aif-fix

Fix a bug or problem. Supports fix-now or plan-first; no args executes FIX_PLAN.md. When a regression check is needed, reproduce first, then implement and rerun it. Adds logging and suggests extra coverage.

Quality

68%

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/aif-fix/SKILL.md

Quality

Content

70%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 a well-sequenced, highly actionable workflow with strong validation checkpoints, but it is repetitive in places and monolithic — templates and examples that belong in separate reference files are all inlined.

Suggestions

Move the FIX_PLAN.md template, patch template, and worked examples into separate reference files under ./references/ and link to them one level deep to improve progressive disclosure.

De-duplicate the handoff_sync_status call signatures and the regression-first policy restatements by defining them once and referencing them from later steps.

Trim explanatory passages that restate why logging or root-cause analysis matters, since they assume Claude lacks knowledge it already has.

Dimension	Reasoning	Score
Conciseness	Mostly operational and useful, but noticeably repetitive: the regression-first policy and near-identical handoff_sync_status call signatures are restated at multiple steps, and a few sections explain why logging helps as if Claude does not know.	3 / 5
Actionability	Provides concrete, executable guidance throughout — bash commands, copy-paste FIX_PLAN and patch templates, logging code, and exact MCP call field names — with only minor placeholder gaps in the Explore agent prompts.	4 / 5
Workflow Clarity	Clear sequenced steps (0 through 6) with explicit validation checkpoints and feedback loops: the Canonical Regression-First Policy enforces reproduce -> confirm fail -> fix -> rerun -> confirm pass, plus a fix checklist.	5 / 5
Progressive Disclosure	Good internal section structure, but no bundle files exist and large referenceable content (FIX_PLAN template, patch template, examples) is inlined in one monolithic SKILL.md with no external file navigation.	3 / 5
	Total	15 / 20 Passed

Description

67%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 is specific and action-rich, naming the workflow modes and concrete behaviors, but it lacks an explicit 'when to use' trigger clause and its trigger phrasing is broad enough to risk overlap with related skills.

Suggestions

Add an explicit 'Use when ...' clause naming the natural trigger phrases (e.g. 'Use when the user reports a bug, error, or regression and wants it fixed').

Narrow the trigger surface from 'Fix a bug or problem' to bug/regression-specific language to reduce overlap with general coding and review skills.

Include common synonyms users say ('error', 'crash', 'broken', 'regression') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions with comprehensive coverage: 'fix-now or plan-first', 'executes FIX_PLAN.md', 'reproduce first, then implement and rerun it', 'Adds logging', 'suggests extra coverage'.	5 / 5
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; the 'when' is only weakly implied.	3 / 5
Trigger Term Quality	Good natural keywords ('Fix a bug', 'problem', 'regression check', 'reproduce') but missing common synonyms and file-extension-style trigger variations that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	The regression-first/FIX_PLAN/patch identity is fairly distinct, but the bare trigger 'Fix a bug or problem' is broad and could overlap with general debugging, code-review, or security-review skills.	3 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (662 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-fix/SKILL.md
Commit: ac92beb

Reviewed: 4 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.