claude-code-usage

[AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strategies, and Foundry-specific workflows. Trigger: beginning of any new conversation or coding session in a Solidity/Foundry project.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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-organized and highly actionable, with executable forge/git commands and copy-paste meta-prompting templates. Its weaknesses are mild verbosity from generic prompting advice and a long worked example, implicit rather than explicit validation feedback loops, and a monolithic structure with no progressive disclosure.

Suggestions

Trim the generic Do/Avoid prompting advice (Claude already knows to ask for specific paths) and shorten the four-round staking example to the essential rounds.

Add an explicit validate-then-retry feedback loop for the git workflow (e.g., "run forge test; if it fails, fix and re-run before committing").

Move the full meta-prompting worked example into a reference file (e.g., references/meta-prompting.md) and keep SKILL.md as an overview that links to it, enabling one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	It is table-driven and does not explain what Foundry/Solidity is, but the generic prompting advice ("Give specific paths", "Vague references: which one?") and the lengthy four-round staking-contract worked example are content Claude largely already knows or could be tightened, matching the "mostly efficient but could be tightened" anchor rather than the lean level-3.	2 / 3
Actionability	Provides copy-paste-ready, executable commands ("forge fmt && forge test", "forge test --match-test <name> -vvvv", "git diff before committing") and exact meta-prompting templates, fully meeting the "executable code/commands, specific examples, copy-paste ready" anchor; not level 2 because no key details are missing.	3 / 3
Workflow Clarity	Sequences are present (the meta-prompting Step 1-4 flow and the Foundry before/after table) and some validation commands exist (forge build, forge test, git diff), but for destructive/batch operations like git commits there is no explicit feedback loop ("if validation fails, fix and re-run"), which caps it at level 2 per the rubric's destructive-operation note.	2 / 3
Progressive Disclosure	It is a single ~130-line monolithic file with clear section headers but no external references at all; the detailed meta-prompting worked example and Quick Command Reference are inline content that could be split out, matching the "some structure but content that should be separate is inline" anchor rather than a one-level-deep reference structure.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 has an explicit trigger clause and names a domain niche, but it over-claims mandatory auto-invocation for every session and relies on generic category labels rather than concrete actions or natural user trigger phrases. This leaves it mid-range across all dimensions.

Suggestions

Replace the generic "Covers context management, task strategies" with concrete actions (e.g., "Plans multi-file refactors, clears context between tasks, runs forge fmt/test gates").

Drop the "[AUTO-INVOKE] MUST be invoked at the START" over-claim and use a conditional "Use when..." trigger tied to a real user need (e.g., "Use when starting a Foundry/Solidity task that spans multiple files or needs a plan").

Add natural trigger terms users would actually say ("Foundry", "forge test", "Solidity refactor", "/plan") to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names domains ("context management, task strategies, and Foundry-specific workflows") but the only action verb is the generic "Covers", with no concrete operations like the score-3 example's "extract/fill/merge"; it is not a level-1 "Helps with documents" because three concrete domains are enumerated.	2 / 3
Completeness	It states both what ("Covers context management...") and a when ("Trigger: beginning of any new conversation or coding session"), but the "when" is a blanket auto-invoke for every session rather than the specific conditional trigger ("Use when...") shown in the level-3 anchor, and the over-claim weakens it below 3.	2 / 3
Trigger Term Quality	Contains the relevant domain keyword "Solidity/Foundry project" but the actual trigger phrase "beginning of any new conversation or coding session" is an auto-invoke timing condition rather than something a user would naturally say, so it does not reach the natural-term coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The Foundry/Solidity niche gives it some specificity, but the generic "context management, task strategies" scope combined with the claim that it "MUST be invoked at the START of each new coding session" would cause it to overlap/conflict with nearly every other coding skill, keeping it below the clear-niche level 3.	2 / 3
	Total	8 / 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: NeverSight/skills_feed
Commit: 26d37ce

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.