create-instructions

Create an instructions file (.instructions.md) for a project rule or convention.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./extensions/copilot/assets/prompts/skills/create-instructions/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

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

The body is a concise, well-structured instruction-only skill with a clear three-phase workflow, concrete clarify questions, and a feedback loop, plus a cleanly signaled single external reference. It falls just short of top marks on actionability and workflow clarity for not specifying where/how to save the file or how to verify it works.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean, assumes Claude's competence, and adds only project-specific process knowledge; the only padding is minor redundancy (the agent-customization pointer appears both at the top and in the closing line, and "Guide the user to create an instructions file" restates the description). It is not a 5 because of those trimmable repetitions, and well above a 3 since nothing explains concepts Claude already knows.	4 / 5
Actionability	Guidance is concrete for an instruction-only skill: specific extraction targets (corrections, enforced patterns, project conventions), explicit clarify questions, and a three-step iterate loop. It is not a 5 because "Draft the instruction and save it" omits where to save it and what shape it takes, deferring entirely to the external instructions.md rather than showing even one example.	4 / 5
Workflow Clarity	The Extract → Clarify → Iterate sequence is clear, with a conditional checkpoint ("If no clear rule emerges from the conversation, clarify") and a genuine feedback loop (draft, identify ambiguous parts, ask, finalize). It is not a 5 because there is no explicit validation that the saved file is correctly placed or effective, and not a 3 because the sequence and checkpoints are explicit and coherent.	4 / 5
Progressive Disclosure	This is a sub-50-line skill with no bundle files, and the body is cleanly organized into well-labeled sections; its single external dependency (instructions.md from agent-customization) is clearly signaled at the very top and is one level deep. Per the rubric's simple-skill exception this matches the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clear, third-person, and names a concrete artifact, but it states only a single action and completely lacks a 'when to use' trigger clause, capping completeness. Trigger term coverage is adequate but misses natural user phrasings. Overall a serviceable but under-specified description.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to enforce a project rule or convention, or asks to make the agent always/never do something."

Enumerate the concrete actions the skill performs, e.g., "Extracts rules from conversation corrections, drafts and iterates on the file with the user, and suggests example prompts to verify it."

Include natural synonyms users would say — "coding style", "standards", "enforce a rule" — alongside "project rule or convention" to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Create an instructions file (.instructions.md) for a project rule or convention" names the concrete artifact and its purpose, but lists only one action with no elaboration of what the skill actually does (extract, draft, refine), matching the 'domain plus 1-2 concrete actions, not comprehensive' anchor. It is not a 4 because there is no list of several specific actions, and not a 2 because the action named is concrete rather than generic.	3 / 5
Completeness	The 'what' is clear (create an instructions file for a project rule or convention), but there is no 'Use when...' clause or any explicit 'when' trigger, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' is specific rather than vague; it is not a 4 because 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	Relevant keywords like "instructions file", ".instructions.md", "project rule", and "convention" are present, but common natural variations users would say ("enforce a style", "always/never do X", "coding standard", "customization") are missing. It sits between 'some relevant keywords' (3) and 'good keyword coverage' (4) but leans to 3 because there is no trigger guidance at all to surface those natural phrases.	3 / 5
Distinctiveness Conflict Risk	The ".instructions.md" artifact and the project-rule/convention framing give it a fairly distinct niche with only minor overlap risk against closely related skills (e.g., agent-customization, CLAUDE.md/init skills). It is not a 5 because 'rule or convention' is somewhat broad phrasing that a general coding-standards skill could also claim.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: extensions/copilot/assets/prompts/skills/create-instructions/SKILL.md
Commit: b0258bc

Reviewed: 5 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.