self-modifying-code

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source. Use when designing UI for agent editability, deciding whether a file is safe for the agent to change, or when tempted to patch config, `.env`, or an `@agent-native/*` package. Do not load it for ordinary source edits.

Quality

100%

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

Quality

Content

100%

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 concise, actionable, and well-structured, with executable commands, a validated rollback workflow for risky edits, and clear single-level navigation to related skills. It assumes Claude's competence and adds only domain-specific guidance that Claude would not already know.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding explaining what git, typecheck, or package overrides are; every section earns its place.	3 / 3
Actionability	Provides fully executable commands ('pnpm typecheck && pnpm lint', 'git checkout -- <file>', 'agent-native upgrade') and concrete, copy-paste TS snippets for exposing UI state, plus a precise tier table.	3 / 3
Workflow Clarity	The Git Checkpoint Pattern is a clearly numbered sequence with an explicit validation step (typecheck/lint) and a revert feedback loop on failure, covering the risky source-edit operation fully.	3 / 3
Progressive Disclosure	A single self-contained file with well-organized sections and one-level cross-links to related skills by name; no monolithic wall or nested references, so it is easy to navigate.	3 / 3
	Total	12 / 12 Passed

Description

100%

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, well-triggered, and clearly scoped to a distinct niche, explicitly stating both what the skill covers and when to use it (and when not to). It is concise without fluff and reads naturally as something that would be invoked for this exact situation.

Dimension	Reasoning	Score
Specificity	Names concrete, specific concepts and actions ('tiers, checkpoints, and off-limits paths', 'editing the app's own source', 'deciding whether a file is safe') rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (tiers, checkpoints, off-limits paths) and 'when' via a clear 'Use when...' clause, plus a negative trigger ('Do not load it for ordinary source edits').	3 / 3
Trigger Term Quality	Covers natural trigger terms a user or Claude would say when needing this skill ('designing UI for agent editability', 'patch config', '.env', '@agent-native/*'), spanning multiple phrasings.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (an agent editing an app's own source within an agent-native framework) with distinctive triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/self-modifying-code/SKILL.md
Commit: e9a2f0e

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.