CtrlK
BlogDocsLog inGet started
Tessl Logo

debug-false-positive

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

60

Quality

70%

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 ./.agents/skills/debug-false-positive/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured as a debugging checklist with genuine verification steps, but most steps give abstract direction rather than executable commands and the validation checkpoints are implicit. Adding concrete commands and explicit pass/fail gating would raise actionability and workflow clarity.

Suggestions

Provide executable commands for the abstract steps — e.g. the exact reduce/trace invocation and how to run the regression test — so guidance is copy-paste ready.

Make verification explicit with pass/fail gating: state what a passing regression test or matching old-vs-new output means and what to do if it fails.

Clarify step 3's 'Trace the finding through extract, resolve, graph...' with the specific command or tool to run at each layer.

DimensionReasoningScore

Conciseness

Lean and efficient with no concept-explaining fluff; every line is an action and assumes Claude's competence, so each token earns its place.

3 / 3

Actionability

Some concrete guidance appears ('--format json --quiet', 'review'), but most steps describe rather than instruct ('Reduce to a minimal fixture', 'Fix the earliest incorrect layer') with no executable commands.

2 / 3

Workflow Clarity

A clear 1–7 sequence with verification present (regression test, old-vs-new comparison, reviewer run), but checkpoints are implicit and lack an explicit error-recovery feedback loop.

2 / 3

Progressive Disclosure

Under 50 lines with no external references needed; the single well-organized numbered list qualifies for a 3 under the simple-skill guidance.

3 / 3

Total

10

/

12

Passed

Description

67%

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 well-scoped to Fallow false results, but it omits explicit 'Use when' trigger guidance and leans on internal pipeline jargon rather than natural user phrasing. Adding a usage trigger clause would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a Fallow result is wrong — a finding that should not have been reported (false positive) or one that was missed (false negative).'

Replace internal-pipeline jargon ('extraction, resolution, graph, analysis') with terms users naturally say, or move them into the body and keep the description user-facing.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'Diagnose and fix', 'extraction, resolution, graph, analysis, reporting, and real-consumer verification' — rather than vague language.

3 / 3

Completeness

Clearly states what the skill does but lacks an explicit 'Use when...' clause; per the rubric, missing explicit trigger guidance caps completeness at 2.

2 / 3

Trigger Term Quality

'false positive or false negative' are natural user terms, but the remainder ('extraction, resolution, graph, analysis') is internal-pipeline jargon a user would rarely say, and common variations are missing.

2 / 3

Distinctiveness Conflict Risk

Scoped to a named product ('Fallow') and a specific outcome (false positive/negative), giving it a clear niche unlikely to trigger for the wrong skill.

3 / 3

Total

10

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fallow-rs/fallow
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.