generate-repo-instructions

Generates the global repository constitution file (.github/copilot-instructions.md). Works for code repositories, documentation repositories, data repositories, and mixed repos. Performs LLM-driven deep repository analysis including docs, code patterns, build systems, documentation generators, and data schemas. Generates constitutional rules following context economics (under 1000 lines). Enforces positive constraints and no hardcoded secrets.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with actionable templates, explicit validation checkpoints, and clean one-level-deep progressive disclosure backed by real reference files. Its main weakness is conciseness: the Best Practices and Example Usage sections duplicate the workflow content already covered above.

Suggestions

Remove or condense the 'Best Practices' DO/DON'T list and the 'Example Usage' 14-step walkthrough, since they restate the workflow steps already detailed in Steps 1-8.

Tighten the Overview section, as repository-type coverage is already stated in the frontmatter description.

Trim the repeated reference descriptions in the Resources section to one-line pointers to avoid restating each file's contents.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the 'Best Practices' DO/DON'T list and the 14-step 'Example Usage' walkthrough largely rehash the workflow steps already detailed above, and the Overview repeats repo-type coverage from the frontmatter; it could be tightened without losing substance.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: explicit 'cat references/...' commands, a placeholder-to-source mapping table, a positive-constraint conversion table, validation checklists, 'mkdir -p .github/' and write steps, and a full confirmation-report template.	3 / 3
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints: a Step 1 decision tree with STOP conditions, a Step 4 positive-constraint checklist, and a Step 6 context-economics checklist with 'If validation fails: Trim content before writing' feedback guidance.	3 / 3
Progressive Disclosure	SKILL.md is an overview that loads four real, one-level-deep reference files (analysis_checklist.md, instruction_template.md, context_economics.md, positive_constraints_patterns.md — all present) via clearly signaled 'cat' commands and a Resources section, with content appropriately split for on-demand use.	3 / 3
	Total	11 / 12 Passed

Description

60%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and third-person with clear actions, but it lacks an explicit 'Use when...' trigger clause and leans on internal jargon over natural user terms, capping completeness and trigger quality at 2. Distinctiveness is moderate due to unspecified overlap with the path-instructions sibling skill.

Suggestions

Add an explicit 'Use when...' clause with natural phrasing, e.g. 'Use when generating or updating global Copilot instructions for a repository.'

Include common user terms such as 'copilot instructions', 'repo instructions', and 'Copilot config' rather than internal jargon like 'constitution file' or 'context economics'.

Disambiguate from the sibling skill, e.g. 'Use for repo-wide instructions; for path-scoped instructions use generate-path-instructions.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Generates the global repository constitution file', 'Performs LLM-driven deep repository analysis including docs, code patterns, build systems...', and 'Enforces positive constraints and no hardcoded secrets', matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is explicit, but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It mentions the concrete artifact '.github/copilot-instructions.md' and 'repositories', but leans on jargon ('constitution file', 'context economics', 'constitutional rules', 'positive constraints') and omits common user phrasings like 'copilot instructions' or 'repo instructions', plus it lacks a 'Use when...' clause.	2 / 3
Distinctiveness Conflict Risk	It targets a fairly specific artifact (copilot-instructions.md) with a 'global' qualifier, but the description does not disambiguate from the sibling generate-path-instructions skill, leaving overlap risk with path-scoped instruction requests.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: canonical/copilot-collections
Commit: d1b6440

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.