Name: phase-gated-debugging
Rating: 60.8 (1 reviews)
Author: administrakt0r

phase-gated-debugging

Use when debugging any bug. Enforces a 5-phase protocol where code edits are blocked until root cause is confirmed. Prevents premature fix attempts.

Quality

71%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/phase-gated-debugging/SKILL.md

The canonical home for this skill is phase-gated-debugging in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

81%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 strong instruction-only skill with an exceptionally clear workflow that enforces disciplined debugging through explicit phase gates and validation checkpoints. The content is well-structured and mostly concise, with only minor verbosity in the introductory sections. The bug-type strategies table adds practical value, and the feedback loop from Phase 5 back to Phase 2 demonstrates thoughtful error recovery design.

Suggestions

Trim the overview paragraph — Claude doesn't need to be told why AI agents spiral; start directly with the protocol purpose.

Consider adding a brief concrete example of a // DEBUG diagnostic line to make Phase 2 more immediately actionable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient. The overview paragraph explaining why AI agents spiral is slightly unnecessary (Claude knows this), and the 'When to Use' section is somewhat verbose. But the protocol itself is lean and well-structured with minimal padding.	4 / 5
Actionability	Provides concrete, specific steps for each phase with clear constraints (e.g., 'Only // DEBUG marked logging is allowed'). The bug-type strategies table adds actionable techniques. However, there are no executable code examples or specific commands — this is acceptable for an instruction-only skill, but the guidance could be slightly more concrete (e.g., example debug logging syntax, example git bisect command).	4 / 5
Workflow Clarity	Excellent 5-phase sequence with explicit validation checkpoints: user confirmation gate at Phase 3, verification at Phase 5, and a feedback loop back to Phase 2 if verification fails. The constraints at each phase are clearly stated, and destructive operations (code edits) are explicitly blocked until confirmation.	5 / 5
Progressive Disclosure	Well-structured with clear sections (Overview, When to Use, Protocol phases, Bug-Type Strategies, Key Rules). References the full plugin repo for deeper enforcement. No bundle files exist, but the skill is under 50 lines of core content and is well-organized. Minor gap: the bug-type strategies table could potentially be a separate reference for complex cases, but it's short enough to be inline.	4 / 5
	Total	17 / 20 Passed

Description

62%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 communicates a clear methodology (structured debugging with a gated protocol) and includes an explicit 'Use when' clause, which is good. However, it lacks specificity about what the 5 phases entail and misses many natural trigger terms users would use when encountering bugs (e.g., 'error', 'troubleshoot', 'not working'). The scope is also very broad ('any bug') which could benefit from more nuance.

Suggestions

Add common trigger term synonyms like 'error', 'issue', 'troubleshoot', 'crash', 'not working', 'broken' to improve matching when users describe problems naturally.

Briefly enumerate or summarize the 5 phases (e.g., 'reproduce, isolate, diagnose root cause, fix, verify') to increase specificity and help Claude understand when this structured approach is appropriate versus simpler debugging.

Dimension	Reasoning	Score
Specificity	Names the domain (debugging) and describes a concrete mechanism (5-phase protocol, blocking code edits until root cause confirmed), but doesn't enumerate what the 5 phases are or what specific debugging actions are performed.	3 / 5
Completeness	Has a clear 'when' ('Use when debugging any bug') and a reasonable 'what' (enforces 5-phase protocol, blocks edits until root cause confirmed, prevents premature fixes). The 'when' is explicit but very broad ('any bug'), and the 'what' could be more detailed about the phases.	4 / 5
Trigger Term Quality	Includes 'debugging' and 'bug' as natural trigger terms, but misses common synonyms and variations like 'error', 'issue', 'fix', 'troubleshoot', 'crash', 'broken', 'not working', which users would naturally say.	3 / 5
Distinctiveness Conflict Risk	The specific mention of a '5-phase protocol' and 'blocking code edits until root cause is confirmed' creates a distinctive methodology that differentiates it from generic debugging or coding skills. Minor overlap risk with other debugging-related skills, but the structured protocol approach is fairly unique.	4 / 5
	Total	14 / 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: plugins/AI-Agents-Safe-Coding-Skills/skills/phase-gated-debugging/SKILL.md
Commit: 57c135b

Reviewed: 3 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.