CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A tight, well-structured instruction-only skill whose main strength is a clearly sequenced 5-phase workflow with explicit validation and feedback loops. Actionability and conciseness are strong with only minor room to tighten redundant restatements.

Suggestions

Collapse or remove the 'Key Rules' section since its rules already appear verbatim in the phase descriptions, reducing redundancy.

Add one or two concrete commands or a short example for 'Binary search' and '5 Whys' so the named techniques become fully executable.

Trim the opening Overview sentence about agents guessing and spiraling to a single clause; the protocol itself conveys the value.

DimensionReasoningScore

Conciseness

Largely lean with directive phases and a compact bug-type table, but the Overview sentence and the 'Key Rules' section partly restate protocol constraints already stated in the phases, leaving minor trim opportunities (anchor 4).

4 / 5

Actionability

Concrete, executable directives throughout ('Run the failing command/test', 'Add diagnostic logging marked `// DEBUG`', 'git bisect', 'run 5+ times', an exact phrase to state to the user); a few techniques like 'Binary search' and '5 Whys' are named without specifics, so just short of fully copy-paste ready (anchor 4).

4 / 5

Workflow Clarity

Five explicitly numbered phases with clear sequencing and explicit validation checkpoints: a user-confirmation gate in Phase 3 and a verify-and-loop-back feedback loop in Phase 5 ('If verification fails... go back to Phase 2'), plus a Key Rules checklist, matching anchor 5.

5 / 5

Progressive Disclosure

A single, well-organized file with clear section headers (Overview, When to Use, Protocol, Bug-Type Strategies, Key Rules) and no nested references; at this size no external reference files are needed, so easy navigation earns anchor 5.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong, third-person description that clearly pairs a 'Use when' trigger with concrete mechanics. It is specific and complete; only slightly limited trigger-term variety and the broad 'any bug' scope keep it from the top marks.

DimensionReasoningScore

Specificity

Names the domain and several concrete mechanisms ('Enforces a 5-phase protocol', 'code edits are blocked until root cause is confirmed', 'Prevents premature fix attempts'); not a comprehensive enumeration of all actions, so below the anchor 5.

4 / 5

Completeness

Explicitly answers both: a clear 'Use when debugging any bug' trigger and a concrete statement of what it does ('Enforces a 5-phase protocol where code edits are blocked until root cause is confirmed'), matching the anchor 5 pattern.

5 / 5

Trigger Term Quality

'Use when debugging any bug' supplies the two most natural terms a user would say ('debugging', 'bug'); good coverage though common synonyms like 'error', 'failing test', or 'regression' are absent, keeping it at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The 5-phase blocked-edit protocol is a distinct niche, but the trigger 'debugging any bug' is broad and could overlap with general debugging skills, so mostly distinct with minor overlap risk (anchor 4).

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.