a "Known False Positives" section that tells Copilot Code Review not to flag agent-config path patterns as broken. When optimizing, keep that section intact — never delete it as "redundant" and never trim its bullets. The patterns it covers:

  • Relative cross-references inside .augment/ rules / skills (../docs/guidelines/foo.md, ../contexts/bar.md) — paths resolve from the file's delivered location, not from the symlink in .claude/rules/ etc. (per road-to-path-fixes.md Strategy A).
  • path_prefix: triggers containing .agent-src.uncondensed/ — literal match patterns, not file refs (per Modified Option 1, P2.2).
  • Symlinked rule files under .claude/rules/, .cursor/rules/, .clinerules/ — targets resolve into .augment/rules/.

If the consumer project's copilot-instructions.md is missing the section, add it during optimization using the canonical block from .augment/templates/copilot-instructions.md. Surfaces include /agents init and /agents optimize.

Optimization Checklist

When optimizing either file, check:

  • "Known False Positives" section present and unmodified?
  • No identifiers from other projects (FORBIDDEN_IDENTIFIERS blocklist)?
  • Tech stack claims match actual project dependencies?
  • All referenced commands/targets exist (Makefile, composer scripts, artisan, task)?
  • Line count within budget?
  • No content duplicated with .augment/rules/?
  • No content duplicated with .augment/guidelines/?
  • No content duplicated between the two files unnecessarily?
  • AGENTS.md references .augment/ instead of duplicating?
  • copilot-instructions.md is self-contained for Code Review?
  • No ECS/Rector-enforced rules in copilot-instructions.md?
  • Project structure is brief (link to module docs for details)?
  • All sections still relevant (no outdated references)?
  • Cross-references to agents/ docs are valid?

Related

  • Command: /agents optimize
  • Skill: copilot-config — Copilot behavior and PR review patterns
  • Skill: agent-docs-writing — documentation hierarchy
  • Context: augment-infrastructure.md — full .augment/ overview

Output format

  1. Optimized file(s) with deduplication applied and line budget respected
  2. Summary of what was removed, moved, or consolidated
  3. Line count before/after for each file

Gotcha

  • AGENTS.md is read by GitHub Copilot and other tools — changes affect all AI assistants, not just Augment.
  • Don't remove content from AGENTS.md that other tools depend on — verify cross-tool compatibility first.
  • The model tends to over-optimize by removing "obvious" content that other models actually need.

Do NOT

  • Do NOT add content to AGENTS.md that belongs in .augment/ files.
  • Do NOT exceed the recommended line budget for copilot-instructions.md.
  • Do NOT duplicate rules between AGENTS.md and .augment/rules/.

Auto-trigger keywords

  • AGENTS.md optimization
  • copilot-instructions
  • deduplication

Alternatives

Compare before choosing

Computed 10042,015

coreyhaines31/marketingskills

ab-testing

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

Computed 10042,015

coreyhaines31/marketingskills

churn-prevention

When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o

Computed 997

event4u-app/agent-config

design-review

Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.

Computed 9831,966

K-Dense-AI/scientific-agent-skills

dask

Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.