avoid-scope-creep

Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change. Only change what was explicitly asked.

Quality

80%

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 ./memory_data/skills/avoid-scope-creep/SKILL.md

Quality

Content

100%Weight 40%Scale 1-3

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 tight, well-structured instruction skill: concise, actionable, and clearly organized into pattern/rule/exception/anti-pattern. It fully respects token budget and gives Claude unambiguous, executable behavioral guidance.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what refactoring or scope creep is; every section (Mistake pattern, Rule, Exception, Anti-pattern) earns its place.	3 / 3
Actionability	Instruction-only yet concrete: 'Only change what was asked', 'mention them as a note rather than silently fixing them', and 'fix the minimum required dependency and explain why' give clear executable guidance, plus a concrete anti-pattern example.	3 / 3
Workflow Clarity	This is a simple single-purpose skill where the single action (restrict changes to what was asked) is unambiguous; per the simple-skills note, that qualifies for a 3 even without an explicit multi-step workflow.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, and content is organized into clearly labeled sections (Mistake pattern, Rule, Exception, Anti-pattern); per the simple-skills guideline this earns a 3 with well-organized sections and no bundle files needed.	3 / 3
	Total	12 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 concretely names the mistake pattern and its constituent actions, but omits an explicit 'when to use' trigger clause, which caps both completeness and distinctiveness. It is clear but not maximally scorable as a description.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when making a code change and tempted to also refactor or add unrequested features').

Broaden natural trigger terms to include phrases users actually say, like 'don't over-engineer', 'keep the change minimal', or 'scope creep'.

Reframe to start with the action ('Avoid doing unrequested work...') rather than 'Common mistake —', to make the skill's purpose and trigger more distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('refactoring, adding extra features, cleaning up style') tied to a specific change request, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the mistake is but only implies when to apply it; there is no explicit 'Use when...' trigger clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relevant terms like 'refactoring' and 'adding extra features' are present, but coverage is thin and lacks common phrasings a user would naturally say when invoking this, so it sits at the 'some relevant keywords' level rather than good coverage.	2 / 3
Distinctiveness Conflict Risk	The scope-creep focus is fairly specific, but without an explicit trigger the description could still overlap with general change-management guidance, placing it at 'somewhat specific but could overlap'.	2 / 3
	Total	9 / 12 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: aiming-lab/MetaClaw
Path: memory_data/skills/avoid-scope-creep/SKILL.md
Commit: 922caf3

Reviewed: 9 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.