verification-before-completion

Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.

Quality

43%

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/verification-before-completion/SKILL.md

Quality

Content

70%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-intentioned behavioral/process skill with a clear core message and good workflow structure. Its main weakness is repetition — the same 'verify before claiming' message is conveyed through overlapping tables, lists, and examples that could be consolidated. The Gate Function and Key Patterns sections are strong, but the Rationalization Prevention and Red Flags sections largely duplicate each other and the Common Failures table.

Suggestions

Merge the 'Red Flags', 'Rationalization Prevention', and parts of 'Common Failures' into a single concise section to eliminate redundancy and reduce token usage by ~30%.

Remove the duplicate 'When to Use' section at the bottom of the file.

Consider consolidating the motivational framing ('Why This Matters') — the failure memories add value but the quoted phrases could be trimmed to just the key lessons learned.

Dimension	Reasoning	Score
Conciseness	The skill has significant repetition — the 'Common Failures' table, 'Red Flags', and 'Rationalization Prevention' table all overlap substantially in conveying the same message. The 'When to Use' section appears twice. However, the tables and patterns are reasonably structured and not explaining concepts Claude doesn't know. Could be tightened by ~40%.	3 / 5
Actionability	The Gate Function provides a clear, concrete 5-step process. The Key Patterns section gives specific ✅/❌ examples showing exactly what to do vs. not do. However, the guidance is procedural/behavioral rather than code-executable — the 'commands' referenced are generic placeholders like '[Run test command]' rather than specific commands, which is appropriate for a meta-skill but slightly reduces actionability.	4 / 5
Workflow Clarity	The Gate Function is a clear, sequenced workflow with explicit validation checkpoints and a feedback loop (step 4: if NO, state actual status; if YES, proceed). The regression test pattern includes a full red-green verification cycle. For a behavioral/process skill, this is exceptionally well-sequenced with clear decision points.	5 / 5
Progressive Disclosure	The content is structured with clear headers and tables, but it's somewhat monolithic — the Common Failures table, Red Flags, Rationalization Prevention, and Key Patterns could potentially be consolidated or split. There are no bundle files or external references. The duplicate 'When to Use' section suggests organizational issues. For a standalone skill of this length (~100 lines of substantive content), the structure is adequate but not optimally organized.	3 / 5
	Total	15 / 20 Passed

Description

16%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.

This description reads as a behavioral guardrail or meta-instruction rather than a skill description. It lacks any concrete actions or domain specificity, and its trigger conditions are so broad ('ANY positive statement about work state') that it would conflict with virtually every other skill. The description fails to communicate what specific capability this skill provides.

Suggestions

Define concrete actions this skill performs (e.g., 'Runs verification checks on completed work, validates outputs against requirements, confirms file changes were saved correctly').

Narrow the trigger conditions to specific, distinguishable scenarios (e.g., 'Use when verifying code changes, checking build results, or confirming deployment status') rather than matching on 'ANY positive statement'.

Reframe from a behavioral constraint into a capability description — describe what the skill does rather than what behavior it prohibits.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions or capabilities. It describes a behavioral constraint ('claiming work is complete without verification is dishonesty') rather than any specific skill actions like processing, analyzing, or generating something.	1 / 5
Completeness	The 'what' is vague — it seems to be about verification before claiming completion, but this is not clearly stated as a capability. There is a 'when' clause ('Use when ANY variation of success/completion claims...'), but it is overly broad and describes internal Claude behavior rather than user-facing triggers.	2 / 5
Trigger Term Quality	The trigger terms are extremely broad and generic — 'success/completion claims', 'expression of satisfaction', 'positive statement about work state' are not natural user phrases. These are internal behavioral triggers rather than terms a user would naturally say.	2 / 5
Distinctiveness Conflict Risk	This description would trigger on virtually any task completion scenario across all skills. 'ANY expression of satisfaction' or 'ANY positive statement about work state' would conflict with every other skill that involves completing work, making it extremely non-distinctive.	1 / 5
	Total	6 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/verification-before-completion/SKILL.md
Commit: 900c504

Reviewed: 5 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.