debug-false-positive

Diagnose and fix a Fallow false positive or false negative through extraction, resolution, graph, analysis, reporting, and real-consumer verification.

Quality

66%

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 ./.claude/skills/debug-false-positive/SKILL.md

Quality

Content

76%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 admirably concise, well-sequenced debugging workflow with built-in verification steps, but several steps give direction rather than the concrete commands or code needed to execute them, and validation checkpoints are implicit rather than explicit gates.

Suggestions

Add the specific commands or code for the abstract steps, e.g. the exact 'trace' command(s) and how to 'fix the earliest incorrect layer'.

Make validation checkpoints explicit pass/fail gates (e.g. 'Only proceed to step 7 if the real-consumer output matches expectations').

Add a brief error-recovery loop for the real-consumer comparison step, noting what to do when old vs new output still diverges.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean (~16 lines), assumes Claude's competence, and every line is an actionable instruction with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	It names concrete flags and paths ('--format json --quiet', '.fallow/', 'review') and a numbered procedure, but several steps are abstract ('Trace the finding through...', 'Fix the earliest incorrect layer') without the specific commands or code to execute them.	3 / 5
Workflow Clarity	A clear 7-step sequence with built-in verification (reproduce, regression test, real-consumer comparison, reviewer run), though validation checkpoints are implicit rather than explicit pass/fail gates and error-recovery loops are not spelled out.	4 / 5
Progressive Disclosure	This is a short single-purpose skill with no bundle files and no need for external references; the well-organized numbered structure satisfies the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

56%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 clearly states what the skill does and enumerates the pipeline layers, but it lacks any explicit 'when to use' trigger guidance and relies on domain jargon rather than natural user phrasing. It is specific and fairly distinct, yet incomplete on the trigger side.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a Fallow finding is wrong or missing and you need to locate the failing layer.'

Include natural-language trigger terms a user would actually say, such as 'wrong result', 'buggy finding', or 'missing finding'.

Consider noting file/output cues terms (e.g. '--format json', '.fallow/') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Diagnose and fix', 'extraction, resolution, graph, analysis, reporting, and real-consumer verification') naming the domain and a multi-stage pipeline, but the actions are high-level layer names rather than fully concrete verbs like the score-5 anchor.	4 / 5
Completeness	The 'what' is clearly stated (diagnose and fix a Fallow false result through the named layers), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Terms like 'false positive', 'false negative', 'reporting', and 'verification' are relevant, but it omits the natural phrases a user would say (e.g. 'wrong result', 'buggy finding') and offers no synonyms or filename cues.	3 / 5
Distinctiveness Conflict Risk	The Fallow-specific domain and the named layer chain make it mostly distinct from other skills, with only minor overlap risk against a general debugging skill.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .claude/skills/debug-false-positive/SKILL.md
Commit: 7e1e075

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.