CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

focused-fix

Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix <feature-path>

60

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cmd-focused-fix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

The body is an exemplar of an instruction-only skill: a tightly ordered 5-phase protocol with explicit feedback loops, stop conditions, and verification gates, delivered with almost no wasted tokens. Its only gaps are a few underspecified diagnostic directives and slightly ambiguous pointers to a nonexistent fuller version of the skill.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — phase instructions, a compact manifest template, the Iron Law, and the 3-Strike Rule all earn their tokens, with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching the anchor for a maximally efficient skill.

5 / 5

Actionability

Mostly executable guidance: 'Fix in this EXACT order', 'Fix ONE issue at a time, run related test after each', 'Search entire codebase for imports from this feature', and concrete risk tiers (HIGH/MED/LOW with caller counts). A few directives remain abstract — 'search error logs' and 'check coverage' give no specifics on which logs or how — keeping it just below fully copy-paste-ready. Anchor 4.

4 / 5

Workflow Clarity

The 5-phase protocol is explicitly ordered ('Execute ALL 5 Phases IN ORDER') with genuine feedback loops: 'If a fix breaks something else → go back to DIAGNOSE', the 3-Strike Rule stop condition, the Iron Law gating fixes on completed diagnosis, and a dedicated VERIFY phase running the full test suite. This matches the anchor 'clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

Well-organized sections at ~86 lines with no monolithic content and one-level-deep 'Related Skills' pointers. Held at anchor 4 rather than 5 because the 'engineering/focused-fix — Full SKILL.md' pointer reads as an ambiguous self-reference and no bundle files exist to back the referenced detailed checklists and templates.

4 / 5

Total

18

/

20

Passed

Description

53%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.

The description communicates a clear niche (whole-feature repair) with a decent 'what', but it is generic about the actual actions performed and completely lacks 'when to use' trigger guidance — 'Usage:' syntax does not substitute for it. It sits squarely at the midpoint of the rubric.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g. 'Use when the user asks to fix, repair, or debug an entire feature or module, or when a feature is broken across multiple files.'

Enumerate the concrete actions instead of 'systematically fix' — e.g. 'maps the feature's files, traces inbound/outbound dependencies, diagnoses all issues, and fixes them in risk order with tests after each fix.'

Include natural synonyms users would say, such as 'broken feature', 'module repair', or 'fix this feature', so the skill triggers on real user phrasing rather than only on the slash-command name.

DimensionReasoningScore

Specificity

Names the domain (feature/module repair) and scopes the action to 'all its files and dependencies', but enumerates no concrete actions such as mapping scope, tracing dependencies, diagnosing, or verifying. This matches the anchor 'names domain and 1-2 concrete actions, but not comprehensive', not level 4 which requires several specific listed actions.

3 / 5

Completeness

The 'what' is clear ('systematically fix an entire feature/module across all its files and dependencies') but there is no 'when' clause — 'Usage: /focused-fix <feature-path>' is syntax, not trigger guidance. Per the judging guidelines, a missing 'Use when...' clause or equivalent explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ('feature repair', 'fix', 'module', 'dependencies') but common natural variations users would actually say ('broken feature', 'fix this module', 'feature is broken across files') are missing, and 'Usage: /focused-fix <feature-path>' is invocation syntax rather than a trigger term. Fits anchor 3: some relevant keywords but missing common variations or synonyms.

3 / 5

Distinctiveness Conflict Risk

'Deep-dive feature repair' carves a clear niche (repairing an entire feature/module) distinct from single-bug debugging skills, with only minor overlap risk against general debugging/refactoring skills. Not level 5 because the description lacks distinctive trigger phrases that would eliminate overlap entirely.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

.gemini/skills/cmd-focused-fix/SKILL.md

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.