coding

Best practices for code editing, search, and file operations

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 ./skills/coding/SKILL.md

Quality

Content

100%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 well-structured, lean set of actionable coding-discipline directives culminating in a clearly sequenced verification workflow with feedback loops. It assumes Claude's competence and adds only non-obvious guidance, with no padding or concept re-teaching.

Dimension	Reasoning	Score
Conciseness	The body is lean directive bullets with no over-explanation of concepts Claude already knows (no 'what a function is', no library tutorials); every line states a concrete practice, fitting the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Guidance names specific tools and behaviors throughout ('Prefer apply_patch over write_file', 'Use glob for file discovery', 'use grep to search for all occurrences'); as an instruction-only skill, the absence of code blocks is not penalized because the guidance is concrete and actionable, matching the top anchor.	5 / 5
Workflow Clarity	The 'Verify Before You Finish' section is an explicit sequenced workflow with validation checkpoints and feedback loops (reproduce -> re-run -> run existing tests -> 'a test you broke is your bug' -> re-read diff), satisfying the top anchor; destructive/batch code-editing work has its required verification present, so no cap applies.	5 / 5
Progressive Disclosure	The skill is ~45 lines (under 50), has no bundle files, and is organized into clearly headed sections (Tool Usage, Code Change, Code Quality, Verify), so the simple-skill exception grants the top score for well-organized sections with no need for external references.	5 / 5
	Total	20 / 20 Passed

Description

32%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 a terse tagline that names broad domains but gives no concrete actions, no usage trigger, and high overlap risk with general coding skills. It needs an explicit 'Use when ...' clause and specific verbs to reach the mid-range anchors.

Suggestions

Replace generic framing with concrete actions, e.g. 'Edits, refactors, searches, and renames code across files using apply_patch, grep, and glob.'

Add an explicit trigger clause: 'Use when the user asks to edit, refactor, fix, search, or rename code or files.'

Narrow the scope or add distinctive triggers (e.g. 'apply_patch', 'minimal diff', 'verify-before-finish') to reduce overlap with a general coding skill.

Dimension	Reasoning	Score
Specificity	The phrase 'Best practices for code editing, search, and file operations' names three activity domains but describes no concrete actions — 'best practices for' is generic framing comparable to 'Processes PDF files', so it sits at the domain-named-but-generic level rather than the 3-anchor which requires 1-2 concrete actions.	2 / 5
Completeness	It offers only a vague 'what' ('best practices for ...') and no 'when'/Use-when clause at all, fitting the 'vague what and no when' anchor; the missing-trigger-guidance cap at 3 does not raise it above this anchor.	2 / 5
Trigger Term Quality	'code editing' and 'search' are reasonably natural terms a user might say, but 'file operations' is generic jargon and common variations/synonyms (refactor, debug, implement, fix bug) are absent, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'code editing, search, and file operations' is very broad and would overlap with nearly any general development/coding skill, matching the 'very broad; high overlap risk' anchor rather than the more-narrowed 3-anchor.	2 / 5
	Total	9 / 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: nearai/ironclaw
Path: skills/coding/SKILL.md
Commit: 94b7187

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.