coding-agents-prompt-authoring

To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.

Quality

65%

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 ./instructions/r2/core/skills/coding-agents-prompt-authoring/SKILL.md

Quality

Content

71%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 content is a well-structured, reference-driven overview with strong progressive disclosure and a clear sequenced workflow. Its main weakness is a principles section that re-explains concepts Claude already knows, slightly hurting token efficiency.

Suggestions

Trim the core_principles list to only non-obvious or project-specific principles, assuming Claude's knowledge of SRP/DRY/KISS/YAGNI.

State the key validation/simulation checkpoints inline (e.g., 'validate before returning target prompt') rather than only implying them via reference file names.

Consider one inline mini-example of the logical flow applied to a single small prompt, to make the abstract sequence immediately concrete.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullets with detail delegated to references, but the core_principles list restates SRP/DRY/KISS/YAGNI/MECE/MoSCoW/SMART — concepts Claude already knows — adding unnecessary tokens.	3 / 5
Actionability	Concrete guidance via explicit 'ACQUIRE <path> FROM KB' commands for each phase plus a named logical flow gives mostly executable direction with only minor gaps in inline specifics.	4 / 5
Workflow Clarity	A clear sequenced flow (discover → extract+intake → blueprint → draft→hardening→edit → simulate → validate) with review/simulate checkpoints is present, though some validation checkpoints are delegated to reference files rather than stated inline.	4 / 5
Progressive Disclosure	The body is an overview that points to well-signaled, one-level-deep reference and asset files, all of which exist in the bundle, making navigation easy and the split appropriate.	5 / 5
	Total	16 / 20 Passed

Description

58%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 conveys a clear, fairly specific capability set for prompt authoring/review/validation but omits any explicit "Use when…" trigger guidance, capping its completeness and trigger quality. It is distinct as a niche but would benefit from concrete trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when authoring, reviewing, porting, or validating prompts, skills, agents, workflows, or rules').

Include common synonyms users say (e.g., 'write', 'rewrite', 'refactor', 'port', 'migrate') alongside the current verbs to broaden trigger coverage.

Tie the 'when' explicitly to scenarios like porting prompts between agents/IDEs or migrating rule formats, which are currently buried in the body.

Dimension	Reasoning	Score
Specificity	Names the prompt-engineering domain plus four concrete verbs ("author, adapt, review, and validate") and concrete artifacts ("brief, contracts, and a validation pack"), listing several specific actions with only minor coverage gaps.	4 / 5
Completeness	The "what" is clear (author/adapt/review/validate prompts), but there is no "Use when…" clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant nouns ("prompts, skills, agents, workflows, rules") are present but common natural synonyms and trigger phrasing users would actually say are largely missing, so coverage is partial rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	It occupies a clear meta-prompt-engineering niche with distinct triggers, with only minor overlap risk against closely related general coding-assistant skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: griddynamics/rosetta
Path: instructions/r2/core/skills/coding-agents-prompt-authoring/SKILL.md
Commit: 044d86c

Reviewed: 21 hours 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.