CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/generate-repo-instructions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

The skill body is well-structured with a clear multi-step workflow, concrete actionable guidance, and exemplary progressive disclosure through real one-level-deep references. Its main weakness is mild verbosity in the example and confirmation-report sections.

Suggestions

Trim the full confirmation-report mockup in Step 8 to a compact bullet list of fields to report, reducing token weight.

Remove the standalone DO/DON'T Best Practices section or fold its unique items into the relevant workflow steps to eliminate repetition.

Condense the 14-step Example Usage to the 3-4 most illustrative steps to avoid re-walking the entire workflow.

DimensionReasoningScore

Conciseness

The ~290-line body is mostly efficient and actionable, but includes padding — the full emoji confirmation-report mockup, a redundant DO/DON'T Best Practices section that repeats earlier guidance, and a 14-step worked example — that could be trimmed without losing clarity.

2 / 3

Actionability

Provides concrete commands ('cat references/analysis_checklist.md', 'mkdir -p .github/'), a specific placeholder-to-source mapping table, a conversion table, and explicit validation checklists — copy-paste ready guidance for an instruction-only skill.

3 / 3

Workflow Clarity

A clear 8-step sequence with an intent-validation decision tree (STOP conditions), validation checklists in Steps 4 and 6, and explicit feedback loops ('If validation fails: Trim content before writing'; 'If user doesn't respond: Use best judgment').

3 / 3

Progressive Disclosure

The body is an overview that signals four one-level-deep reference files (analysis_checklist.md, positive_constraints_patterns.md, instruction_template.md, context_economics.md) via explicit cat commands at the correct step, all of which exist in ./references/, with a Resources section summarizing each.

3 / 3

Total

11

/

12

Passed

Description

60%Weight 40%Scale 1-3

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 concrete about capabilities, but lacks an explicit 'Use when' trigger clause and leans on the technical filename rather than natural user language, limiting trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when generating global Copilot/repo instructions, or when the user asks to create .github/copilot-instructions.md').

Include common user-facing variations such as 'repo instructions', 'copilot instructions', and 'repository constitution' rather than only the filename.

Distinguish from sibling skills by noting global scope (e.g., 'For global instructions; use generate-path-instructions for path-specific rules').

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generates the global repository constitution file (.github/copilot-instructions.md)', 'Performs LLM-driven deep repository analysis including docs, code patterns, build systems, documentation generators, and data schemas', and 'Enforces positive constraints and no hardcoded secrets'.

3 / 3

Completeness

Thoroughly answers 'what does this do' but has no 'Use when...' clause or explicit trigger guidance, which caps completeness at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Contains relevant terms like 'repository', 'code repositories', and 'copilot-instructions' but relies on the technical filename rather than natural phrases a user would say, and omits common variations like 'repo instructions' or 'generate copilot instructions'.

2 / 3

Distinctiveness Conflict Risk

Targets a specific file and niche, but the description does not disambiguate global vs path instructions and 'repository analysis' overlaps with the sibling generate-path-instructions skill referenced in the body.

2 / 3

Total

9

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
canonical/copilot-collections
Reviewed

Table of Contents

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.